Wednesday, February 27, 2013



Music By :  Bappi Lahiri
Lyricist :  Gulshan Bawra

Music On : EMI 



Educated, traveled, intelligent, wealthy, and a businesswomen Mala Mathur would like to marry a man who can look after the household duties while she works. Her uncle, Mr. Mathur, ridicules this idea, and tells her that she will never find any husband in this manner. Mala advertises in the newspapers, and gets tons of responses. She decides on marrying a young man by the name of Shekar Sinha, who is poor, unemployed, and willing to commit himself to household duties. Before the marriage, Shekar is asked to sign an agreement, which he does. And thus begins the marriage, which is not really a marriage, but an employment contract, which is terminable after one year. The question is will Shekar be able to survive for one year - especially when he does not know how to cook meals for his wealthy "wife".
Record Details
TitleAgreement - 45 NLP 1090
Star Cast
Rekha, Utpal Dutt, Shailendra Singh, Asrani, Aruna Irani, Sujit Kumar, Bindu, Sheetal, Dinesh Hingoo & Viju Khote
DirectorAnil Ganguly
ProducerJogendra Singh
MusicBappi Lahiri
LyricsGulshan Bawra
Movie Releasing Year1980
GenreOriginal Soundtrack
Made InIndia
ManufactureThe Gramophone Company Of India Limited
Serial No45 NLP 1090
Side One
  • Jane Kyon Mujhe
Lata Mangeshkar
  • Jeena Bhi Koi Jeena Hai
Shailendra Singh
Side Two

  • Aapne Pyar Diya
Shailendra Singh & Chorus
  • Suno Suno Baat Pate Ki
Lata Mangeshkar


 DISCLAIMER: This blog promotes the appreciation of vinyl records in an encoded audio format called MP3 and hereby disclaims any violations of copyright law. The author of this blog does not engage in buying and/or selling songs in MP3 or any other format on this blog. Visitors of this blog are encouraged first and foremost to buy original records (to maintain the posterity of the vinyl record) and secondly, audio CDs. The music that is available here is meant for promotional and appreciation purposes only.


Tuesday, February 26, 2013

Different Strokes for Different Social Media Folks

This week has been a milestone for this blog, with the number of page views surpassing the 100,000 mark since its inception in March, 2009. This achievement gives me a chance to reflect on my use of social media, which seems to be different than for others. Maybe social media is just like anything else in life, with different people preferring differing aspects and uses of it.

Clearly I have enjoyed being a blogger. This blog has provided me a nice platform from which to share my thoughts and views with a worldwide audience. As I have noted before, I am not a stream of consciousness blogger, feeling compelled to post things continuously, such as every day. Rather, I prefer that my postings carefully reflect thoughts and ideas on specific topics.

Another social media activity I enjoy is Facebook. I have three main networks on Facebook, and I enjoy seeing them interact with my personal and professional life. These networks include my professional colleagues, my family and friends, and my high school classmates. Facebook is also a great medium for sharing and annotating photos and other digital artifacts.

Two social media activities I personally find less valuable to myself are Twitter and LinkedIn. I know this is at odds with some dear friends and colleagues. However, tweets just seem too short (I often have more to say than can be expressed in 140 characters!) and fleeting (it seems you either catch something in the Twitter stream or never see it again) to sustain my interest. Sometimes I try to get involved in the Twitter dialogue at conferences, but soon find it distracting to try to otherwise participate in the meeting (whose primary value is usually the direct personal interaction). I have the most fun with it when I use it to editorialize about presentations at those meetings, but I find it difficult to sustain any sort of dialogue when doing that.

As for LinkedIn, while I am sure it is highly valuable for some people, I find that my major interaction with it is to receive requests for connections and endorsements. I am happy to connect with anyone on LinkedIn, but I have yet to find value in the hundreds of connections I have made. I also do not like to make generic LinkedIn endorsements, instead preferring to serve as real references for colleagues and current or former students when they need it for specific opportunities.

I know that other people have different preferences for social media, and perhaps my own preferences will change over time. And of course, it is likely that the social media tools and sites will change over time, or that new ones will emerge. For now, however, I will keep blogging and Facebooking while still trying to determine the value of other social media.

Sunday, February 24, 2013

Data Mining Systems Improve Cost and Quality of Healthcare - Or Do They?

Several email lists I am on were abuzz last week about the publication of a paper that was described in a press release from Indiana University to demonstrate that "machine learning -- the same computer science discipline that helped create voice recognition systems, self-driving cars and credit card fraud detection systems -- can drastically improve both the cost and quality of health care in the United States." The press release referred to a study published by an Indiana faculty member in the journal, Artificial Intelligence in Medicine [1].

While I am a proponent of computer applications that aim to improve the quality and cost of healthcare, I also believe we must be careful about the claims being made for them, especially those derived from results from scientific research.

