Wednesday, September 13, 2023

Sample LOR image and links to LOR stance from 2021-23

 




LOR SEL stance on USMLE aspirants who haven't been mentored rigorously by us: Conversational transcripts 

5/16/2020, 4:48 PM] USMLE Aspirant 2015 MBBS: This is one of the patient I have been following for the past 3 days sir


[5/16/2020, 9:50 PM] Rakesh Biswas: Good. Well done. Please share it in the intern log book group. 

Ask everyone of the interns to provide inputs in the form of queries to it. 

Make sure you also do the same to their log books

[5/16/2020, 10:26 PM] USMLE Aspirant 2015 MBBS: Okay sir, will do. Thank you sir

[4/26/2022, 3:57 PM] USMLE Aspirant 2015 MBBS: Good afternoon sir.
I am reaching out to you regarding the letter of recommendation for  my application to an elective at Yale School of Medicine. I have drafted a letter, kindly have a look at it sir. 
Thank you.

[4/26/2022, 4:06 PM] Rakesh Biswas: Here are our LOR conditions πŸ‘‡


[4/26/2022, 4:12 PM] USMLE Aspirant 2015 MBBS: Sir, the LOR helps differentiate candidates for the said elective. I would be grateful if you could take a look at the draft that I sent you and maybe give me a more personalized one.

[4/26/2022, 4:19 PM] Rakesh Biswas: We will need to have a summative assessment of your competencies in medicine tomorrow for which you would need to check out our current patient in ICU and then identify his problems and then share your evidence based plan toward further management comparing with what has already been done till date. 

This particular patient I'm talking about has come with hypoglycemia and we have found multiple abscesses in his liver and lung. Ask our PG Dr Pradeep or Dr Manasa in ICU to direct you to that patient

[4/26/2022, 4:21 PM] Rakesh Biswas: This summative assessment will help us to understand if you are "able to comprehend and apply patient centred health care, which is our specialty

[4/26/2022, 4:25 PM] USMLE Aspirant 2015 MBBS: Sir, I belong to the 2015 batch of interns. I had come to narketpally regarding the application.

[4/26/2022, 4:29 PM] Rakesh Biswas: Yes I know. But we didn't have your summative assessment either. 

Without that how will we know if the LOR script is correct or not?

[4/26/2022, 4:53 PM] USMLE Aspirant 2015 MBBS: Sir, please do consider. It would be really helpful for my application.

[4/26/2022, 4:54 PM] Rakesh Biswas: Why should it be difficult for you to prove what you have written in the LOR?

[4/26/2022, 4:55 PM] Rakesh Biswas: πŸ‘†Is this a big deal for someone who has the competencies that the LOR claims? πŸ€”

[4/26/2022, 9:19 PM] USMLE Aspirant 2015 MBBS: I am sorry sir, I was preparing for my step exam and am in a time crunch. I cant demand it, and I apologize that I  couldn't give you the required assessment.

[9/13, 9:19 AM] USMLE Aspirant 2015 MBBS: Good morning, sir. I am from 2k15 batch. I am at the last step of my USMLE journey, sir, and I would like your help with my application. I would like to request a LOR from you as I intend to apply for internal medicine residency here in the USA. I look forward to hearing from you soon, sir. Thank you so much for your time and consideration.

[9/13, 9:23 AM] Rakesh Biswas: We give LORs only to those who work in our "ongoing departmental projects" and publish with us. 

For the rest there's the official LOR from the Principal office

[9/13, 9:27 AM] USMLE Aspirant 2015 MBBS: I understand, sir. Is there a possibility for me to request an IMSEL, which is an evaluation form for my performance during medical school, sir?

[9/13, 9:47 AM] Rakesh Biswas: From the principal office 

Rest is available open access in your online learning portfolio through our dashboard hereπŸ‘‡


[9/13, 10:19 AM] USMLE Aspirant 2015 MBBS: IMSEL is given by the HOD, sir. I could show you a sample draft someone received from their HOD. I would really appreciate it if you would have a look at it sir.

