BIG DATA ANALYTICS

Data Analytics: The Straight-Lined Labyrinth that Entrapped the HIM Profession – @ahimaint

Skills in data analytics are critical to the future of health information management (HIM), yet there has been considerable confusion regarding how to articulate what data analytics means for the profession. In a survey of more than 3,300 HIM professionals, skills in data analysis were ranked among the top five most important skills for future HIM practice.1 

Health Data Analytics and clinical terminology systems like SNOMED CT by Prof. Supten Sarbadhikari, @supten

Healthcare, with its inherent complexity, deals with large volumes of data coming in. Well designed and used EMRs (Electronic Medical Records) can collect huge amounts of data. However, neither the volume nor the velocity of data in traditional modern healthcare may qualify as big data now. Only a small fraction of the tables in an EMR database may be relevant to the current practice of medicine and its corresponding analytics use cases.

Healthcare Decoded – The #Analytics Conundrum by Harish Rijhwani, @Harish_Rijhwani

If we want to start using Analytics in India, one of the areas to focus on can be in the area of Diagnostic Analytics. We can leverage Transfer learning in this area as there are many pre-trained models leveraged by others and available. 

Data Analytics for cell and gene therapy by Dr. Ruchi Dass, @drruchibhatt

Cell and gene therapies are becoming more and more popular because of encouraging clinical results worldwide. Major pharma manufacturing companies have invested in the concept’s commercialization worldwide. Recently, we read about Takeda’s license for commercialization of Aloficel (developed by TiGenix), Celgene’s acquisition of Juno Therapeutics or Gilead’s acquisition of Kite Pharma.

A Data Scientist’s Experience in Decoding Chest Imaging by Vidya MS


The Chest Imaging Update 2018 held by the Narayana Health group, brought together over 150 radiologists, pulmonologists and doctors gathered to update and improve their knowledge in the reporting of Chest Imaging, both X-ray and CT. As a data scientist with keen interest in medical imaging, my aim was to get an inside look into the daily practice of medical professionals in detection and diagnosis of pulmonary diseases.


The conference opened with Dr. Vimal Raj, Conference chair and an accomplished Cardiothoracic Radiologist, stating that thoracic imaging is not reported well enough and there is a lot more value that a radiologist could add in the diagnosis to enable better treatment options for the patient. The flow of the subsequent sessions was extremely well constructed reflecting the everyday reporting workflow in the chest imaging space – starting from assessment of the humble chest X-ray to the CT followed by diagnosis and treatment plans. The second day was mainly focused on hands on sessions.
The first session of the day was conducted by Dr. Kishore Kumar from NH and Dr. Aparna Irodi from CMC Vellore on what never to miss on a chest X-ray and assessment of neonatal chest-X-rays. Dr. Kishore covered the important parts to access in a chest X-ray before reporting it as a normal one. One of the challenges that he brought out was that these areas are often easily missed and there is large amount of misdiagnosis made while assessing a chest X-ray which could led to significant impact later on for the patient. One case was presented where an early stage opacity, which could have been easily caught, progressed into a cancerous stage. There are a multitude of reasons for misdiagnosis, including, superimposition of thoracic structures, similarity in radiographic appearances of some chest diseases, and subtlety of some chest pathologies rendering them indistinguishable. Each chest X-ray takes a trained radiologist several minutes to review and given the ubiquitous nature of the X-ray in the imaging world, this often leads to significant increase in the workload. Another reason could be the variance of reporting across radiologists due to inconsistent terminologies.
The sessions then shifted towards the more complex CT imaging, where the physics and protocols behind the CT imaging were first introduced, followed by multiple sessions on reporting of lung cancer on a CT and standard definitions of chest patterns on CXR and CT to ensure better reporting.
Since the conference was focused on updating radiologists and how to better report their studies, the important question on why accurate reporting is needed was excellently handled by Dr. Murali Mohan. He walked through a comprehensive series of statistics conducted by various institutions, to explain why the importance of reporting accurately.
One of the highlights and most interesting sessions for the day for me, was the ‘Multi-Disciplinary Team’ panel featuring, Dr. Vimal Raj, Dr. Murali, Dr. Aparna, Dr. Rajani Bhat, Dr. Ranganatha R. They wonderfully presented how an MDT team conclude in diagnosis and determining a course of action when things are unclear. This was extremely insightful for an outsider like myself to truly understand the complications, uncertainties and how the various disciplines come together to define the best course of action for the patient.
Considering all the complications mentioned above, the variations in manifestations of the same medical condition across demographics, overlap of multiple patterns and mimic cases, many of these cases require significant expertise in the diagnosis of a thoracic scan. There is also a high variance in reporting across radiologists and the opinions are sometimes subjective especially in chest X-rays. Many of these uncertainties sometimes require a group of expertise to reach a consensus. In addition to these clinical challenges, developing an AI system to aid the reporting process requires large amounts of consistently reported data to truly learn the patterns on an image. Many of these systems also do not have access to much of the other patient information that may be pivotal in assessment. The difficulty in obtaining such large high-quality data makes it more complex to build these systems.
AI is still not there to diagnose the myriad of pathologies on a thoracic scan, primarily the chest X-ray though there have been many solutions claiming to detect a limited set of abnormalities. That being said, with the immense improvement in technology in the recent years, AI can certainly aid a radiologist in diagnosis and subsequently the treatment. The focus for AI models should be around aiding radiologists in repetitive tasks, ensuring that highly skilled expertise focuses on more complex and abnormal cases, detecting and highlighting unusual patterns in the image (especially those than can be easily missed), and also in providing clinical insights to a radiologist in the detection of abnormal regions.