After reading and analyzing the paper, I am skeptical of the claims made not only by the press release but also by the authors themselves. My concern is less about their research methods, although I have some serious qualms about them I will describe below, but more so with the press release that was issued by their university public relations office. Furthermore, as always seems to happen when technology is hyped, the press release was picked up and echoed across the Internet, followed by the inevitable conflation of its findings. Sure enough, one high-profile blogger wrote, "physicians who used an AI framework to make patient care decisions had patient outcomes that were 50 percent better than physicians who did not use AI." It is clear from the paper that physicians did not actually use such a framework, which was only applied retrospectively to clinical data.

What exactly did the study show? Basically, the researchers obtained a small data set for one clinical condition in one institution's electronic health record and applied some complex data mining techniques to show that lower cost and better outcomes could be achieved by following the options suggested by the machine learning algorithm instead of what the clinicians actually did. The claim, therefore, is that if the data mining were followed by the clinicians instead of their own decision-making, then better and cheaper care would ensue.

As done in many scientific papers about technology, the paper goes into exquisite detail about the data mining algorithms and the experiments comparing them. But the paper unfortunately provides very little description about the clinical data itself. There is a reference to another paper from a conference that appears to describe the data set [2], but it is still not clear how the data was applied to evaluate the algorithms.

I have a number of methodological problems with the paper. First is the paucity of clinical details about the data. The authors refer to a metric called the "outcomes rating scale" of the "client-directed outcome informed (CDOI) assessment." No details are provided as to exactly what this scale measures or how differences in measurement correlate with improved clinical outcome. Furthermore, the variables of the details of care for the patient that the data mining algorithm supposedly outperforms are not described either. Therefore anyone hoping to understand the clinical value that this approach is claimed to have improved is not able to do so.

A second problem is that there is no discussion about the cost data or what cost perspective (e.g., system, clinician, societal, etc.) is taken. This is a common problem that plagues many studies in healthcare that attempt to measure costs [3]. Given the relatively modest amounts of money spent on the care that is reported in their results, amounting only to a few hundred dollars per patient, it is unlikely that the data includes the full amount of the costs of treatment for each patient, or over an appropriate time period. If my interpretation of the low value of the cost data is correct (which is difficult to discern from reading the paper due, again due to lack of details), the data do not include the cost of clinician time, facilities, or longer-term costs beyond the time frame of the data set. If that is indeed the case, then it would be particularly problematic for a machine learning system, since such systems make inferences limited only to the data that is provided to the model. Therefore if poor data is provided to the model, its "conclusions" are suspect. (This raises a side issue as to whether there is truly "artificial intelligence" here, since the only intelligence applied by the system is the models developed by their human creators.)

A third concern is that this is a modeling study. As every evaluation methodologist knows, modeling studies are limited in their ability to assign cause and effect. There is certainly a role in informatics science for modeling studies, although we saw recently that such studies have their limits, especially when revisited over the long run. In this study, there may have been reasons for the clinicians following the more expensive path or confounding reasons why such patients had worse outcomes, but they cannot be captured by the approach used in this study.

This is related to the final and most serious problem of the work, which is that the modeling evaluation is a very weak form of evidence to demonstrate the value of an intervention. If the authors truly wanted to show the benefits of the system and approach they developed, they should have performed a randomized controlled trial that compared their intervention with an appropriate control group. This would have led to the type of study that the blogger mentioned above erroneously described this to be. Such a study design would assess some of the more vexing problems we face in informatics, such as whether the advice coming from a computer will change clinician behavior. Or, when such systems are introduced into the "real world," whether the "advice" provided will prospectively lead to better outcomes.

I do believe that the kind of work addressed by this paper is important, especially as we move into the area of personalized medicine. As eloquently described by Stead and colleagues, healthcare will soon be reaching the point where the number of data points required for clinical decisions will exceed the bounds of human cognition [4]. (It probably already has.) Therefore clinicians will require aids to their cognition provided by information systems, perhaps one like that described in the study.

But such aids require, like everything else in medicine, robust evaluative research to demonstrate their value. The methods used in this paper may indeed be the methods to provide this value, but the implementation and evaluation described miss the mark. That miss is further exacerbated by the hype and conflation the ensued after the paper was published.

What can we learn from this paper and its ensuing hype? First, bold claims require bold evidence to back them up. In the case of showing value for an approach in healthcare - be it test, treatment, or informatics application - we must use evaluation methods that provide best evidence for the claim. That is not always a randomized controlled trial, but in this situation, it would be, and the modeling techniques used are really just preliminary data that (might) justify an actual clinical trial. Second, when we perform technology evaluation, we need to describe, and ideally release, all of the clinical data so that others can analyze and even replicate the results. Finally, while we all want to disseminate the results of our research to the widest possible audience, we need to be realistic in explaining what we accomplished and what are its larger implications.