[9/13, 10:20 AM] Rakesh Biswas: Show me an online link that it's supposed to be given by HOD


[9/13, 4:36 PM] Rakesh Biswas: Thanks for sharing this! 

Talk of collective cognition. Around the same time I shared a similar idea here http://medicinedepartment.blogspot.com/2021/07/evidence-based-letter-of-recommendation.html?m=1 with quite a few US program directors!

[9/13, 4:39 PM] Rakesh Biswas: But the link clarifies that it's not the HoD but by a mentor who observed you in the medical field

That is exactly what I meant when I said that we give the LoR only to those students who have worked closely with us and communicated their work in wider platforms. That's when we actually get to mentor our students

[9/13, 4:43 PM] USMLE Aspirant 2015 MBBS: Thank you for this, sir. The effort and idea that went into this is truly inspirational.

[9/13, 4:45 PM] USMLE Aspirant 2015 MBBS: I would request you to take into consideration the medical school work that is part of the curriculum that can be used to assess my performance in providing me with the SEL.

[9/13, 4:48 PM] Indian medical school curriculum is stuck at blooms level 2!!

It means there's no real work for students in Indian medical schools!




Above webshot from : https://residencyexperts.com/what-is-the-sel-for-internal-medicine/

Saturday, September 9, 2023

Selection bias in real world academic intervention trials: hybrid human AI conversational learning

 Summary : Real world academic intervention trials go through a rigorous selection process that could be possibly fraught with bias. Hybrid human AI conversational learning transcripts below toward resolution of bias. 



 [9/8, 8:06 PM] Dr Anil : Government Approved Fees Of Private medical College in Rajasthan.
 
MD RADIO-3.6 CRORE
MD DERMAT- 3.3 CRORE
MD MEDICINE -2.4 CRORE
MS OBGY- 2.4 CRORE
MD PAED- 1.95 Cr
MD RESP MEDICINE -1.8 CRORE
MS ORTHO- 1.65Cr

Note-This University is not even a Deemed University


[9/8, 8:11 PM] Thanga Prabhu: Scam


[9/8, 8:12 PM] Thanga Prabhu: Not worth at all to even think of spending this kind of money. I will keep away from being treated by anyone who has gone down this route. We need a de novo definition of Healer.


[9/8, 8:13 PM] Thanga Prabhu: There are better ways to specialize and be a healer


[9/8, 8:13 PM] Sundar clinical engineer : Rationalising the education fees should be taken up hand in hand with rationalising treatment fees.


[9/8, 8:16 PM] Thanga Prabhu: Politicians own most med colleges. It is foolish to expect them to cull a hen laying eggs in crores. We have to move away from such scams. When demand drops, like engg seats these also will lose value


[9/8, 8:26 PM] Dr Anil : So the blame automatically goes to Politicians and NO self reflection from community,NO filling cases against MCI,Nothing to be done as a self healing practice by the community...🀐

9/9, 8:19 AM] Rakesh Biswas: Only 80% of the community is sheep while the rest 20% are wolves (politicians) in sheep's clothing!

[9/9, 8:20 AM] Sundar Pulmo : Wolves are there everywhere πŸ˜…


[9/9, 8:21 AM] Metapsychist Number 1 Kims 2015: Every voter has to be a politician in democracy.
If they don't play politics,politics play them.

Can play healthy politics too


[9/9, 8:23 AM] Rakesh Biswas: The voter (sheep prey) has to now become a predator (in sheep's clothing)?


[9/9, 8:24 AM] Rakesh Biswas: Healthy as in :

You don't eat me and I don't eat you! Let's all eat grass?



[9/8, 8:26 PM] Sundar CE : True that. But then politicians also own hospitals and it would pinch them to see the fees being reduced, no?

[9/8, 8:31 PM] Sundar CE : Or, the MCI liberalises the permission to open medical colleges that can share hospital facilities between them and have less faculty than it is today. I think Dr Devi Shetty had advocated this some time back. If this is a good idea, we will soon have surplus seats and prices will fall down.