Finally, I would like to thank the organizers of the Chest Imaging Update 2018. Overall, it was a wonderful experience for me to be in the midst of a large group of experts from various disciplines, interact with some of them to understand the key problem areas. 

The article was first published on the Author’s LinkedIn pulse Blog, its been re-published here with the Author’s permission. All ideas presented are author’s personal views

Author
Vidya S.M

Data Scientist at Philips. Data Scientist with a demonstrated history of working in the hospital & health care industry. Skilled in AI, image processing, & algorithms. Strong engineering professional with a Master’s degree focused in Machine Learning & AI from National University of Singapore.

Almighty Data or Hype? By INDERJITH DAVALUR @INDERDAVALUR

DIGITAL TRANSFORMATION AND THE PLACE FOR DATA


Mea Culpa, I am one of those who is guilty of getting on and staying on the Big Data wagon for the wrong reasons. “Data is the new oil” is an oft-repeated phrase. I am about to commit a “virtual” suicide by proclaiming that it is not so. Data has its place and it is not at the top of the digital food chain. I feel that we have crowned the half-naked prince, Emperor in haste.

For the sake of clarity, when I say data, I will be referring to digital data throughout this piece. Data is a by-product of any activity. Therefore, creating data is as natural as breathing. So we have data. A lot of data. So what? Accumulating data, structuring it, storing it, analyzing it are a natural progression from that point onwards. How and what we do with the data is more important. Software. 

The magic that is software, to me, is more transfixing. Consider the prospect of a language written in a semantic that is alien to our natural human language. A cryptic command, logic, condition, trigger – anything at all – that is magically read, understood and acted upon by silicon. Hardware that contains baked-in code that can parse and carry out complex instructions at blazing speeds. Pieces of such chips soldered on a board and communicating through ‘roadways’ of circuits laid out on a board. The miracle of hardware coupled with the magic that is software is what gets my adrenalin pumping. How can such a marvel not be exciting?

Even the awesomeness of hardware pales in comparison to software. Hardware is more or less static. It is confined to physical and functional dimensions. Software, however, is supreme. It can use the same hardware (with some limitations of course) and carry out simple tasks, entertain with games, or perform wildly complex calculations at very very high rates of speed, accurately all the time. And it can do this million million times with alacrity. This is just the beginning of what software can do. But wait, there’s more!

Consider intelligence in software. It suddenly becomes a living, breathing, dynamic being. Almost. Software can learn and teach itself. Crunching data and spitting out patterns and actionable analysis suddenly becomes mundane, banal almost pedestrian. No. I am not against data or big data. By itself, big data is just that. A monstrosity. Sometimes, big data actually gets in the way. Misleads us in making decisions quickly. Software breathes life into data. 

Take any software language or tool. Examine it. Study its flow, the eloquence, the nuance and its brilliance. Brevity in software coding is revered by programming perfectionists. There is elegance in a well-written piece of code that executes beautifully, perfectly, every time. Anyone that can find literary melody in Shakespeare or Milton can certainly begin to enjoy the harmony in a beautifully crafted software application code. So, my appeal goes out to all those who are worshipping big data to take a moment to reflect upon the joy that software brings to our daily lives. After all, the future is software!

Author
Inder Davalur

Inderjith Davalur is a healthcare technology specialist, speaker, writer and utopian dreamer.
Inder works with hospitals committed to transforming the healthcare paradigm with the aid of new innovative technologies. His primary area of interest lies in using data analytics and technologies such as Deep Learning to shift the current physician-driven healthcare model to a patient-driven market dynamic.
Inder focuses on the manifold ways in which data crunching and machine learning can lead to better diagnoses that can not only be made at the time of illness, but predicted way before any symptoms surface. The path ahead in the sector, he believes, lies in the deployment of evolving technologies that immensely influence both diagnostic and therapeutic aspects of healthcare, delivering real patient-driven, data-enabled, informed healthcare.
Inder currently works as the Group CIO at KIMS Hospitals Private Limited, Hyderabad and has previously assumed leadership roles at leading hospitals and companies, in India and the United States of America.

A PhD Researcher’s QnA on #BigDataAnalytics (BDA) with a Healthcare CIO by Inder Davalur, @INDERDAVALUR & Nishita Mehta


Q1. Nishita Mehta: What is data’s role in healthcare & how do you see it influencing future health sector growth in India?

A. Inder Davalur: 

Big Data Analytics (BDA) will have a huge role in healthcare. Healthcare has been a latecomer to using IT as a tool but the future looks good. AI and its children – ML, IoT, and M2M are excellent candidates for advancing technology in healthcare. There is a real potential for technology to advance what I have termed “Connected Continuum of Care” in one of my blogs. This means that with wearables and other Internet of Healthcare Things (IoHT), creating a biome where the patient and doctor/hospital are always connected would become a reality. Always-on Internet is the future and extending that to healthcare is a natural progression. With the price of Internet in India being one of the lowest in the world, we will be in an excellent position to incorporate technology in advancing healthcare delivery.   


Q2. Nishita Mehta: What are the unique challenges of working with clinical data? 

A. Inder Davalur: 

Doctors. Well, the challenge lies with the fact that most clinical data is unstructured. Doctors and hospitals are notorious for NOT wanting to follow standards when it comes to coding diagnoses and treatment. Adoption of DSM, Snomed, ICD codes is very spotty. Physicians complain about the inconvenience in the classifications and prefer to use free text in writing their diagnoses and treatment protocols. This creates a credibility gap in how clinical data can be meaningfully classified and analyzed for any useful prediction or AI driven protocols. EMR applications in India struggle with the similar challenges with physicians disagreeing on a set of standards in capturing and documenting clinical data. 

