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. 


Abacus, one of the earliest form of Calculators, originated around 5000 years back. If we want to look at something, somewhat near to our timeline, we need to go to around 1890. In this year the Hollerith Tabulator was created, it is an Electromagnetic machine use to summarize information present on punch cards. Fifty years from here (the 1940s), Alan Turing created the Turing machine, first of its kind Analytics model to decode encrypted German Messages. From here on the world saw a growing need for computers. Fast forward to today’s day and age; we have reached the point where people have experimented with using DNA as a storage medium. DNA - Deoxyribonucleic Acid which stores the genetic instruction of the body. Oh, by the way, a DNA can store around 215 petabytes of information which is equivalent to 215 million gigabytes. Phew! That’s a huge number. 

Over the past 120 years, Healthcare is one of the most unchartered territories when we consider Analytics. Organizations have focused on Supply Chain, Finance, Human Resources, and other domains. Compared to all these industries, Healthcare is in a stage of discovery. At some point in everyone’s life, one has been to a hospital. In my case I had gone to the US for a business trip in Feb 2006, and what do you know, I got chickenpox. I had to visit an “Urgent Care” where I waited around 20-30 minutes in the lobby before my turn came. Once my turn came, we went to the examination room where the nurse came and asked me some more questions. The nurse also had a form with her clipped on a writing pad. She asked me various questions around my lifestyle for example
  • Do You Smoke?
  • Do You Drink?
  • Are you on any medication?

Along with this, she also took my vitals in terms of Blood pressure, height, weight, and temperature. She noted down all this information on a paper form. After all of this is when arrived the Physician. The physician looked at the information filled on the chart by the Nurse, then looked at the spots and said – "You have Chicken Pox." The Physician then gave me my prescription and also gave me a date for my next visit, which was around 4-5 days away. It was now time to leave, and I had to pay a bill of approx. $200/- out of my pocket, note that this did not include the bill for medications which I had to buy from a nearby pharmacy.

Looking Back

Let us look back at some of the important aspects of the scenario depicted. If it came to your attention, the nurse was using a “Paper Chart,” this is the biggest challenge for the field of Business Intelligence and Analytics. Data in an electronic format is very much necessary for anyone to perform Analytics or create a simple Report depicting Insights viz. “No of Patients visiting the Hospital Daily.” 

The second aspect, I had to wait for 20-30 minutes before the physician could see me. The scenario depicted was not an Emergency, but wait times are important and along with it the Patient Volume, which could be Monthly/Weekly/Daily/Hourly. One of the Largest US Based IDN’s (HCA hospitals) takes the help of large Electronic Billboards to keep people informed of the wait times.

The third aspect is the final bill amount which in this case, I had to pay out of pocket. In my case, I was on a Business Trip and had Insurance but did not have an Insurance Card. In other words, you can say it was not cashless insurance. In general, it would be important to know the approximate cost of treatment upfront.

One final aspect which does not come out that is unlike any other industry; the Healthcare Industry has multiple entities viz.

  • Healthcare Provider – The Hospital / Care Provider, which can be a large hospital to a clinic.
  • Health Insurance Company 
  • Pharmaceutical – Where the patients buy medications
  • Pharma and Life Sciences – These organizations focus on developing new medications
  • Medical Devices – These organizations develop Biomedical Devices viz. Glucometer

Deep Dive

Now that you have a basic idea about Healthcare and some of the touchpoints let us deep dive into more details around some possible scenarios of Analytics which can be done/achieved. These scenarios are not limited to just a Hospital/Care provider but would cover various entities. Let us divide the scenarios across the different types of Machine Learning Algorithms and see what we could do with each specific example.

a. Regression

Regression in its simplest format can solve very limited problems but is the basis for various other algorithms. In the case of healthcare, one can use Regression for some of the below examples.