[9/8, 8:32 PM] Sundar Clinical Engineer: https://youtube.com/watch?v=xewwXKqmCyY&si=6NRlC0LzBQV02nmW


[9/8, 10:50 PM] Thanga Prabhu: Faculty shortage is real but reducing them or overloading them with extra responsibilities is retrograde step. Tech plays big part in force multiplying existing faculty. AI and haptics alongwith gaming tech is already being used across our med colleges.


[9/8, 11:11 PM] Metapsychist Number 1 Kims 2015: Bigger problem is tech adoption in healthcare.
Not tech applications or use cases,as far as I understand from my miniscule experience!


[9/8, 11:29 PM] Thanga Prabhu: It has crossed that bridge a long time ago. Even tier 2 & 3 towns have lab autoanalyzers and issue printed reports. In kollegal 80 km away from Mysore they have 5G connectivity. Right next to sathyamangalam forest. TeleICU is delivered connecting Mysore to Kollegal. Let us now celebrate the tech adoption Indian ecosystem has achieved without too much fuss. Building on top of it is the opportunity today.


[9/8, 11:31 PM] Metapsychist Number 1 Kims 2015: Agree,time to celebrate!!πŸ₯³πŸ₯³


[9/8, 11:36 PM] Metapsychist Number 1

 Kims 2015: What does 'selection bias' mean in research methodology?
Need it for some other work


[9/9, 5:52 AM] Thanga Prabhu: Bread and butter of statistics. Any textbook will have it...


[9/9, 6:46 AM] SBB: Selection bias in statistics refers to a situation where the sample used in a study or analysis is not representative of the larger population it is meant to represent. This bias occurs when certain groups or individuals are more likely to be included or excluded from the sample, leading to inaccurate or skewed results. It can compromise the validity of statistical inferences and make it difficult to generalize findings to the broader population. Researchers often use various techniques to minimize selection bias and ensure that their samples are more representative.


[9/9, 6:46 AM] SBB: πŸ‘†ChatGPT answer


[9/9, 8:14 AM] Rakesh Biswas: Next prompt : @⁨Metapsychist Number 1 Kims 2015⁩ 

What are the techniques to minimize selection bias?


[9/9, 8:15 AM] Rakesh Biswas: πŸ‘†Another real world evidence for selection bias in academic intervention trials!


[9/9, 8:15 AM] Rakesh Biswas: Selection bias driven by conflict of interest


[9/9, 8:17 AM] Rakesh Biswas: Factors influencing outcomes of academic intervention trials


[9/9, 8:17 AM] Metapsychist Number 1 Kims 2015: Minimizing selection bias is crucial when conducting research or making generalizations. Here are some general strategies to minimize selection bias:

1. **Random Sampling:** Use random sampling techniques to select your sample from the population of interest. This ensures that each member of the population has an equal chance of being included in the sample, reducing the risk of bias.

2. **Stratified Sampling:** If your population has subgroups with distinct characteristics, use stratified sampling to ensure representation from each subgroup. This can help prevent bias that might result from one subgroup being overrepresented or underrepresented.

3. **Use Random Assignment:** In experimental studies, randomly assign participants to treatment and control groups. This helps ensure that any differences in outcomes are not due to pre-existing differences between the groups.

4. **Increase Sample Size:** A larger sample size can help reduce bias. With a larger sample, the chances of obtaining a more representative and less biased sample increase.

5. **Blind and Double-Blind Studies:** In experiments, use blind or double-blind techniques to prevent participants or researchers from knowing which group they belong to. This minimizes the risk of bias in reporting or interpreting results.

6. **Avoid Convenience Sampling:** Avoid selecting participants or data points solely based on convenience or accessibility. Convenience sampling can introduce significant bias because it doesn't represent the entire population.

7. **Longitudinal Studies:** If possible, conduct longitudinal studies that track changes over time. This can help account for potential bias introduced by variations at a single point in time.

8. **Transparent Methodology:** Clearly document your sampling methods and research design to make it transparent and replicable. This allows others to assess the potential for bias in your study.

9. **Consider Nonresponse Bias:** Be aware of nonresponse bias if some participants or data points do not respond or drop out of your study. Analyze the characteristics of nonrespondents to assess potential bias.

