Data Analytics and Precision Medicine

Precision Medicine: Data analytics has ventured into another vital area that of using data to deliver personalized health care to millions of citizens. Personalized Medicine has given way to ‘Precision medicine’ and is  a term used to describe a transformative model of health care that involves the selection of diagnostic tests that have the potential to identify changes in each individual’s patients cells and to customize treatment as per individual requirements. Ultimately, the goal of precision medicine is to improve patient outcomes. Having said that while there has been reasonable amounts of success in the application of big data, there are still certain major hurdles in its universal adoption which stem from the economic, technical, regulatory and human aspects involved. The NAS report defines “precision medicine,” — the use of genomic, epigenomic, exposure, and other data to define individual patterns of disease, potentially leading to better individual treatment. Precision Medicine is much more than personalized medicine and is meant to convey a more accurate image of diagnosis that is person-centered and multifaceted.

Data Analytics and Precision Medicine: Data Analytics or Big data in precision medicine essentially refers to the use of data science techniques to capture and analyze huge and complex datasets in order to positively impact patient care outcomes, and optimize business processes. While the term, big data, may seem to reference the volume of data, that’s not necessarily the case. Big data may also refer to the extent of technology that an organization requires to handle large amounts of data, as well as the needed facilities to store it. The healthcare industry produces large amounts of clinical, financial, administrative and genomic data and needs big data techniques to manage it.

Healthcare Data: Health care data uses a variety of data and includes Web and social media data (interaction data from Facebook, Twitter, LinkedIn, blogs, health plan websites, and smartphone apps), Machine-to-machine data (information from sensors, meters, and other devices), Transaction data (healthcare claims and billing records in both semi-structured and unstructured formats), Biometric data (fingerprints, genetics, handwriting, retinal scans, X-rays and other medical images), Human-generated data (Electronic Medical Records (EMRs), physicians’ notes, email, and paper documents), Pharmaceutical R&D data( related to a drug’s mechanism of action, target behavior in the human body and side effects)

The Electronic Health Record (EHR) is a longitudinal systematic collection of electronic health information for a patient generated by one or more interactions in any care setting. In order that they may be accessed it is essential that the same should be shareable across different health care settings. An EHR typically includes information such as Patient demographics, Medical history, Medications and allergies, Immunization status, Laboratory test results, Radiology images, Vital signs, Personal statistics like age and weight, Progress notes and problem details and Billing information. The Electronic Medical Record (EMR) is a part of EHR and refers to the digitized version of the paper chart in clinician offices, clinics, and hospitals. The EMR contains notes and information collected by and for the clinicians in that specific office, clinic, or hospital setting and is mostly used by providers for diagnosis and treatment. The term Personal Health Record (PHR) refers to EHRs that are designed to be set up, accessed, managed and controlled by patients in a private, secure and confidential environment. They usually contain health information generated by clinicians, home-based monitoring devices, and patients themselves.

Big Data has been used for a considerable time in the health care industry. Some of the current applications of big data have involved the processes of collecting and aggregating the vast amounts of patient data produced from a variety of sources for analyzing hospital systems, effectiveness of patient care, return on investment of business processes and general business intelligence.  The use of data analytics will however go a step further in using the data collected to improve patient outcomes through use of advanced clinical analytics to enhance proactive care, enhancement of clinical decision-support using analysis of current knowledge databases, improvement of clinical trial design with the use of statistical tools and algorithms and finally building better models of personalized medicine through the analysis of large data sets.

Applications of Data Analytics in Precision Medicine: It is suggested that data analytics can be used in six very practical cases. They are high-cost patients, readmissions, triage, decompensation (when a patient’s condition worsens), adverse events, and treatment optimization for diseases affecting multiple organ systems (such as autoimmune diseases, including lupus).