[1] Bennett, C. and K. Hauser (2013). Artificial intelligence framework for simulating clinical decision-making: a Markov decision process approach. Artificial Intelligence in Medicine. Epub ahead of print.
[2] Bennett, C., T. Doub, A. Bragg, J. Luellen, C. VanRegenmorter, J. Lockman and R. Reiserer (2011). Data mining session-based patient reported outcomes (PROs) in a mental health setting: toward data-driven clinical decision support and personalized treatment. 2011 First IEEE International Conference on Healthcare Informatics, Imaging and Systems Biology (HISB 2011), San Jose, CA. 229-236.
[3] Drummond, M. and M. Sculpher (2005). Common methodological flaws in economic evaluations. Medical Care. 43(7 Suppl): 5-14.
[4] Stead, W., J. Searle, H. Fessler, J. Smith and E. Shortliffe (2011). Biomedical informatics: changing what physicians need to know and how they learn. Academic Medicine. 86: 429-434.

Friday, February 22, 2013

AMIA Clinical Informatics Board Review Course Announced

This week, the American Medical Informatics Association (AMIA) released the details of the Clinical Informatics Board Review Course (CIBRC), for which I will serving as Course Director. I am excited to see this come to fruition, and look forward not only to these course offerings but also the expansion of the program as other certifications in informatics for non-physicians become reality in the years ahead.

The course will be offered four times in person before the first offering of the certification exam in October. There will also be an online version of the course that can be accessed in tandem with the live courses or taken alone. A question bank of practice questions will also be made available. The four offerings of the course will be:
  • April 12-14 - Bethesda, MD (registration has opened for this course and will soon be available for the others)
  • June 7-9 - Philadelphia, PA
  • August 9-11 - Portland, OR (I am thrilled to have one offering of the course in my own city!)
  • September 7-9 - Rosemont (Chicago), IL
The details of the course are provided on the AMIA Web site:
One question those contemplating pursuing the certification exam might ask is whether this review course is the best preparation for them. I believe the course will be best for those already familiar with the content of the field. The review course material will necessary be at a high level, aiming to provide a broad overview of what is on the exam so that the potential exam candidate can get the big picture and determine where they need to shore up their knowledge.

For those with less knowledge of the field, a better approach might be to start with a course that more fundamentally builds their knowledge base. The 10x10 ("ten by ten") course is option, although even it is only a single course and may not be enough for those with little or no formal training in the field. The next Oregon Health & Science University (OHSU) offering of its 10x10 course runs from April through July; registration is available on the AMIA Web site. For those individuals desiring more training, a more comprehensive course of study leading to a Graduate Certificate or master's degree may be a better option. AMIA has a database of educational programs, which includes our program at OHSU.

The rollout of the course is an exciting event. For convenience, here is an index to some of my important previous postings on the clinical informatics subspecialty:
For those who are not physicians and desire certification in informatics, do not despair! AMIA and others are at work developing plans for certification of non-physicians (as well as physicians who not eligible for the board certification, which requires an active primary specialty certification). In the meantime, I look forward to seeing those who are eligible in one of the course offerings!

Thursday, February 21, 2013

Good Nutrition for Children During Examinations

Sheela Paul,  N.Amudhavali –Dietitian(MVNES)

Good nutrition is often the last thing on one’s mind during exam time. In fact, good nutrition should be part of a student’s study plan because it is going to help with those tests. The better the fuel the brain gets, the better the ability to study. During the exams, students spend long hours studying and staying awake. Eating the right kind of

Monday, February 18, 2013




Music By :  Vijay Singh
Lyricist : Dev Kohli

Music On : Music India Limited 





1. Aaja Mere Sanam 

  Singer/s : Lata Mangeshkar  
 Duration : 05:55 mins 

2. Dil Ki Is Dehleez Tak 
 Singer/s :Ashok Khare                  
  Duration : 04:20 mins 

3. Dil Ki Is Dehleez Tak Jo  
Singer/sLata Mangeshkar                   
  Duration : 04:24 mins

4. Geet Mere Hothon Ko                
Singer/s :  Lata Mangeshkar                 
Duration : 05:51 mins 

5Ik Haseena Diwana Kargayee                
Singer/sVinay Mandke,Annette Pinto,Suneeti Devi                  
Duration : 07:58 mins

6Is Dafaa                 
Singer/s :Lata Mangeshkar                  
Duration : 08:24 mins


7.  Kabhie Ajnabi The              
Singer/s :  Lata Mangeshkar,Suresh Wadkar                   
Duration : 07:27 mins


 DISCLAIMER: This blog promotes the appreciation of vinyl records in an encoded audio format called MP3 and hereby disclaims any violations of copyright law. The author of this blog does not engage in buying and/or selling songs in MP3 or any other format on this blog. Visitors of this blog are encouraged first and foremost to buy original records (to maintain the posterity of the vinyl record) and secondly, audio CDs. The music that is available here is meant for promotional and appreciation purposes only.