Q3. Nishita Mehta: Healthcare seems to be moving from the use of structured data to unstructured data. What is the difference between them when it comes to clinical utility & improving patient outcomes?

A. Inder Davalur:  

Healthcare has always suffered from a lack of structured data. Unstructured data creates several challenges in a software trying to classify the same diagnosis written with slight variations. The same fate awaits treatment plans. If medical coding (DSM, ICD etc.) is followed, it will enable any analytics software to make sense of the data and provide useful insights. With AI, structured data is still king. Predictability of an outcome for a set of patient symptoms, medications, prior history, genetic propensity, lifestyle habits would have a high accuracy 

Q4. Nishita Mehta:What do you think does a hospital need to implement Big Data solutions, i.e. Big Data Analytics Capabilities in terms of infrastructure and personnel requirement?

A. Inder Davalur:  

One of the major challenges a CIO or an IT head faces in a hospital is the lack of budget allocation for anything beyond the basic networking, computing and storage needs. Hospitals do not see the value in the data they currently possess most likely because they are more empirically driven rather than evidence driven. What this means is that hospitals and by nature the doctors who hold a sway over management decisions are more comfortable with their own decades of experience over some hotshot CIO trying to promote the idea of data mining and predictive value of patient outcomes based on past data. There is also a severe shortage of technology-rich personnel in hospitals due to the dull routine of maintenance of existing hardware and software rather than experimenting with new technology. The pay structure for IT personnel in hospitals is also woefully poor in comparison to the technology companies. All these factors combine to deter anyone who is driven to create in hospitals a digital core

Q5. Nishita Mehta: While Big Data can generate a plethora of interesting patterns or hypotheses, there is still a need of experts to analyze the results to confirm whether they make sense or merit further inquiry. Would you like to comment on this?

A. Inder Davalur:  

Absolutely. Right now, there is a paucity of people with skills to interpret and recommend action plans once an organization implements any sort of analytics software. Unlike other verticals, healthcare is lagging far behind in its focus on data interpretation and application in its business model. It might be a whole decade before hospitals wake up to the reality of meaningful interpretation of data and building an action plan around it


Q6. Nishita Mehta: What are the major drivers of Big Data Analytics in healthcare in India?

A. Inder Davalur:  

Have not seen much evidence of it. Perhaps some hospitals have ventured into some basic AI driven applications in specific areas such as pharmacy sales or patient wait times. Other than that, BDA is yet to catch up.

Q7. Nishita Mehta: What are the key benefits Indian hospitals will draw from implementation of Big Data Analytics? 

A. Inder Davalur:  

First and foremost, hospitals will get to see for themselves how poorly structured their data is. BDA for Indian hospitals can cover a better management of the following: 
  1. Sponsored
  2. Accounts Receivables
  3. Professional Fees
  4. Disposables and Consumables
  5. Pharmacy – Generic vs brand name consumption
  6. Targeted marketing
  7. Continuum of Care post-discharge
  8. Predictability of illness propensity from regular Health Check ups
  9. Results-oriented tasking for better output from employees

Besides these areas, hospitals can contribute tremendously to public health issues by sharing anonymized patient data with the State Health Department which can then study outbreaks and lifestyle disease patters in the general public. 

Q8. Nishita Mehta: How does Big Data Analytics help better decision-making & building disease understanding?

A. Inder Davalur:  

One of the most ignored areas is a deeper dive into results from investigations. Empirically speaking, the values considered “normal range” are never questioned. If a better study is conducted, what is normal for one cohort may not be so for another cohort. As an academic exercise, I had a simple deep analysis done to study the correlation between borderline values of lipid profile and any other element from a blood test. The result was a high (>70%) correlation between borderline lipid profile values and an elevated monocytes count. It turned out that among those who fell in this group, nearly 78% of them were later admitted for some coronary complication. The medical reason is that the monocyte levels are elevated when there is presence of a heart disease. Every one of these patient was merely getting a Health Check. Imagine if hospitals did such studies on a multitude of investigations routinely conducted for patients and conducted regular follow ups as a preventive measure

Q9. Nishita Mehta: One of the biggest concerns in healthcare is the rising costs. What potential solutions does Big Data offer for this problem in Indian context?

A. Inder Davalur:  

India’s population is now facing more mortalities from lifestyle diseases – Non Communicable Diseases (NCD) as opposed to communicable diseases. There is a great potential to flip the business model of the healthcare industry to go from disease management to health management. I have written blogs on this topic. The premise is very simple. Make it more profitable for hospitals to keep the public healthy than to treat them. If the payment structure is modified to increase the prices for health checkups and promoting healthy prophylactic therapy methods as opposed to coronary by-pass surgeries, it could completely change the paradigm. These prices can be graded based on age. All old age related treatments can receive higher prices; while treatments like a heart surgery for a 40-year old can be less. At the same time, therapeutic treatments for younger population geared for promoting good health can receive higher prices. A larger healthy population means a larger market for the hospitals. This ensures that the hospitals have a higher incentive to make the healthy population larger

Q10. Nishita Mehta: What would you highlight as being the major challenges today in developing & actually implementing Big Data Analytics capabilities to truly extract meaningful insights?

A. Inder Davalur:  

An urgent awareness creation among promoters and owners of hospitals of the benefits of investing in the technical hardware and personnel resources to build and maintain a BDA infrastructure. Without that awareness, IT costs are always seen as a sunken wasteful expenditure as opposed to an investment. There is nothing else lacking in this respect.