Predicting Length of Stay(LOS): The Revenue for a hospital is directly proportional to the total number of patient visits/discharges. In 2018 my mother had to be admitted for treatment of Pneumonia, and we were not sure how long would it take to get a discharge. Discharge is one aspect, but there is a certain amount of time my mother had to spend in the ICU. The uncertainty around the duration causes a lot of stress, and this is not limited to me but impacts any individual. Regression can be used to calculate the Length of Stay, which can be beneficial to the hospital for planning and scheduling but also the Patients relatives. This length of stay can be broken down by predicting the number of days in ICU as well as in a ward/room before discharge. Assuming this is a supervised learning model, some of the data elements which would be needed to effectively predict/build an algorithm would be Primary Diagnosis, Secondary Diagnosis, Comorbid Conditions, Admit Date, Discharge Date, Days in ICU, Severity of Illness, Prior Admission Details, Medications, Physician Specialty, Date of Birth, Lab Results. 

Reduce Patient Readmissions: Once we have predicted the length of stay, the next logical step would be to find out the possibility of the patient getting readmitted. Readmission is another key concern, and in countries like the US, if a patient gets readmitted within 30 days, there is a possibility of a penalty to the Hospital. The readmission could be due to various reasons viz. “Patient Refused to take therapy” or “Hospital Acquired Infection” to name a few. In this case, we would require similar information/data elements like for LOS. Also, one can consider the geographical location of the patient (Address/Zip Code). We could also leverage external databases related to the weather. E.g., Cases of Pneumonia increase when the weather suddenly changes from Hot and cold and vice versa.

Healthcare Cost Prediction: The Healthcare Cost referred to, can be the Total cost of treatment based on the diagnosis/treatment. By the way, when we talk about regression, we refer to predicting a numerical value, and in this case, one can also find the possible Insurance Premium a member would pay. In this case, as well, one would require data elements used in LOS and Readmissions. Along with this, one could also require Hospital Address/Zip Code, the Cost of Treatment (Prior Years).

Chronic Disease Prediction: At the beginning of the paper, we spoke about the Rise of Computers. In this day and age one cannot live without a Mobile phone (which is a powerful computer in itself). It was 2009, and I had gone to visit an Orthopedic Physician as I had got a stiff neck. The doctor came, asked me mover your neck to the right, left, up down and laterally. One question he asked me, “What is your Profession?” I said I work in the IT Industry (Software). To that, he promptly mentioned, “Your profession is your problem.” For anyone who works in the IT industry, there is a very high probability that a person will get some neck or back problem. By the way, when we look at the young population, kids today use mobiles from the age of 5 & 6 and the probability of getting a similar problem will be pretty high. One can use Logistic Regression to predict the probability of such cases. The data required for such cases might not be so easy to gather since we require Lifestyle details. Things like smoking and drinking are captured during the Patient visit, but what one eats daily is not captured in any system unless the patient is using some system and many such patients are willing to share this data. have 

b. Classification and Clustering

The Banking Industry uses Analytics, especially in terms of Identifying Fraud. I will give a simple example which helps with the explanation. I assume you have Debit Card or a Credit Card and you have used the same. If you use your card 3-4 times in a span of 10 to 15 minutes, it is more than likely you will get a call from the Bank. The customer support executive will ask you if you have just used your card. The reason this happens is because the system has flagged the transaction as a possible fraudulent case. The basis for flagging the transaction could be basis the fact that historically you don’t have such a spending pattern. On similar lines, one can also leverage these algorithms to identify Fraudulent Claims. A very apt example which I can quote here is identifying cases which could be denied for Medical Necessity. To detail the same, let us say a Patient comes to the hospital complaining of chest pain. The physician checks the patient vitals, asks the nurse to do an ECG and other relevant tests if required. All the data looks normal, but still, the Physician asks the patient to stay in the hospital. The patient gets discharged after four days. In this case, one can understand the patient is kept under observation for one day, but more than that without any supporting information, there are very high chances of the claim getting denied. Other examples where a similar algorithm can be used is the Classification of diseases based on Medical data. One can identify patients with similar issues/symptoms and diagnosis.

