Separator

Big Data in Healthcare - Time to Stop Making Any Further Excuses

Separator
Vaibhav Singh, Co-Founder & CEO, myCOL Headquartered in New Delhi, myCOL is a healthcare technology platform that leverages AI and Machine Learning techniques to enable users get information regarding a wide range of hospitals, diagnostic centers, and other healthcare establishments.

Non-state sponsored healthcare economies like India constantly face issues relating to inadequate hospital bed inventory, poor doctor and nurse ratios etc. While supply constraints are widely publicized, interestingly enough, little emphasis is paid to efficiency in utilization of existing resources. Is it not surprising that large public hospitals run wait times extending into several months for certain surgeries while occupancy rates at such hospitals are less than 75 percent? If such a situation continues, the queues will keep getting longer and longer especially in an environment when demand for in-patient healthcare is increasing exponentially due to increased awareness, higher incomes and improved payer pools.

While hospitals have done what seemed apparent to them to ensure smoothening of processes, the answer is not so simple and such improvements do not generally yield desired results. The solution clearly lies in harnessing the power of data to make more meaningful process level changes to effect those incremental changes required for achieving optimization.

However, sadly enough, the healthcare sector has been a laggard in terms of collection as well as retrieval and sharing of data that can help alleviate problems that the sector faces. Not just in India but ubiquitously across the world, barriers have been created which do not permit access to data for experts so that they can deploy cutting edge analytics to unravel the wealth of information that medical cases and processes contain. It is a pity that more work has been done in analytics in the banking and financial services industry, the retail industry etc. and not even a small fraction of that has been done in the healthcare sector. And it would seem obvious that the gains to be had, both in terms of life and resources, may as well be much larger for the healthcare sector than the benefits that accrue to other sectors that avail the benefits of data and analytics.

Why do we feel happy simply by the fact that technology in the form of new
hardware and machines has increasingly percolated into the healthcare domain? Why is it that our learning’s from a case or encounter are not institutionalized and left merely in the realm of the work experience of the doctor/ practitioner. Surprising as it may sound, over the last 100 years or so, there has been little change in the way medicine and healthcare is taught. The dominant form of pedagogy continues to be on the job training and practical involvement of new doctors in live cases with old experienced hands. Such practice suffers from a critical problem of linearity. How can we get more and more doctors and nurses if their training and learning is to be dependent on training that they receive physically on the job from their senior experts?

Most hospitals recognize the importance of LOS and have initiated efforts to improve how data is recorded in this respect

It is undeniable that a treasure trove of data both clinical and non-clinical is created in each unique healthcare encounter. At times, this is not recorded properly. And even when it is collected, the data remains inaccessible under the garb of several layers of confidentiality and trust related issues. And this is where the problem perpetuates itself. While there is no denial that confidentiality of data is critical, we have to all approach this with open minds and act as enablers than disrupters for the common good.

Let me illustrate with a small example. Length of Stay(LOS) is the single most important metric that reflects clinical as well as non-clinical excellence at a hospital. It is defined as the number of calendar days from the day of admission to the day of discharge. Most hospitals recognize the importance of LOS and have initiated efforts to improve how data is recorded in this respect. However, their analysis is presently restricted to descriptive analytics around Average Length of Stay (ALOS) and how to reduce it. What has been observed empirically is that variances are very high (each case is nuanced) and these variances make ALOS highly misleading.

Advanced machine learning led analytical models are now being developed that can predict most likely LOS for different disease groups. By inputting some basic variables (including but not limited to Age, Gender, Height, Weight or any other aspect), accurate estimation of LOS can be made that can have significant impact on:

a. Accurate estimation of the cost of hospitalization of each individual case thereby potentially increasing the conversion ratio by reducing balking due to high cost
b. Availability of the bed, optimal utilization of capacity and capacity planning
c. Quality assessment of the department and doctor
d. Better customer experience

Such predictions not only have a positive impact on patient inflow and admission thereby ensuring that occupancy rates can be improved but also end up impacting healthcare costs since more patients can be served with the same infrastructure during a particular period. Similar analytics can be done in respect of OPD appointment scheduling, hospital acquired infections, readmission etc. and it is therefore essential that hospitals realize this, align with the right partner, share data and reap benefits not just for themselves and the patients but for society as a whole.

If we cannot afford more beds, more hospitals, and more doctors, then definitely we cannot afford to keep making excuses to avoid collecting, analyzing and sharing data to ensure that the benefits of technology and analytics can come to the rescue of some more lives. We owe it to ourselves and to all our fellow citizens.