  1. High-Cost Patients: As per a study done in the US, approximately 5% of patients account for 50% of all US Health Spending. Therefore identification of high cost patients is paramount. To identify high risk or high cost patients may require inclusion of attributes such as behavioral health problems or socioeconomic factors such as poverty or racial minority, marital and living status in the algorithms developed. Algorithms are most effective and perform best when they are derived from and then used in similar populations. A very critical aspect of identification of high cost patients is the use of behavioral data since it is found that a large portion of patients at high risk for hospital admission have some sort of behavioral health issue, depression being most especially frequent. For instance, the standard approach may be to give all patients who are discharged from the hospital a follow-up appointment in two weeks. But it might make more sense to ensure that the highest-risk patients are seen within two days, while patients with very low risk might require follow-up care only as needed. Algorithms can help reallocate resources more effectively at both the high-risk and low-risk ends of the spectrum.
  2. Readmissions: As many as one-third of readmissions have been regarded to be preventable and, therefore present a significant opportunity for improving care delivery. Health care organizations can use a predictive algorithm to predict who is likely to be readmitted to the hospital. The important result differentiation would consist of tailoring the intervention to the individual patient, ensuring that patients actually get the precise interventions intended for them, monitoring specific patients after discharge to find out if they are having problems before they decompensate, and ensuring a low ratio of patients flagged for an intervention to patients who experience a readmission (that is, a low false positive rate). It may also make sense soon to ask patients with a smartphone to allow health care organizations to access data from their phones that will help identify patients who are not managing a chronic condition well or that will monitor people recently discharged from the hospital, since it appears that patients who are not making calls or sending e-mail with their usual frequency may be depressed or suffering from other issues. Patients may also be asked to wear some type of device that monitors physiological parameters, such as heart rate or rhythm. These data will be most effective in informing health care decisions if they are processed with analytics.
  3. Triage: Estimating the risk of complications when a patient first presents to a hospital can be useful for a number of reasons, such as managing staffing and bed resources, anticipating the need for a transfer to the appropriate unit, and informing overall strategy for managing the patient. In newborns and many other populations, using modern big-data techniques that combine routinely collected physiological measurements makes much more accurate assessments possible with a minimal burden of training and implementation. For example using maternal data to assign a preliminary probability of early onset sepsis. Similarly for adult high risk patients, clinicians in the emergency department may be provided with two composite scores that have been calibrated using millions of patient records and that are applicable to all hospitalized patients, not just those in intensive care. The first of these scores summarizes a patient’s global comorbidity burden during the preceding twelve months; the second captures a patient’s physiological instability in the preceding seventy-two hours. In addition, these two scores, available in real time, are combined with vital signs, trends in vital signs, and other information, such as how long a patient has been in the hospital. If the information collectively indicates that a patient has ≥8 percent risk of deteriorating in the next twelve hours, an alert is sent to the responsible providers.
  4. Decompensation: Often before decompensation—the worsening of a patient’s condition—there is a period in which physiological data can be used to determine whether the patient is at risk for decompensating. Much of the initial rationale for intensive care units (ICUs) was to allow patients who were critically ill to be closely monitored. A host of technologies are now available that can be used to monitor patients who are in general care units, in nursing homes, or even at home but at risk of some sort of decompensation. Monitors are becoming available in which multiple data streams can be compared simultaneously, and analytics can be used in the background to determine whether or not the signal is valid. One example of these new monitors is a device that sits under the mattress and that collects data about the patient’s respiratory rate and pulse and whether or not the patient is moving. The data are transmitted to a server, where analytics are used in real time to determine if the patient appears likely to be decompensating. When the system detects a likely decompensation, an e-mail message is sent to an on-duty nurse’s smartphone. With this system, the likelihood that a true decompensation is present has been increased to approximately 50 percent—far better than for cardiac telemetry, for which it is typically 5–10 percent.
  5. Adverse Events: Another use case for analytics will be to predict which patients are at risk of adverse events of several types. Adverse events are expensive and cause substantial morbidity and mortality, yet many are preventable. It seems likely that analytics could be combined with data about exposures to specific medications and with measures of kidney function, blood pressure, urine output, and other processes to identify patients at risk of decompensation. Analytics can also be effective in managing infection. One example involves monitoring and interpreting changes in heart rate variability for detection of major decompensation in infants with very low birthweights before the emergence of an infection. Monitoring the heart-rate characteristics of newborns alone has already resulted in reductions in mortality and increases in the number of ventilator-free days. However, there is room for improvement using increasingly sophisticated analytics that account for subtle signals but also filter out extraneous patterns, such as those that occur when the baby moves.