Classification is used when we have labeled data, if not, then we use Clustering. So, in case we don’t have Labelled information related to Fraudulent old claims, we can use Clustering to identify similar claims.

c. Natural Language Processing

In the lifecycle of a patient, the hospital captures a lot of information. This information comes in the form of Physician notes, Nurse Notes, Lab & Radiology Reports, and Discharge summary. All of this information together forms Clinical Documentation. This documentation, when in electronic format, can be used in a very powerful way, and we will talk about a couple of use cases. Before a new drug comes in the market, there are a lot of clinical trials which are done. To do clinical trials, one needs to identify and enroll patients for such trials. The process is manual and time-consuming. Identification of Trial Patients is where one can use Clinical Text Mining to mine the Clinical. One such tool is CLIX ENRICH from Clinithink. The second aspect where we can use Text Mining is to identify disease progression. Mining Clinical notes of similar patients, we can gather a lot of information. Clinical Notes mining is possible by leveraging the power of SNOMED-CT. If you are not aware, SNOMED is a collection of medical terms and it has 100,000 plus concepts. Using this and the logic of engrams, we can identify key terms in the Clinical notes. Example, if the note says “Patient comes to the Hospital complaining of Chest Pain,” using SNOMED API’s we can find out if the word “Chest Pain” is a finding, diagnosis or any other aspect. This logic can also be extended to Medical Coding and Hierarchical Condition Coding where Medical Coders have to identify Clinical Terms for billing purposes.

d. Time Series Forecasting

In any business, it is very important to identify the volume of customers expected each day. The same is true in case of a Hospital as well; here is where one can use Time Series Forecasting, to forecast the Hourly Patient Volume. This volume can be forecasted based on prior patient volumes for the past three to four years. In addition to this, one can also leverage seasonal factors like climate to identify the impact on patient volume. Based on the seasonal data, one can also go to the extent of identifying Patient Volume for a specific type of disease. For examples, Emergency Cases/Fractures cases increase during festivals like Janmashtami. On similar lines, burn cases increase during Diwali. All of this information, when tied together, can be used to forecast Patient Volume and accordingly, we can also calculate the Resourcing needs.

e. Survival Analysis

Survival Analysis is generally used for a time to event analysis. This technique is widely used in the manufacturing industry to calculate the warranty period of the product. In healthcare, we can use Survival analysis to calculate the Probability of Survival after the diagnosis of a Disease. As per the Analysis published by IHME, Global Burden of Disease, Cardiovascular Diseases, and Cancer are the Top two causes of deaths in 2017. Cancer has been the top four causes of death since 1990, and as per National Cancer Registry Programme (NCRP), more than 1300 Indians die every day due to cancer. If Cancer is identified at an early stage, the chances of survival increase. In this case, the data which we would require is quite varied; we have listed some of the data elements which can be considered. Age, Gender, Genetic Information (Defects), Skin Type, Location (Geography), Lifestyle (Alcohol, Tobacco, Food), Type of Job/Work. Using this information (Survival Analysis), the physician can decide the medication and diet plan for the patient. Small changes in the lifestyle of a patient can help increase the survival rate of the patient.

f. Deep Learning

Deep learning is a branch of machine learning which can be used to mimic the human brain. There are various Machine Learning Algorithms around Deep Learning, a couple of them being Artificial Neural Network (ANN) and Convolutional Neural Network (CNN).

Diagnostic systems – Neural Networks can be used to detect heart problems; this can be done using ECG information as well as other details like Stress Test. Some of the prominent use cases here are to identify Metastatic Breast Cancer and Skin Cancer. A very common example where Convolutional Neural networks (CNN) are used is in Pneumonia detection. Stanford University has built a 121 Layer CNN to identify 14 different diagnosis just using X-Rays.

Biochemical analysis – Analyze urine and blood samples, as well as tracking glucose levels in people with diabetes, determining ion levels in fluids, and detecting various pathological conditions. 

Drug development – Another key area is the development of drugs for various conditions – working by using large amounts of data to come to conclusions about treatment options.

How can India Leverage Analytics? 

One of the biggest challenges for India is the lack of data(electronic), more than that the means to capture data electronically. Many hospitals do not use any form of a HIS (Hospital Information System) or EHR (Electronic Health Record). If you want to do Analytics, you need data and that too a large amount. Even if we implement a HIS/EHR from tomorrow, we would have to wait for two years to do some decent Analytics. HIS/EHR is a long-term solution, but not something organizations can use immediately. For us to start leveraging the power of Analytics, we need to take the help of Transfer Learning. In simple terms, Transfer Learning is using the research done while solving one problem and applying the same while solving another but related problem. My team.  