10. **Validate Data:** Cross-check data through multiple sources or methods to ensure consistency and accuracy, reducing the likelihood of bias due to data errors.

11. **Peer Review:** Have your study or research design reviewed by peers or experts in the field. They can provide valuable feedback and help identify potential sources of bias.

12. **Sensitivity Analysis:** Conduct sensitivity analysis to assess how sensitive your results are to different assumptions and potential sources of bias.

By implementing these strategies, you can minimize selection bias and improve the validity and reliability of your research or analysis.

[9

[9/9, 8:34 AM] Rakesh Biswas: πŸ‘πŸ‘full marks to chgpt

Now extrapolating to our current day academic intervention trials :

1) Randomly select all NEET PG aspirants 

2) Stratified selection based on special characteristics: general, reserved, EWS etc 

3) Random allocation to various departments! 

4) Devi Shetty? 

5) Don't let them know how they got selected into your academic department 

6) Stop this capitation business of convenience 

7) PaJR ProJR group and online learning portfolios for all students toward their life long CME monitoring 

8) See 7

9) Follow the drop outs who join IAS or become coaching center teachers instead of the noble prof 

10) Triangulation 360

11) See 10

12) Next prompt to cgpt : What's sensitivity analysis? 

The last paragraph by chgpt is a trashy opinion without evidence!



The image above is an   "illustration of hypothetical damage pattern on a WW2 bomber. Based on a not-illustrated report by Abraham Wald (1943), picture concept by Cameron Moll (2005, claimed on Twitter and credited by Mother Jones), new version by McGeddon based on a Lockheed PV-1 Ventura drawing (2016), vector file by Martin Grandjean (2021). Made available under creative commons licence here: https://commons.m.wikimedia.org/wiki/File:Survivorship-bias.svg#mw-jump-to-license

More about the image quoted from Wikipedia:

"During World War II, the statistician Abraham Wald took survivorship bias into his calculations when considering how to minimize bomber losses to enemy fire.[17] The Statistical Research Group (SRG) at Columbia University, which Wald was a part of, examined the damage done to aircraft that had returned from missions and recommended adding armor to the areas that showed the least damage.[18][19][20] The bullet holes in the returning aircraft represented areas where a bomber could take damage and still fly well enough to return safely to base. Therefore, Wald proposed that the Navy reinforce areas where the returning aircraft were unscathed,[17]: 88  inferring that planes hit in those areas were the ones most likely to be lost. His work is considered seminal in the then-nascent discipline of operational research."

Analogy to medical education and other life  
interventions: Intervention outcomes as to 
why mortality or drop out can be 
gleaned from "till end of trial participant 
survivors" and postulated as to 
why some didn't survive the system from the 
tell tale  markers of injury in those who didn't
drop out! 




Thursday, September 7, 2023

Task shifting the medical education bloom game through tech driven stakeholders such as third party administrators and insurance assurers

Summary : Currently medical education driven practice is a low level bloom game. Tech driven industry stakeholders show promising solutions 



[8/26, 8:33 AM] Thanga Prabhu: Like in UK medschool admission criteria both Attitude and Aptitude are given weightage. Last 5 years how one spent time is used as a factor. If a student volunteered in clinic, palliative care, hospital, rehab, etc. they are given higher rating. One can't pretend for 5 years right?
[8/26, 8:50 AM] Rakesh Biswas: In Indian medical schools, the entire focus is on memory (bloom game level 1) little on understanding (bloom game level 2) almost nothing about application (bloom game level 3) in MBBS. 

Post graduate Indian medical education is largely about learning application that was denied to them in MBBS and there is some backtracking to level 1 and 2 but almost no rising to level 4-6 which is about analysis (level 4), evaluation (level 5) and creating (level 6) because of the invisible rusty lock on their medical cognition that has gotten stuck as it lay unopened since their MBBS days! 

Incidentally the role of health IT begins from level 4 and this may explain why we don't currently need it in India! 