Q11. Nishita Mehta: Do most doctors now have a checklist for what they should be doing with patients with certain conditions? How does Big Data solution change what they are doing currently?

A. Inder Davalur:  

Hard to predict. Most clinical pathways and treatment protocols are traditionally empirically driven. It is hard to imagine a medical community to take notice of what BDA might reveal and radically change their protocols. That said, things have changed – take robotic surgery – and there is hope and a high degree of probability that medicine might be “data-powered” (my phrase over the more commonly used data-driven) offering the physician to choose to use such data-powered results wherever she finds it viable or desirables

Q12. Nishita Mehta: How do hospitals need to adapt to embrace the full potential of data-driven innovation?

A. Inder Davalur:  

Promoters and owners having a greater understanding of the power of data

Q13. Nishita Mehta: How important do you think Big Data Management & Analytics is right now to enhance healthcare in India?

A. Inder Davalur:  

Tremendously. With the technical resources at its disposal, India would be imprudent not to take full advantage of the benefits of BDA. Population health data is one of the most ignored among developing nations. India would do extremely well to develop and use BDA for advancing population health

Q14. Nishita Mehta: What do you see as the main emerging opportunities for hospitals from greater adoption of Big Data Analytics?

A. Inder Davalur:  

Connected Continuum of Care (a phrase I first used in a blog) is a concept of keeping the patient engaged post treatment and post discharge through the use of wearables and IoHTs (Internet of Healthcare Things). This ensures that hospitals are not merely agents in episodic encounters and instead become agents of well-being. BDA will help provide the big picture in the overall health and well-being of the population it serves

Q15. Nishita Mehta: What are some of the biggest challenges facing the healthcare industry in terms of its ability to use Big Data to improve healthcare outcomes?

A. Inder Davalur:  

A better understanding and incentive to invest in the infrastructure is all it takes. Once that happens, India is best equipped to leverage from its large technology-aware population. At the hospital level, BDA could help establish a new approach to purely outcomes-driven pricing structure and treatment protocols that would be data-powered. 

Q16. Nishita Mehta: Would you like to share additional insights on the topic, which I might have missed?

A. Inder Davalur:  

Public-Private-Partnerships with educational institutions and hospitals would also be beneficial. There is going to be a severe shortage of technical resources who are trained in AI and BDA by 2020. If the government partnered with colleges to promote courses and training in AI and BDA India could be the largest supplier of technical talent to the world. If hospitals also partnered with the government to share health data, the state of overall population health will rise and costs will come down.

The article was first published on Mr. Inder Davalur’s LinkedIn Pulse page. The blog was Mr. Inder’s answers to Ms. Nishita Mehta’s Survey published on the HCITExpert Blog earlier, here. I would like to thank both the Author’s for sharing their insights via the HCITExperts Blog. 
Team @HCITExperts [Updated: 03 rd Sep 2018]
Authors
Nishita Mehta

Ph.D. Scholar at SYMBIOSIS INTERNATIONAL UNIVERSITY

Inder Davalur

Inderjith Davalur is a healthcare technology specialist, speaker, writer and utopian dreamer.
Inder works with hospitals committed to transforming the healthcare paradigm with the aid of new innovative technologies. His primary area of interest lies in using data analytics and technologies such as Deep Learning to shift the current physician-driven healthcare model to a patient-driven market dynamic.
Inder focuses on the manifold ways in which data crunching and machine learning can lead to better diagnoses that can not only be made at the time of illness, but predicted way before any symptoms surface. The path ahead in the sector, he believes, lies in the deployment of evolving technologies that immensely influence both diagnostic and therapeutic aspects of healthcare, delivering real patient-driven, data-enabled, informed healthcare.
Inder currently works as the Group CIO at KIMS Hospitals Private Limited, Hyderabad and has previously assumed leadership roles at leading hospitals and companies, in India and the United States of America.

SURVEY: The use of Big Data Analytics (BDA) for better healthcare delivery in India by Nishita Mehta

This survey tries to understand the state of healthcare data management in hospitals in India and the use of Big Data Analytics (BDA) for better healthcare delivery


The results of this survey will help obtain insights in how the hospitals can make use of technological developments for improving care delivery. 


The survey has been created keeping in mind the expertise of respondents, hence it has been divided into two categories: 

(a) User: hospital personnel 
(b) Solution provider/ healthcare technology experts. 

The survey has been distributed across two parts, each would take around 10 mins to answer. The responses to this survey will remain anonymous and will only be used for research purpose. 

I personally thank you for each minute you invested in this research.

(a) User: Hospital Personnel
Part I: https://goo.gl/forms/AS52RYFA4VDP9ct42
Part II: https://goo.gl/forms/ICXKGd19exvuMito2

(b) Solution Provider/ Healthcare Technology Experts
Part I: https://goo.gl/forms/WblNKZgRkq8PGAXs2
Part II: https://goo.gl/forms/WhUUIvfQCuvciwEG2

Author
Nishita Mehta

Ph.D. Scholar at SYMBIOSIS INTERNATIONAL UNIVERSITY

KPIs on fingertips – Healthcare by Jyoti Sahai @JyotiSahai


During a recent conversation with the CEO-Doctor of a multi-specialty hospital our discussion veered towards how data-driven decision-making using analytic insights could benefit the hospital. His response, typical of most of the CEOs (for that matter from any industry) was – Oh! I really don’t need any analytics! All the facts I need to run my organization are on my finger-tips!