Each year lot of deaths happen due to Pneumonia, and the best diagnosis for the same is using a Chest X-Ray. A Chest X-Ray is the most common diagnosis used in any scenario. 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. One example is leveraging ImageNet to identify Pneumonia in Chest X-rays. If one would want to build this from scratch one can even leverage datasets provided by National Institutes of Health (NIH) which has 100,000 Chest X-Rays. In recent times Stanford has released 224,000 Chest X-Rays which can be leveraged for building an improved model.

If you would like to understand more about Healthcare you can download my book “Healthcare Decoded – Begin Your Health IT Journey”.  


1. Retrieved from
2. Comparing Hospital ER Wait Times. (2011, May 2). Retrieved from
3. Burden of Disease. (n.d.). Retrieved from
4. Life Sciences 06/16 Copy. (n.d.). Retrieved from
5. Neural Networks in Healthcare. (2017, April 6). Retrieved from

Harish Rijhwani 
Harish Rijhwani has 17+ years of experience in Healthcare Information Technology. He has worked in Atos Syntel (15 years), Hinduja Global Solutions (1.5 years) and currently in CitiusTech. Provided Solutions across various Healthcare areas Clinical, Revenue Cycle Management, Telemedicine, Analytics, Non-Clinical: HR Payroll, Finance & Supply Chain. Multi-faceted with experience across Solutioning, Pre-sales and Delivery. He has been a Visiting Faculty/Speaker/IT Judge at various events/institutes viz. Welingkar, Somaiya, VIT, Symbiosis, and NASSCOM. He has a passion for teaching Healthcare IT and has done BE Electronics & MBA Systems. He is also author of the book Healthcare Decoded – Begin your Health IT Journey
Read more »

Algorithms in #EMR by Dr. Joyoti Goswami @Joyoti10

Practicing physicians these days are barraged with a lot of technical jargon promoted by the Information technology professionals such as Big Data, Hadoop, Artificial Intelligence and Predictive analytics. For a physician not introduced to the these terms, the conversation is of little value unless there is a specified value in the clinical setting.

Pulitzer Prize winning author Siddhartha Mukherjee in his book ‘Emperor of Maladies’ has quoted “The greatest clinicians who I know seem to have a sixth sense for biases. They understand, almost instinctively, when prior bits of scattered knowledge apply to their patients—but, more important, when they don’t apply to their patients.”

So the accumulation of all the 6th sense of multiple physicians in the form of scattered notes in documents is the food for Big Data professionals, who curate this data manually with standard vocabularies and then analyse patterns that can help physicians make informed decisions at the point of care.

While Predictive Analytics is a huge winner if there is genomic data available, the fact remains that in current clinical scenarios, complete genomic sequencing is not yet the norm. They are still restricted to the areas of research as the cost of doing a complete sequencing of the genome is still about $ 1000 and very few institutions are prescribing it as a norm in routine clinical practice. Once that is in place, it can lead to a whole lot of practical applications and use cases making the use of technology like Big Data and Hadoop. 

Till then, use cases which use traditional computing powers like SQL and simple queries and algorithms running on top of it could be used to get the benefits of clean data and technology in the clinical workplace.

In an attempt to utilize Predictive Analytics and Artificial Intelligence in the world of EMR and healthcare data, a list of 5 practical clinical use cases and 5 administrative/Claims Related use cases of how data could be used at the point of care and integrated with the EMR is listed out below:

Clinical Usecases

1 Acute Kidney Injury

According to Statistics, 1.2 million people per year get AKI during a hospital stay and 300,000 people in the US die annually due to AKI, this is more than breast cancer, prostate cancer, heart failure and diabetes combined. 

The successful documentation and implementation of the AKI algorithm published by the NHS is a systematic and step by step program that can help reduce the incidence of Acute Kidney Injury and the mortality and comorbidities associated with it. The e-alert for AKI installed in the LIMS (Laboratory Information Management Systems) alerts physicians when a patients’ Serum Creatinine rises greater than 26 mmol/litre from a baseline within 48 hours or there is a rise of 50% or more in 7days and/or the urine output is < 0.5 ml/kg body weight/hour.