Challenges for Data Analytics in Precision Medicine: However there are also various factors that inhibit the use of big data in analytics. Some of them can be cited as: A resistance to a systems-approach by the medical community; acute shortage of professionals in data analytics in health care; lack of comparable and transparent data in health care; financial constraints in adoption of big data analytical systems and finally the lack of interoperability between health care systems.

The perhaps most difficult challenge to be addressed in a Precision Medicine research program is that it must have a value proposition that is compelling to all participants’ i.e.  data providers, patients and healthcare organizations. With the rapid growth and developments in genomics research, data science and electronic health records, it is possible to integrate an individual’s information into their clinical care for precision medicine. To address this opportunity, it is necessary to have a large cohort which is participant centric in concept so that it is possible to share structured data with participants, researchers and clinicians and at the same time is transparent in purpose, management and execution.

Another challenge relates to the lack of a practical mechanism to uniquely identify participants. The integrity and value of EHR data depends fundamentally on being able to unambiguously link it to one and only one individual whose healthcare it represents. This is sometimes achieved by matching records based on several characteristics (probabilistic matching) instead of using a unique identifier, which circumvents but does not eliminate privacy concerns. Unintentional duplicate records, name ambiguities, and utilization of another person’s identity to obtain care all contribute complexity to the seemingly straightforward task of linking data to the correct individual. This problem grows in proportion to the number of individuals who participate and the number of different care organizations that generate data about those individuals.

To complicate things, existing consortia that extract, transform, “clean” and analyze clinical data for research purposes have extensively depended upon the local expertise of informatics teams at each of the data contributing sites. Such expertise is currently unavailable in most healthcare institutions except in large academic medical centers. The paucity of experts constitutes a bottleneck in the development of a national PM cohort that includes all care settings.

Further, there will be certain technical specifications that must be methodically drafted and all possibilities integrated. To make progress toward a reliable research data resource based on individuals accessing their records as study participants, there is a need for a definition of a common structure for granular research-related data, have agreed-upon definitions (semantics) for key research data, and finally a development of an extensible “comprehensive electronic data format” that will accommodate both structured and unstructured data.

Transforming the realities of real-world EHR data into interoperable, standardized data structures requires significant vendor-to-vendor and site-to-site interpretation. EHR vendors and healthcare providers must be given guidance and testing capabilities regarding how to configure systems for these new requirements.


Research Methodology in the Classroom

I began delving into research methodology actively in the classroom some 15 years ago purely out of passion. I was and still am an economics and finance professor, and therefore it seemed more logical that I would be interested more in the performance of stocks and investment products rather than something related to primary research. But it seemed that the moment I got a chance, I was finding creative ways to devise projects that had some or the other element of figuring out what people did, what they thought, how they made decisions, what went on in their life and so on. Initially I was doing a fair amount of primary research around investment decisions such as those pertaining to mutual funds, stocks, pension or insurance or something related to risk profile of investors. These research projects were limited to students doing their summer or final projects and were extensions to their main project.

Thereafter I decided to throw the towel in and decided to enter the hallowed portals of a research methodology class. Very soon one ventured into a whole host of areas of research which was as inane as what factors and features would people choose cars, toothpastes, shampoos, hair oil, mobiles on, how much would they spend on them, and what was the brand recall.

We also did things that were somewhat not totally business based such as what kind of causes would people like to support, does celebrity endorsement matter for specific products, why do people cheat in exams and what goes in their minds when doing so, and even something as profane as what language is most preferred when you want to swear so that it really hits hard.

And then there were some topics that were public health based such as what kind of ailments do people living in slum regularly suffer from, how much do they spend on the same and whether their choice of primary medical provider was a private practitioner or a government hospital. I remember even doing one on self-medication for various ailments, its frequency and the most preferred choice of treatment as per ailment.