My takeaway from that conversation were the two keywords ‘facts‘ and ‘fingertips‘! For running a successful organization, you do always need to have near real-time relevant and critical (may be up to ten, one for each fingertip!) facts on what is happening within the company. However, just the facts (measures) may not always be sufficient to arrive at a decision unless those are benchmarked against the desired performance and/or trends over different periods for those measures. Deployment of analytics enables the stakeholders to have that additional edge over the decision-making, by making the exercise based more on validated data than just a gut feeling.

That set me thinking on what could be those top key performance indicators (KPIs) which if available on fingertips (at the click of a button) could aid a CEO in achieving the organizational objectives more effectively, and what could be the ones relevant for a hospital CEO!   .
I presume that any hospital CEO’s top priority is to strive to earn the patients’ trust, and that is possible only if the hospital could meet and exceed patient expectations.

Meeting the patient expectations

What a patient expects from the hospital is a treatment that is effective, timely and fair. The following KPIs keep the hospital CEO and other stakeholders informed on how effectively that is happening?

Treating the patients effectively …

The top hospital stakeholders should be worried if higher % of patients who have been already discharged (whether out-patients from day-care or inpatients with hospital-care) return to hospital for re-treatment or re-admittance for the same ailment. That will show that either the initial diagnosis was flawed, or some critical elements were missed out while administering the treatment. Either way it would be matter of great concern for the hospital CEO, who should always be aware of the Re-admittance Index – % of discharged patients who required re-treatment or re-admittance.

... and timely …

One of the most critical performance indicator within a day-care hospital is the TAT, the turnaround time – the elapsed time between entry of the patient in the hospital (registration) and start of consultation of that patient by the physician. Other important TATs that are tracked within a hospital include – for a test being conducted, the elapsed time between the ordering of the test till the report collection, and most importantly for an inpatient, the elapsed time between the decision to discharge and the actual vacating of the bed. Inordinate delays in these lead to irritated patients, increased costs, and avoidable queueing issues too. Typically hospitals set internal benchmarks, or compare with any available industry benchmarks, to track the various TATs. In case of inordinate delays, hospitals could carry out a root cause analysis and take preventive and corrective actions.
What any hospital CEO should strive for is that the TAT Index for any given period is less than 5%, that means not more than 5% patient-visits experience a delay beyond a set benchmark in treatment or in discharge.

… and fairly …

I remember once a CEO of a hospital was concerned about if any of the eleven consultants in the hospital were at any time prescribing investigations and/or medicines that were not warranted for the observed symptoms and the medical condition of the patient. Periodic audit of all prescriptions comparing those prescriptions with a defined set of rules (lines of treatment) for corresponding symptoms will give a fair idea of the deviations if any. What a CEO has to do to control it, is to always ensure that the Unfair Treatment Index (% of possible deviations from an appropriate line of treatment) is kept below the minimum acceptable tolerance benchmark.

… and thus earning patients’ trust!

A hospital may expect that it has earned a patient’s trust by providing treatment that is effective, timely and fair, but it can really know that for sure by arriving at the Patient Satisfaction (P-SAT) Index only. P-SAT can be derived by analyzing the feedbacks received from the patients, results of internal surveys, and the comments (adverse or commending) on the social media. A prudent CEO always depends upon the P-SAT Index to accurately gauge the extent of the hospital’s success and reputation.
We have now understood that patients’ trust can be earned by providing effective, timely and fair treatment. However none of that is possible unless the hospital itself is run efficiently and profitably.
How does the CEO keep track whether the hospital is run efficiently?

Managing the hospital operations efficiently

For meeting and exceeding the patients’ expectations it is imperative that the hospital operations including administrative and clinical processes are efficient and stable. Primarily it means that the all the hospital resources are used optimally, and are available for use when needed. The above-mentioned TAT Index is one such KPI. The following other KPIs too provide an indication of a hospital’s operational efficiency.

Are the resources and infrastructure used optimally?

Hospital resources and infrastructure, if not used optimally, lead to lost opportunity, frittering away of resources, and most importantly increase in operating costs. The Management has to ensure that the various Wards, Operation Theaters, Labs, and various equipments, and even the service providers (human resources) are available for providing service to the patient when needed. Out of these various parameters, tracking of the bed utilization (% of hospital beds occupied at any given time) is considered very critical for any large hospital as it has a direct impact on the efficiency of that hospital. A consistently low bed utilization could mean among other things, either faulty planning (resulting in over-investment) or a low P-SAT. On the other hand a consistently high bed utilization could lead to severe strain on resources and maybe result in declining quality of service.
Thus it is imperative that the hospital CEO constantly monitor the Bed Utilization Index.

Are the patients kept in hospital for a period that is necessary and sufficient?

One of the most critical KPIs for a hospital is the Average Length of Stay (ALOS) of inpatients for specific types of ailments or procedures carried out. The hospital could compare its such averages with either the industry benchmarks, or internally set benchmarks. For example assume that for a specific operation procedure (including the pre-operation and post-operation in-hopsital care) the ALOS is 6 days. If elsewhere in the industry the ALOS for the same procedure is 7 days, that will mean either your administrative and/or clinical processes are more efficient than others or you may be missing out on some necessary hospital-care (a point not in your favor). On the other hand if the ALOS elsewhere is 5 days, that will mean either you are providing some additional necessary services that others are not offering (a point in your favor) or your treatment more often is less efficient (your processes take extra time and/or resources for the same procedure).
Either way the CEO should keep a close watch on ALOS to optimize the services provided under the various procedures offered by the hospital.
However, even an efficiently run hospital having earned it patients’ trust to may fail if it is financially weak.