2 Sepsis Management

Sepsis or SIRS (Systemic Inflammatory Response Syndrome) accounts for 20 to 30% hospital deaths and $15.4 billion in annual healthcare costs. Needless to say early diagnosis and treatment is critical to optimal care. 

In a study, it was found that 24% of infected patients with 2 or 3 qSOFA (or Quick Sepsis Related Organ Dysfunction Assessment) points accounted for 70% of the deaths. An automated EMR based Sepsis identification system helps to detect cases with sepsis. A sepsis sniffer algorithm in ED identifies patients who exhibit at least 2 of the 3 criteria of Altered Mental Status, Fast Respiratory Rate and Low Blood Pressure and initiates the Sepsis Order set if the results of the score warrant it. The content on the Sepsis Order Set helps to make sure that none of the key variables for the management of sepsis is missed out.

3 Initiation of Statins

Mayo clinic has implemented a single click decision support tool within the EMR to automate the calculation of 10-year atherosclerotic   cardiovascular risk and populate the statin choice decision.  Based on the risk score calculation parameters of the ASCVD (atherosclerotic cardiovascular disease), the tool populates whether the patient needs a statin or not and if yes, which statin would be the best choice. This is defined on the basis of an algorithm running which has historical data of similar patients along with their outcomes.

4 Algorithm to identify major cardiac adverse events while on statins

Cardiovascular disease is a leading cause of death worldwide and statins are largely prescribed for the same. A study was conducted using historical data to identify patients with MACE (Major Adverse Cardiac Events) while on statins for primary prevention.  This algorithm achieved a 90 to 97% positive predictive value for the identification of adverse cardiac events while on statins

5 Detection of Diabetic Retinopathy

Diabetic retinopathy is the fastest growing cause of blindness and screening patients with diabetes for retinopathy has been mandated as part of all the Quality Measures such as MIPS, HEDIS and others. Google analysed a dataset of  128,000 images of the retinal fundus and used that to predict retinopathy based on the lesions present on the scan such as microaneurysms, haemorrhages, exudates etc. A blindfold comparison of the results predicted by the AI algorithm was compared with the results given by experienced ophthalmologists. The AI algorithm had an accuracy of 90% which is a huge win especially in areas where there is a shortfall of specialists to interpret the results.

In the areas of diagnostics especially interpretation of Imaging results, a lot of good work is going on and soon AI capabilities will lead decision making in the interpretation of reports.

Physicians working closely with Data scientists can help create some exciting algorithms given that healthcare centres today have large volumes of data sitting in their EMRs. A physician with even 50 patient records of 2 years has sufficient information to derive useful insights on predicting interesting patterns on the future health and preventive measures therefore can be planned accordingly. The approach for healthcare institutions should be to first identify their most pressing problems and then evaluate if any kind of Prediction of solutions to those problems could lead to better outcomes in patient care. A well thought and organized approach could go a long way to develop algorithms that work well for the hospitals and ambulatory clinics to achieve their goals and have favourable outcomes for both the patient and the hospital.

Administrative Use Cases:

In Patient Registration systems and billing systems, the algorithms can have a different flavour, some of which are listed below:

1. Healthcare Utilization Management: Integration of hospital resource utilizations in different departments, risk management and quality assurance into a management dashboard in order to ensure the judicious use of the facility's resources. A review of the procedures and services rendered by the hospital and the resources used by them (such as rooms, timings, instruments, admin and clinical staff) can help to identify under utilized and spare capacity of the hospital. This can be inbuilt in the system with the help of algorithms so as to get an optimal effect.

2. Capturing Missed and Incorrect Charges: Many facilities lose revenue due to billing errors done manually. Billing amounts associated with each DRG (Diagnosis Related Group) can be used to create models and compare them with the actual billing. Outliers in patient invoices can help to identify the likelihood of missing or incorrect charges. The higher prioritized invoices can then be reviewed to confirm the charges, which may be incorrect, over billed or under billed.

3. Predicting denials: There is a constant tug of war between the providers and payers about the claims to be settled. Most of the denials are due to incorrect documentation or missing information, duplicate claims, service already paid as a part of bundled services or others, services not covered by payer and late submission of claims. All of the above can easily be avoided by streamlining coding and billing processes. The industry benchmark for medical billing denials is 2% and in practices between 5% to 10%. Reworking on denials has a cost associated, so having algorithms running within the systems can help to streamline these efforts.