[8/26, 8:54 AM] Rahul healthcare 2.0: Very insightful


[8/26, 9:28 AM] Sundar IAMI: A very insightful method to stimulate reform of the medical curriculum, Doc! 🫑
We all could support an initiative to bring reforms in medical education in this direction. Without that we will be playing in the fringe areas of healthtech for decades to come. Lead us @⁨Rakesh Biswas⁩


[8/26, 9:35 AM] Thanga Prabhu: So we have whole mountain to climb now?


[8/26, 9:36 AM] Rakesh Biswas: Maybe circumvent or dig a tunnel! πŸ™‚πŸ™


[8/26, 9:40 AM] Rakesh Biswas: The problem is just to do with current policies in the medical curricula focusing on level 1-2 and completely ignoring the primary beneficiary of medical education (the patient)! 

We need to begin the curriculum at level 3, centred around the primary beneficiary and then move the game up and down the different levels! 

This can tremendously improve make in India at level 6 of this game


[8/26, 9:42 AM] Thanga Prabhu: Let us pivot and see it as a patient. I come to you with fever. How does the system look to me? Starts with naam kya hai 😭


[8/26, 9:43 AM] Sundar IAMI: Please show the way. There could be a focus group formed and grown to influence the authorities


[8/26, 9:44 AM] Rakesh Biswas: Yes it needs to start with someone holding hands and gently applying a temperature monitoring device for continuous monitoring along with symptom relief


[8/26, 9:46 AM] Rahul healthcare 2.0: Would the standard treatment workflows change? Or that they would be implemented in a more human centric way?


[8/26, 9:52 AM] Rakesh Biswas: Have presented these in JIPMER where a focus group was created to change the curriculum in 2015 chaired by MK Bhan who was a director there at that time. 

It wasn't looked upon well by many departments who would be most affected by patient centeredness as they are currently not encouraged to see patients. 

The only fall out of that was when one of the JIPMER faculty became AIIMS director later, our student @⁨Avinash Gupta Nepal⁩ was invited to present our work as archived here πŸ‘‡


From then my focus has been to develop departments of patient centred anatomy, Physiology, biochemistry, pathology and essentially we need to make make medical college teachers all round physicians who can deal with patients everyday (in a blended manner offline and online) as well as their own specialty devices, be it the cadaver, microscope or spectroscope!


[8/26, 9:54 AM] Rakesh Biswas: Even they would change as we get more and more patient centred and realize that the standard workflow solutions are at best average in terms of outcomes and level 4-6 can do much better! 

That is when we begin to move from standard static ontologies to dynamic rapidly evolving ontologies geared to deliver improved outcomes toward precision medicine led patient care


[8/26, 9:59 AM] Sundar IAMI: When I take a balcony view of all the discussions we are having, I see the following areas of reforms that we seem to be wanting:
a)Medicolegal - Dr Rajeev has already got started
b)Medical practice ethical guidelines embracing digital health
c)Affordable access to digital health, medtech and healthcare delivery technologies 
d) Self-sustaining ecosystem of new age ecosystem in healthcare
e) Digital health standards and adoption - Digital Health India has been founded - @⁨Pramod Jacob⁩ @⁨Uma Nambiar Dean IISc Medical School⁩ 
f) Preventive care 
g) Medical curriculum to prepare future doctors 

We seem to need reforms in many areas. That's why we are not able to acquire escape velocity. 

If we want to be effective we need to fan out in groups along these 7 areas and start aggressively bringing in changes. 
Views, perhaps, of a frustrated yet optimistic man


[8/26, 9:59 AM] Arnab Iami Iim: Does India have equivalent of nurse practioners?


[8/26, 10:06 AM] Rakesh Biswas: [8/24, 11:18 PM] Thanga Prabhu: can pharmacy serve as an interface?



[8/24, 11:30 PM] +91: It was difficult for us when we tried to transition pharmacists from a pure commerce-led mindset to a long term healthcare based model. That being said, couple of startups are trying to leverage the retail pharmacy network to setup e-clinics.



[8/25, 5:40 AM] Rakesh Biswas: Wow! What a find! 

Have become a fan of the authors after reading this paper! 