Monitoring the financial health of the hospital

For a hospital to ensure efficiency in its operations, it is imperative that its finances are stable and profitable. Without that the hospital will not be able to sustain its efficient operations for a longer period. It is the hospital CEO’s prime responsibility to ensure that that does not happen. The hospital CEO can depend upon the following KPIs to keep a check on the financial health of the hospital itself.

What is the hospital’s margin on an average for each patient-visit?

Whether you are an individual or an establishment, the universal fact remains that you cannot consistently spend more than what you earn if you have to sustain financially in the long-term.
What is critical for the hospital Management is to know what is the hospital earning on an average for each visit that a patient makes to it for treatment. Once ARPV is known for a period, and is compared with the average cost of operations for that period (ACPV), the hospital CEO knows whether the hospital operations at the current levels are sustainable or not.
Trends of ARPV and ACPV over a period give sufficient insights to the CEO to arrive at fair pricing of services, and take steps to manage optimal utilization of resources.
However a strong ARPV or a manageable ACPV alone will not be sufficient for financial stability unless the cash management is also strong.

Are the insurance claims being settled in time by the insurance companies?

Once a CEO of a 100-bed hospital was complaining that though he knew that the hospital had been having a strong revenue stream during that period, he was finding it difficult to pay on time for even the relatively small purchases made for materials and services. Why was that? A quick look at the hospital accounts revealed that (as is typical of all medium-large hospitals) almost 75% of the hospital revenue was derived thru insured patients, provided care under cash-less treatment schemes. It was also found that a substantial portion of that money was blocked in over-due claims submitted to the insurance companies and remaining outstanding for various reasons. That meant that the cash-flow was heavily dependent upon the timely settlement of insurance claims.
Any prudent CEO keeps a tight watch on the number of days claim outstanding (DCO) with the insurance companies; monitoring closely the TPAs – Third-party Administrators – ensuring that the claims are settled by the insurance companies as per agreed contractual terms. Timely settlement of insurance claims results in improved and predictable cash-flows and strengthens financial stability.
A hospital CEO may track the above-mentioned KPIs and ensure that the hospital is earning patients’ trust, and is operationally efficient and is financially stable too. But the litmus test of a hospital’s reputation and success is when its performance is compared with its peers, the other similar hospitals in the geography or with the same specialization.

Where does the hospital stand when compared with its peers?

Several independent agencies periodically rank the participating hospitals based on various performance factors, and the ranking could be geography-wise, type of hospital-wise, or specialty-wise.
For a CEO it is imperative that whichever ranking is most important for the hospital is thoroughly analyzed, and a proper strategy to improve/maintain the ranking in future put in place.

In conclusion

How does the CEO keep track of the above-mentioned top KPIs? The CEO’s Dashboardcould display the current status of the KPIs, available at any time at the click of a button (literally putting those on fingertips). A typical dashboard containing the critical KPIs could look like as shown below:
(The numbers and the traffic-light shown against each KPI in the dashboard are for illustration purpose only and do not represent any industry benchmark or desired value)
The above list contains the typical KPIs critical for gauging any hospital’s performance on various operational and financial parameters. However depending upon the criticality for a particular hospital, different and more relevant KPIs could replace those less relevant for that hospital.
By design, I have not included any KPIs or insights produced by clinical analytics, as those will be specialized and specific to each individual hospital.
My suggestion is that let the CEOs use their fingertips for recalling critical tricks of their trade and expertise only, and let an analytics system recall the KPIs for them whenever needed for reference!
[Glossary:
ACPV – Average Cost per Patient-Visit; ALOS – Average Length of Stay; ARPV – Average Revenue per Patient-Visit; DCO – Days Claims Outstanding; KPI – Key Performance Indicator; P-SAT – Patient Satisfaction; TAT – Turn-around Time]

Note: A version of this article also appears in my blog gyaan-alytics and more…

Author
Jyoti Sahai

Jyoti Sahai has over 42 years of experience in banking and IT industry, and is currently the CMD of Kavaii Business Analytics India. Kavaii provides analytic solutions in Healthcare and IT Services domains.

Case Study: Efficiently Converting Healthcare Data into Information and Intelligence by @uddenfeldt


This article was published by Mats Uddenfeldt, on his LinkedIn Pulse page [ https://www.linkedin.com/pulse/case-study-efficiently-converting-healthcare-data-mats-uddenfeldt ]. The article is republished here with the author’s permission.
Valence Health provides healthcare providers with customized solutions for value based care, helping them better manage their patient populations and accept financial responsibility for the quality of the care they provide. The company offers advisory services, health plan services and a suite of population health technology software as a service (SaaS) products that help their clients transition from a transaction-based approach to a value-based approach to healthcare. Headquartered in Chicago, Valence Health serves 85,000 physicians and 135 hospitals, helping them manage the health of 20 million patients nationwide.


The Challenge

The company’s rapid client growth and the increasing volume of data required to keep up with that growth were straining its existing technology infrastructure. “Our services have a voracious appetite for data. We use that data to inform decisions about improving both healthcare outcomes and operational processes. We knew if we continued to grow, we couldn’t sustain this,” explains Dan Blake, Valence Health Chief Technology Officer. “We had outgrown our Extract Transform and Load (ETL) infrastructure and knew we had to replace it.”
Valence Health looked at various alternative technologies. “We looked at large monolithic technologies like Informatica and point solutions like Syncsort but they did not give us the robustness and flexibility we needed in the long run,” says Blake. “We wanted something very open that would give us the flexibility to choose where to make investments over time. We were drawn to Hadoop and the capabilities those tools provided.”