All these projects were done with students and we spent countless hours devising and revising questionnaires. Those were days when google surveys were not there and the possibility of adding logic in questions was really difficult. We squeezed questions in maximum three pages so that no survey would take more than 15 minutes inclusive of demographic questions. Those instruments were hard work but what really mattered was getting responses on those questions. We sent these groups out on field trips each group given a target of 100 surveys, 20 each to a student with some instructions on quotas for female and male respondents, age and income categories. But however much we tried, we trusted, only some students went to the field, most simply went home or hostel and self-filled it. As a result, very few projects got converted into full-fledged research papers, simply because we failed on one parameter, ethics in data collection and representative sample selection.

I shifted jobs and for six years, there was a lull in research methodology not because I did not want to teach it, but because the institutional leadership only wanted me to teach finance, economics and strategy, it being their primary focus. Another 2 years thereafter, I now work totally in the area of applied research and yes primary research is part of the portfolio except that my role usually demands that I analyze the data post its collection. The shortcuts in data collection and instrument design continue to hassle me despite sometimes the ease of electronic means of data capture.

I recently got an opportunity to go back into the classroom, a new set of students, a fresh list of projects, a new chance once again to teach research methodology. This time I choose projects targeted at 18-25 age category with projects revolving around issues that concern them directly. I am also armed with google surveys, so students don’t have to go out in the field, they can simply whatsapp the link to potential respondents, all of whom have smartphones. The target respondent group was meant to be urban, educated and media savvy so that they would not have any problem filling up the questionnaires at all. We also made sure that the questionnaire would take a maximum of 15 minutes even if someone took their time, and demographic questions were placed in the last and were minimal. The language was simple, direct and no logic added to questions to make it clutter free. I purposely did not mandate email addresses as a compulsory question, simply because I want to practice anonymity and protection of respondents’s privacy as a part of research ethics since those email addresses would be available to students and many of the respondents could be female as well. The targets are still the same, a group of 4 students, a target of 100 responses. Yes of course I get responses, the required number, but I also learn that each student auto-filled multiple questionnaires, each of them doing around 8-10 questionnaires. Some responses are no doubt genuine and one will figure out a way to remove duplicate responses in the questionnaires so maybe I can still derive some research insights but not enough to achieve a research paper status.

Yes the students will complete their projects, will learn a bit about framing a research question and testing a hypothesis… What they have still not learnt is research ethics and ethics in data collection. These are the same students who will one day be corporate professionals and will be responsible for making decisions based on research …


Getting a Voter’s Id Card in Haryana: My story

I do not remember being a political person ever. Unless of course, one counts a certain sense of right and wrong and a belief in the supremacy of the Constitution as being associated with politically interested. Politics to me, was not a very interesting vocation given that it had connotations of being associated with all kinds of corruption and unsavory crime. But that is not the only reason, why I did not manage to get a voter’s id card for almost 20 years. Every two years or so, I would move either cities, or jobs or residential locations. In that sense, I just kept postponing the ultimate proof of democratic license thinking that I will get one, when I will be more stable. My last lame reason was my complete involvement in my profession and therefore not having the time and patience to run around from pillar to post to get a voter’s id.

Therefore, when someone suggested that you can get your voter id card online, I jumped at the idea. Moreover, it seemed easy enough. All I had to do was to log on to, fill in my details, attach some identification and address proof documents, a photograph and my voters id was on its way in just a matter of 2 weeks. It also helped that I now had a permanent address.

That was 10th of February, 2019 and now we are on 13th of April, 2019 and I am still twiddling my thumbs regarding receipt of my voter’s id card. I have however managed to get my name included in the voter’s list so even if the voter id card does not arrive, at least with the help of my identity card, I will at least be able to fulfill my right and duty to vote. That achievement too however required my active intervention.

If you have logged on to the site, you would know that the portal has a provision of tracking your application. So, post my submission of voter card application on 10th of February, 2019, it said BLO appointed on 19th of February, 2019. Then the story becomes interesting. Apparently the BLO in question was an Aaganwadi worker who was with her fellow comrades was on strike due to non-receipt of expected salaries/incentives. I did manage to get the number of the BLO but for 2 weeks since the number was incommunicado, I did not get a chance to speak to her. Finally, someone told me about an app that could be downloaded on the phone and a helpline number 1950 which could be called. I then proceeded to do that and post multiple determined calls, the election executive relented and gave me the number of the main election officer in Faridabad. Then again, it was a series of calls to his office, before I managed a word with him, and he gave me some good news- the aaganwadi strike was off. The next day, I dialed the BLO and this time she took my call. It was a relief, but I can assure you only short lived.