4. Predicting wait times and No shows: Idle time in clinics, both for patients and providers can be frustrating. In departments where procedures are done, it is possible to predict treatment durations by looking at historical data. Similarly the number of no shows of scheduled appointments can be predicted by including variables like age of patient, severity of disease, previous appointment regularity of the patient and others. This could help the facility to take in additional patients on the free slots proactively.

5. Measuring Bad debt, Days in A/R and DNFB (Days in Total Discharged Not Final Billed): These metrics help to determine the effectiveness of the claims generation process and effectiveness of collection efforts.

A number of KPIs tracked by hospitals and payer systems can be in built within the Revenue Management Systems and Scheduling systems. These include patient costs, ROI of the facility, Average Patient Wait times, Average patient appointment scheduling times and Patient Satisfaction.

With the healthcare market growing and many EMRs, both locally created and branded companies in the play, it is eventually the content within the EMR that can make it user friendly. Many content companies offer excellent standardised algorithms and content that can be integrated within the EMR, but there always remains physician preferences based on specialty, region of practice and other personal preferences. The end user i.e. the physician ultimately needs to decide on what suits his practice and then have the algorithms accordingly tailored within the EMR.

Dr. Joyoti Goswami
Healthcare expertise of over 20 + years. Clinician having worked in specialty hospitals as medical officer and currently in the Healthcare Information Technology domain since the last 10 + years. Have a good combination of clinical and technology skills in multiple areas. Worked with multiple EMRs such as Allscripts, GE Centricity, Athena health and Nextgen
Read more »

What does it take to build real-world #AI enabled healthcare solution? By Vijayananda J, @vijayanandaj

Development of new technologies has undoubtedly enabled several breakthroughs in the healthcare industry. To put it simply, it has revolutionised the growth of healthcare from nascent patient-care to accomplishing treatment of life-threatening diseases. High-performance computing and the availability of digital data have extended these remarkable outcomes explaining why AI-based healthcare solutions are at top of the funding lists and are continuously gaining traction.

Read more »

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.
Read more »

I & L to #AI & #ML in Healthcare by Jyoti Sahai, @jyotisahai

Have you ever wondered why if confronted with any illness symptoms that appear even a bit abnormal, we prefer to consult with a doctor in a large hospital only, even though a more competent doctor may have a clinic next door itself.

Read more »

Artificial Intelligence #AI can help address current healthcare challenges in India, Dr Sandeep Reddy @docsunny50

Earlier this year, while making a keynote speech at an Artificial Intelligence (AI) in Health conference in Dubai, I mentioned that AI techniques can be used to address some of the intractable health issues in developing countries. 

Read more »

4 hints to get started with #AI in your company by Devesh Rajadhyax @deveshrajadhyax

Most companies are working on Digital Transformation today, and Artificial Intelligence is a critical part of that transformation.

Two questions immediately present themselves-
1.    What is Digital Transformation and how it is different from the IT/ICT transformation that is happening since for than four decades?
2.    Why is AI a critical part of this transformation?

Read more »

Artificial Intelligence #AI – the new hope for Pharma R&D - By Manishree Bhattacharya @ManishreeBhatt1

Pretty much every article starts with the challenges that pharmaceutical industry across the globe is facing. It is a difficult industry and everybody acknowledges that, considering the time to develop an original drug (10-15 years), the costs involved (last time I checked it was USD 2-3 billion), the high attrition rates of drug candidates (1 out of 5,000 or 10,000 leads make way for FDA approval), the tough regulatory environment which is varied across countries and geographies, and the rising pressures on pricing (pricing advantage for truly outcome-driven therapeutics). All of these, with the looming patent expiry, the imminent entry of generics, and the tantalizing RoIs, make it even more difficult.

Read more »

Artificial Intelligence #AI Could Add $957 Billion to Indian Economy, According to New Research by @AccentureIndia

In a recently published report by Accenture, they have highlighted the need for india to invest in AI, we bring you the excerpts of the report. (The following content is sourced from the Accenture report).