MapR Solution

Valence Health is using the MapR Converged Data Platform [ https://www.mapr.com/products/mapr-converged-data-platform ] to build a data lake that is the company’s main data repository. The company consumes 3,000 inbound data feeds with 45 different types of data including lab test results, patient vitals, prescriptions, immunizations, pharmacy benefits, claims and payment, and claims from doctors and hospitals.
“NFS was a very important feature for data ingestion. It is making our migration much easier,” says Blake. In the short term, Valence is transferring data back to the SQL server database as their portal and analytics expect that format. Once they get through the ETL transformation, they plan to transition from SQL to an HBase solution.
    “We chose MapR [ https://www.mapr.com/why-hadoop/why-mapr ] because they were the easiest company to work with. They were the most receptive and answered questions quickly, honestly and efficiently. On the technology side, we’ve been very impressed with the overall ability to implement and integrate sequential data transformation.” Dan Blake, Chief Technology Officer, Valence Health

Benefits

Valence Health is already seeing many benefits from its MapR solution including increased performance, better responsiveness to customers, higher quality data and a flexible platform to sustain their growth over time.

Growth requires new data architecture that can scale the business

Valence Health has been on a steep growth path over the last several years. “In the wake of the ACA’s implementation, more and more healthcare providers and organizations like Consumer Orientated and Operated Plans (CO-Ops) are taking on risk. As a result, we have tripled the size of our business in three years and expect do the same next year,” says Kevin Weinstein, Valence Health Chief Growth Officer. “Every year we’re more than doubling the amount of data we are processing. Having a robust data architecture is integral to our success.”
The company’s growth path is tied to client growth and the growth in the data infrastructure that those clients require. “We have to use technology to scale the business. We have to be able to manage more data with the same amount of people,” says Weinstein.

Performance gains increase customer satisfaction

The reliable and high performance of the MapR Platform enables Valence to be much more responsiveness to their customers. “In the past, if we received a feed with 20 million lab records, it would take 22 hours to process that data,” says Blake. “MapR can cut that cycle time down from 22 hours to 20 minutes [ https://www.mapr.com/company/press-releases/valence-health-dramatically-improves-data-ingestion-performance-and ] . And it’s running on much less hardware.”
“MapR gives us the resource efficiency, speed and flexibility to make a huge difference in customer satisfaction. As soon as the data hits our system it’s pushed all the way through,” he says. “It gives our customers much faster feedback about what’s going on with the population they are trying to manage.”

Flexibility serves customers faster

Valence Health is also now able to answer customer requests that were very difficult to answer in the past. “It allows us to do things we could not do in our old world,” explains Blake. “For example, a customer might call and say: ‘I sent you an incorrect file three months ago and I need you to take that file out.’ That’s not something you can do in a normal ETL system on top of a relational database. It could take 3-4 weeks to get that data deleted,” he says. “But with MapR, that is naturally supported, we can just roll it back and take that file out.”
This ease of administration and maintenance means that the company can focus more resources on their core business. “I can spend less on outsourced resources and instead spend money on adding new features, analytics or visualization capabilities or acquiring new types of data. We can do things that truly matter to our customers,” says Blake.

Enriching the data lake with new data sources enhances data quality

The MapR Platform also makes it much easier for Valence Health to enrich their data lake with new data sources. “It’s not just the volume of data, we’re looking to integrate new types of data like socioeconomic and demographic information, or immunization records. With our old architecture it was painful to do so,” says Blake. “Our data scientists are looking at new sources of data. The data can tell you things you don’t even know about. If we can augment our data, we can build new types of analytics that allow our client and our company to successfully invest in areas we have not been in before.”

Data acquisition and integration capabilities enable differentiated services

Valence Health believes that their new data acquisition and integration capabilities will give them a leg up over their competitors. “Other startups are selling software solutions in spaces we operate in,” explains Blake. “But the hard part is getting the data into the system and into formats where it can be truly useful. Our twenty years of hands-on practical experience in working with provider organizations that have taken on all sorts of risk-arrangements coupled with our effective and efficient infrastructure to get data flowing and keep it flowing is hugely powerful. The data acquisition infrastructure is very important to our ongoing success and to our customers.”

Recommended Reading

Want to learn more about Big Data for the Healthcare industry? Please check out the links below:
  1. How Health Care IT Diagnoses Data Pain Points, CIO Insight – http://www.cioinsight.com/case-studies/how-health-care-it-diagnoses-data-pain-points.html
  2. Stepping Up to the Life Science Storage System Challenge, HPC wire – http://www.hpcwire.com/2015/10/05/stepping-up-to-the-life-science-storage-system-challenge/
  3. Health Care Emerges as Hadoop Use Case, Datanami – http://www.datanami.com/2015/10/08/health-care-emerges-as-hadoop-use-case/
  4. Big Data and Apache Hadoop for Healthcare and Life Sciences, MapR – https://www.mapr.com/solutions/industry/big-data-and-apache-hadoop-healthcare-and-life-sciences
Join our more than 700+ paying customers and discover why MapR [ https://www.mapr.com/ ]  is the clear market leader for production ready Big Data applications by reading about the Top 10 Reasons Customers Choose MapR [ https://www.mapr.com/top-ten-reasons ].
This article was published by Mats Uddenfeldt, on his LinkedIn Pulse page [ https://www.linkedin.com/pulse/case-study-efficiently-converting-healthcare-data-mats-uddenfeldt ] . The article is republished here with the author’s permission.
Author
Mats Uddenfeldt

Big Data Thought Leadership ♦ Enabling As-It-Happens Business

From Mere Health Statistics to Real Health Data by @AtulVB


The Health Statistics play a major role in deciding the Health Policies of Nations, no doubt they provide the insights into the health parameters in question and health statistics such as Rates, Ratio, Incidence, Prevalence and Life Tables are needed to be formed into indicators of progress of the nation in terms of improvement of the factors in consideration.