We have ourselves travelled from pillar (our tertiary care medical college centers) to post (even talked to post offices) to deliver comprehensive continuity of health care over the past few decades but never made much headway training pharmacists due to the barriers that @⁨~Vibhor Agnihotri⁩ possibly hinted at. 

Pharmacists have the selling retail mindset (even most doctors do) while comprehensive continuity of care requires a research mindset? Either way it's related to our field of medical cognition that we dabble in 24x7.

More about it later. πŸ™‚πŸ™


[8/26, 10:18 AM] Rahul healthcare 2.0: Brilliant thought. The trust of patients with pharmacists is often more than that with the doctor.

Pharmacists are in neighbourhood, you say hi even when you are not buying anything, local language, casual setting, direct access. 

Compare that to doctor's AC office, precise articulation needed (else doctor expresses impatience), condescending remarks on how you messed up your health, receptionist hop to meet doctor, you feel like you are being done a huge favour by being granted audience by the president, and of course you pay a bomb.

.
[8/26, 10:24 AM] Thanga Prabhu: Ahem...i object milord. You probably are seeing the wrong Dr.


[8/26, 10:43 AM] Bharat Gera: Quite true that the experience with doctors is not convenient..doesn't mean trust is lowered..some of the most crowded clinics are most preferred as people trust the doctor


[8/26, 10:53 AM] Bharat Gera: On the other hand, it does improve things vastly if clinics can provide a better experience..going through one right now with my wife at Proactive for Her..they have created an awesome ambience that appeals to the new generation woman..of course it costs a lot more to provide a Lux experience

[8/26, 10:54 AM] Rakesh Biswas: Like everyone throngs to most crowded hotel!


[8/26, 10:55 AM] Rakesh Biswas: Yes that's the reason corporate hospitals are such a big draw and government hospitals are a nightmare


[8/26, 11:01 AM] Bharat Gera: Combination of 4 Cs are needed by patient, Care, Convenience, Clinical Outcome and Cost..most important is always clinical outcome to gain trust..cost that patient is willing to pay is influenced by convenience and care as these are more directly measurable and observable..bit finally it is the clinical value that builds trust.. corporate hospitals or Lux clinics cannot sustain in long term without trust


[8/26, 11:02 AM] Vijayasimha Ajarananda: Absolutely. But I think the MCI was the bottleneck. The NMC is calling it task shifting. Wonder, if it's a word that implies 'give the boring and repetitive work out'.


[8/26, 11:24 AM] Thanga Prabhu: It means deskilling. A la Henry Ford the maverick who figured out if a task is broken up to its smallest possible component, it can be done by less skilled worker. Who can be paid a pittance. Model T was born. Healthcare is being equated to that production line...🀦🏽‍♂️


[8/26, 11:27 AM] Rakesh Biswas: Using a medical cognition lens :

All that demand for patients conciseness in information sharing making the doctor appear brusque and condescending is because of limited static ontology driven workflows where the doctor is trying to simplistically mental model and fit the patients information into a quick drug or device  outcome as his medical education is heavily influenced by the two! 

Pharmacy education needless to say is even more narrow and hence fraught with danger if it's standalone. 

As hinted by @⁨Sundar IAMI⁩ and others, we need to move away from the traditional dyadic and embrace the team driven information support systems approach where the individual competents of a deskilled workforce can be better regulated. 



[8/26, 11:30 AM] Sundar IAMI: Unfortunate. Healthcare needs its own Henry Ford visionary. Healthcare should *not* get inspired by the reforms in industries based on man-made inventions. Yet we must find appropriate ways of delivering healthcare by decentralisation and dispersed collaboration.


[8/26, 11:30 AM] Thanga Prabhu: One can assist a Dr. Replacing him with lesser trained folks is criminal in my world.


[8/26, 11:51 AM] Rahul healthcare 2.0: Haan... I forgot the family doctor, who has highest trust of the patient. If family doctor can be the single point of contact and one shouldn't need to run to specialists, that would be ideal for trust.

@⁨Sundar IAMI⁩ was sharing how patients nowadays want to directly go to specialists.