As defined by the site, it is the BLO who is supposed to come to your residence to verify your documents. My area BLO flatly refused saying that it was not her job to go from house to house. If I wanted my card, I should show up at the Aaaganwadi center to get my details verified.  So I went looking for the local Aaaganwadi and landed there to find the village uncle of the BLO and some representatives from nearby societies all sitting on tiny kid stools. That was around 10th of March, 2019. She had some forms, but my name was not there. There was a lot of discussion on when I filled the form, how I filled it up and that it takes 4 months to get a voter id card etc etc. She had no answers, and neither was she interested in getting answers. At best, she could fill up the form and only then take some responsibility for it. She also told me that maybe the forms would arrive in a week or even might be automatically verified at the office. So, I sat patient for another 4-5 days and then having received no call from either the BLO, or the election office, made yet another call to the voter helpline. I was then told that the verification process by the BLO was compulsory and it was the duty of the BLO to do the house verification personally. It was of course clear that the lady BLO was in no mood to do that and would not even make a call. Further, there was no information when the physical verification forms would be received and acknowledged by her. Since she was doing purdah in front of her village uncle, apart from what could be like a possible monetary angle, patriarchy too was going to be a stumbling block in my quest for a voter id card.

Since I was determined to discharge my duty to vote only as an upright citizen, neither patriarchy nor corruption nor procrastination was going to get in my way to get my right to vote. My next stop was then the district election office. Armed with a fresh printout of my identity documents, I walked in the office and a bit of persuasion and lots of introduction about myself, one tiny process, but one giant obstacle in the process chart of getting a voter id card was lopped off. My application was not only field verified but also accepted in just 5 minutes on the 15th of March, 2019 after one month and 5 days of submitting my application. Within 3 days, I got an epic number. I checked my number in the electoral rolls and voila, it was there though I am not sure it had all the correct details.

Now starts the wait for a final physical proof of my right to vote, my voter id card. I assumed that once the epic number had come, the card would be there within 2 weeks. The election officer however told me that I would have to collect the card again from the BLO. One would have assumed that if they had your address, it could have easily been couriered. I was however very helpfully told by the voice at the other end of the 1950 helpline that it takes time to print election cards and it could easily take a month or so. In the meantime, post 30th of March, I have received two calls from the BLO village uncle who is our society neighbor to drop in at his residence to find out whether my card has arrived. I am not sure why I should be dropping in frequently at the residence of a village uncle. I understand that he is helping out and probably also has some future political ambitions, but right now it has to be between me and the Election Commission of India and their designated representatives.

So, I once again make a call to our BLO to find a way if she can intimate me when the card arrives. As usual, the BLO neither has a list handed over by the election office of whose cards have arrived, nor is interested to make a call and will definitely not tell you if your card has arrived even if you call her up and ask. I am expected to check in periodically at the aaganwadi to see if my card has arrived and that too only between 10 am to 12 noon and only if the BLO is present. This requires yet another couple of calls to the 1950 helpline who promises to check with the BLO why she will not make even a call of intimation and then revert back to me. I never got the revert but am sure he got a mouthful from the BLO probably asking him whether the ECI was providing any additional compensation for services rendered.

Since he did not revert, I had to revert, and it was obvious that the matter was status quo with only an added topped sheepish communication that it might take still another month for the cards to be printed. They also did not have any answers why they have no process either to send me a sms, or a call, or any intimation at all to collect my cards as and when they arrive. Apparently, the cards are printed in Chandigarh and arrive in batches and the election office has no Gantt chart nor tracking process to help figure out a way to even roughly estimate by when the card will arrive based on the date of generation of epic number.