The question is – is mere statistics enough or is there something more to it?

As we move from Millennium Development Goals (MDGs) to Sustainable Development Goals (SDGs) – this question becomes more imperative!

According to WHO, Health is defined as “Health is a state of complete physical, mental and social well-being and not merely the absence of disease or infirmity”. 1

Health is also identified the state of “not well”, “ill “or “morbidity” or “sickness”. Further “death”, which is caused by illness or sickness, reflects the condition of Health. Hence measurement of “Mortality” and “Morbidity” reveals of Health condition of a community.2

Statistics definitely provide a macro-level / micro-level understanding of the situation and brings in quantitative pointer to a qualitative, exhaustive and comprehensive activity. Year-on-year the quantitative pointer is kept as the reference. Any deviation from it is representative of the growth or decline of the parameters in consideration.

Such laser sharp focus on quantitative data is the hallmark for Population Census, Surveys and even Market Research – where absolute number, a figure in percentage is the gospel truth.

What about Health / Medical Data of the population? What about the Medical History? What about the Medical Condition – improvement / degradation?

The last point gets easily converted into an explainable number or a percentage as an indicator, but what about the relapse or repeat condition of the same person – it’s again… just a number!  

Limitations of data especially in developing countries are a real concern, as available data is not reliable and post-2015 presents an opportunity to think beyond what data is available so that countries can invest in capacity building to get it.3

Alongside the number comes a lot of health and health-related data, but with the focus being statistics, basic essential health data is obviously missed out.

Non-communicable disease continues to be an important public health problem in India, being responsible for a major proportion of mortality and morbidity. Surveillance of NCDs and their risk factors should also become an integral function of health systems. Evidence based clinical practice and appropriate use of technologies should be promoted at all levels of health care, including tertiary services.4

With the focus on Non-Communicable diseases (NCDs) – it is imperative we focus on the Healthcare & Medical Data for Clinical outcomes and not mere Health Information for Management Systems.

Ageing Population is one of the major concern globally, more so in India. It is now recognized that while both developed and developing countries are experiencing growing proportions of elderly, developing countries currently are ageing faster than developed countries. In India, the proportion of the population aged 60 years and above was 7 per cent in 2009 (88 million) and is expected to increase to 20 per cent (315 million) by the year 2050. 7

As per a study conducted 5, among the most significant findings that emerged was the incompleteness of data on the burdens of access and affordability among elderly populations in India. A major reason for this is that routine health data collection in India is not designed to reflect or characterize pathological progression. Many routine data collection procedures (National Sample Surveys, Census data, or death certificates) in India do not capture pathological progression nor do they disaggregate morbidity and disability outcomes among the elderly. 5

Further research, especially qualitative research, is needed to explore the depth of the problems of the elderly. 6

With a rise in the Ageing Population, it is all the more important to look at the efficacy of the health data collected than mere health statistic data and a Longitudinal Study along with Cross-Sectional Study is needed for an efficient health data repository.

With the advent of new age technology: connected technology, Connected Health has become pervasive and with embedded systems and IoT taking center-stage, it is all the more essential to focus on the Data and not mere Number! And when I say ‘Data’ it is ‘Health Data’.

And last, but not the lease – the necessity for increased clinical / medical research in today’s evidence based approach makes it is all the more important to focus on the fundamental health data collection, collation, transformation and consolidation to begin with leading to Analysis, Research and building the knowledge base for Healthcare / Medical Data Management.

Looking at the underlining need for Health / Healthcare Data, we need to move from just Statistical Data to Meaningful Data – not to mistake ‘Meaningful use of Data’!

The article was first published on Mr. Atul Bengeri’s – LinkedIn Pulse. The article is republished here with the authors’ permission

References
  1. CIGI, TISS, KDI, Post-2015 Development Goals, Targets and Indicators: Indian Perspectives, Mumbai, India / Meeting Report, August, 2012
  2. An Overview of the Burden of Non- Communicable Diseases in India – R Prakash Upadhyay. Iranian J Publ Health, Vol. 41, No.3, 2012, pp.1-8 http://www.ncbi.nlm.nih.gov/pmc/articles/PMC3481705/pdf/ijph-41-1.pdf
  3. Health of the Elderly in India: Challenges of Access and Affordability. Subhojit Dey, Devaki Nambiar, J. K. Lakshmi, Kabir Sheikh, and K. Srinath Reddy. National Research Council (US) Panel on Policy Research and Data Needs to Meet the Challenge of Aging in Asia; Smith JP, Majmundar M, editors. Washington (DC): National Academies Press (US); 2012. http://www.ncbi.nlm.nih.gov/books/NBK109208/
  4. Health and Social Problems of the Elderly: A Cross-Sectional Study in Udupi Taluk, Karnataka A Lena, K Ashok, M Padma,1 V Kamath, and A Kamath. Indian J Community Med. 2009 Apr; 34(2): 131–134. doi:  10.4103/0970-0218.51236 PMCID: PMC2781120
  5. Demographics of Population Aging in India. Subaiya, Lekha and Dhananjay W Bansod. 2011. Demographics of Population Ageing in India: Trends and Citation Advice: Differentials, BKPAI Working Paper No. 1, United Nations Population Fund (UNFPA), New Delhi.

Author

Atul Bengeri

Digital Health Influencer & Evangelizing Digital Transformation across verticals, Strategic Planning, Leadership, Program Management, Partnerships / Alliance Management