Artificial intelligence (AI) has reached a tipping point. The combination of the technology, data and talent that make intelligent systems possible has reached critical mass, driving extraordinary growth in AI investment. Across the world, G20 countries have been building up their AI capabilities. The power of AI starts with people and intelligent technologies working together within and across company boundaries to create better outcomes for customers and society. But India is not fully prepared to seize the enormous opportunities that AI presents. Even with a tech-savvy talent pool, renowned universities, healthy levels of entrepreneurship and strong corporations, the country lags on key indicators of AI development. Much work remains. 

Read more »

#AI in Healthcare by @deveshrajadhyax

There are some subjects that invoke sharp and contrasting emotions in the society. In present day India, the GST tops the list of such things that are considered boon by some and curse by others. New technology usually does this to people. The steam engine, the telephone and the computer all have been greeted both as the savior and the nemesis of the mankind. 

Read more »

Four ways in which #AI can help humankind @deveshrajadhyax

Artificial Intelligence is receiving more than its fair share of public attention. On one side there are promises of miracles, while on the other side there are warnings of doomsday. What is probably missing is a simple listing of clear benefits. This is article is an attempt to create such a list.

Read more »

Understanding the Medical Diagnosis processes, to build an AI based solution by @msharmas

Human Intelligence

is The ability to adapt one's behavior to fit new circumstances.

In Psychology, human intelligence is not regarded as a single ability or cognitive process but rather as an “array” of separate components. Research in building AI systems has focused on the following components of intelligence: [1]
  • learning,
  • reasoning,
  • problem-solving,
  • perception, and
  • Language-understanding
These components of human intelligence are also utilized during diagnosing a patient and defining the treatment plan and protocol for the patient.

Read more »

Is superintelligence the inevitable next step in evolution? by Dr. Roshini Beenukumar, @roshiniBR

Experts predict that by 2050, there is a 50% probability that AIs which will match the intelligence of an average adult human. It is not a long wait, isn’t it?

Last week, my husband and I finally sat down to plan our summer vacation. After spending two full hours on 10 different tour websites, we ended up being completely overwhelmed by the options; all-inclusive vs half-board, city vs seaside or sea vs land. 

Read more »

The Current Status of 8 Future Technologies on Healthcare by @msharmas

It's mid-2016, and here is a look at the current status of 8 Future Technologies that might be having a significant impact on Healthcare

Most if not all these technologies will make an impact on Healthcare, and hence it is important to understand the various scenarios and the stories detailing how the experts from across the world are incorporating these technologies in healthcare

Read more »

House MD vs Doctor #AI- Who will turn out to be the better by @RoshiniBR

House MD vs Doctor AI- Who will turn out to be the better diagnostician?

Do a google search for “all-inclusive beach holiday” and all you see for the next weeks are advertisements for all-inclusive holidays following the virtual you. Google knows you better than your family or friends- creepy but true! Whether or not we realize it, we have made the decision to donate our data to the virtual world.

Can we put our data to better use – to improve healthcare on a scale unimaginable a decade or two ago?

Read more »

Benefits of an AI-Based Patient Appointments service for Hospitals by @msharmas

One of the areas where AI can be implemented in the Hospital with high volume of transactions, is the Appointments Scheduling of Patients. On any given day, there are a finite number of slots available for a doctor, e.g. 10 min or 30 min slots, depending on whether its a first visit or a follow up visit. In most hospitals, Routine patients are scheduled in advance and some patients are scheduled based on an urgency, to the physician schedule.  [Denton et al - 8]
A typical workflow for booking an appointment can go like this:

1. Patient calls (or visits) the hospital, and speaks to the person at the reception, at a specific department
2. The person looks up the available time slots, that a doctor is free and available in the clinic
3. Consults with the Patient on the best time possible for her appointment and then schedules the appointment

Read more »

Zen Clinicals: An Activity & Workflow based solution (1 of 4)

Part 1 of 4:
Recently, during the Gartner Symposium, it was predicted that cognitve platforms would take over a lot of activities. Keeping this future at the back of our minds, its important for the EHRs of today to metamorphosize to the Cognitive Computing platforms of tomorrow, and fast.
Read more »


Popular Posts