Today is 13th of April, and 2 months, 3 days have elapsed since my online submission of voter id card application and still no sign or news of my voter id card. In the meantime, the Election Commission of India has conducted the first round of elections, banned the Modi biopic, stopped the telecast of the Namo channel, given notices to Yogi Adityanath, Mayawati and Maneka Gandhi and scores of other politicians. Maybe by next election, they will have been able to reach out to my BLO about the importance of facilitating access to a voter id card to the hapless voter in search of his/her right to exercise their vote and that neither purdah, nor patriarchy, nor corruption can come between us and our right to get a valid voter id card in Haryana. I finally close this story with a statement that I believe in the power of democracy and though it will take some time to function seamlessly, we will eventually reach there. This real life story has only been written with that aim in view.


My Citizen to Citizenship Journey

If you are born in a country, you do end becoming a citizen of that country by virtue of your birth status. But citizenship as the way I see it, is more evolved than just birth status and sometimes goes beyond the narrow confines of nationalism. Of course I love my country, but then I love the world too and so also civilization and its preservation. Citizenship to me is something more godly, more spiritual and it comes from being one with the world and its denizens.

Growing up in a particular country also implies growing up with its biases , injustices, inefficiencies inequalities, and poverty. People experience it first hand and it also gets honed and cemented through reading, viewing and discussions. In my case, since I was teaching economics and its implications, I was slightly more exposed of it through articles, data and information that came into my inbox through human and electronic interfaces. Slowly it started hitting hard and it starting hurting as to why am I part of it, but still not doing something about it.

Everyone earns a living and it is important for basic survival and happiness, but can you earn a living and still practice citizenship. Are they ways that you can contribute besides just going to attend neighborly events, weddings, parties, religious gatherings as a social and political animal. Everyone does something meaningful every day of their lives, except only their vision, scale and commitment levels may differ.

What if you had to really convert the meaningful involvement into a significant citizenship quotient that could bring change. How do you do that is a question that requires a great deal of thought. For a critical mass to practice citizenship on a more evolved level, they need understanding, space, time, and even at times resources to devote. Unfortunately society is wired in a way that revolves around at daily routines, earning a living, some entertainment and family topped with a bit of ego boosting. In a way, policy makers, government, society mores also do their bit in perpetuating lifestyles and values that ends must making life more like a roller coaster rather than something that is deeply meaningful, altruistic and balanced.

Obviously in our own ways, a lot of us are trying to bring change in mindsets, attitudes and the lens with which we view life. I am trying to do the same and therefore my journey from citizen to citizenship is also evolving. At times it is spiritual, sometimes reflective and sometimes replete with tongue in cheek humor. Bear with me, together you and I just might end up getting somewhere.


Citizens standing for Peace

14th of February 2019 henceforth, will no more stand for Valentine’s Day, instead it will be remembered as a day when a terrorist rammed hundreds of kg of RDX in a CRPF convoy killing 44 soldiers in Jammu and Kashmir.

It is an irony that a day meant for celebration for love turned thereafter, literally into an opportunity for self proclaimed nationalists to spew hatred and revenge. Some did it in television rooms, some in social media groups, and some even took to the streets to beat and intimidate. There were mobs, that not only took to gheraoing institutions to hound Kashmiri students, but also forced landlords to forcibly make these students vacate their rooms. Some others tried to find political legitimacy in market places by unleashing terror on helpless traders. There was mourning no doubt, but there was mayhem too by lumpen elements and some over-enthusiastic zealots keen to prove their nationalistic superiority through war-mongering.

Even after three days had elapsed, the madness had not stopped, although it had considerably been contained, with some contribution by disciplined institutional mechanisms of the establishment. However if something or someone made the difference in not allowing communal mindsets to completely take over the political discourse of the country, it was the role played by ordinary citizens across the country who rallied around for peace and restraint. Some gave clarion calls to debunk fake news and forwards, some shamed the hyper active war-mongers, and some willingly opened their homes to give shelter to students and persons who had been targeted. Some went to court to ensure protection mechanisms, some took to social media to negate the glories of aggression, some wrote moving stories of how families were destroyed in the wake of war.

The massacre was horrifying, but the intent of terrorism was far deeper than just the killing of 40 plus soldiers. It was an act of aggression to widen communal fault lines within society, and create more stooges of terror across the length and breadth of the country. This is where they faced the might of some ordinary citizens who rallied around the principles of the constitution and ensured that this country remains committed to the cause of peace and harmony.