[8/26, 11:52 AM] Thanga Prabhu: Why the If? They exist

[8/26, 11:56 AM] Rahul healthcare 2.0: I meant the family physician refers patients to specialists (for a good reason) and the it's like passing the baton. 

Just a thought - Can the physician only get opinion from specialists and convey that to patient? Does the patient have to talk to specialist?


[8/26, 11:58 AM] Sundar IAMI: In the world of complex chips and software, the system engineer is a revered role and the competence takes years to acquire. Any system problem first gets analysed by the system engineer and then referred to the subsystem experts. In medical practice why should the general physician (who understands the complete human body and determines the expert to refer to) be the person with the least valued qualification?


[8/26, 12:00 PM] Thanga Prabhu: I can handle basics + emergency. When a patient has brain tumour, i cant operate in him. There i request my neurosurgery colleague to help. He steps in, does his magic and hands patient back to me. I am the constant, others come when i invite

[8/26, 12:09 PM] Thanga Prabhu: You are asking the right question. In a world of value added services...pay 150 to talk. 50 more for gaana. 20 more for chat. 30 more for movies. That model crept into healthcare delivery. Hence if I charge x then I need to do y activity. Market forces mean, higher demand/ lesser supply = Higher mrp. Medical education and so called star Dr now can ask for moon and it is delivered.


[8/26, 12:14 PM] Sandeep Dighe CPS: Starting with this...

In the olden days (My Grandfather's days, who was a GP having all "good" qualities mentioned here - "trust" of patients, knowing when to treat himself vs when to refer, numerous informal hello walk ins during Clinic times - used to be handled between actual Patients quickly with Medical Representatives etc), "GPs" as Family Physicians would be _confident_. Over time, dare I say, it became mandatory for the MBBS ppl who could get PG Seats to do Post-graduation for better prospects and only the slightly less capable ppl remained at MBBS/as Family Physicians; Society also played their part in this. Thus, the best don't stop at MBBS hence Family Physicians no longer command that kind of trust in Society...

Sounds debatable? *There can be exceptions in everything* but can we say it became "fashionable" to get more degrees rather than remaining an All Rounder GP (My Grandfather would even do Minor Surgeries, something rarely done by GPs nowadays...?)

Discussion welcome...

So my point is similar to one already expressed... ⤵️

[8/26, 12:15 PM] Thanga Prabhu: Secondary care is his solution. Can't medical College do 3 things: 1. Treat 2. Educate and skills training 3. Research to publish


[8/26, 12:27 PM] Rahul healthcare 2.0: True.. but can the whole process be controlled by the family doctor? So today when a family doctor suggests going to specialist, the specialist takes over.. not just the medical advice part ..since they are associated with some big hospital, everything from the tests to the experience is now transferred to the specialist. I guess that is where a patient feels that they are out of control, out of their comfort zone.. even the GP isn't able to interfere.

[8/26, 12:35 PM] Aniruddha Nene: Why can the payer ( insurance cos ) offer an advocate to support the patient during the care journey, rather than turning  to TPA and into claim rejection mode?


[8/26, 12:38 PM] Sundar IAMI: These models are being tried out .... check out "patient navigation". The problem here is that the patient navigator has no expertise nor credibility for his advice to override the suggestions from the Specialist

[8/26, 12:51 PM] Sundar IAMI: What if the district level medical colleges offer patient navigation? They have no mercenary incentive. They get rich set of cases for study. They have the expertise. If navigation is captured digitally on a platform, participating specialists and physicians and hospitals will be obliged to consider (even if they are permitted to modify) the recommended pathways.


[8/26, 12:56 PM] Sundar IAMI: Money spoils what would otherwise have been a great service of immense value to mankind. Some other models of rewarding the value created are missing.


[8/26, 12:56 PM] Rahul healthcare 2.0: Brilliant idea @⁨Sundar IAMI⁩ !! 

Would it be possible for a teaching hospital to take on more remote patients for navigating them and doing the analysis, evaluation and at times creativity @⁨Rakesh Biswas⁩  ?


[8/26, 1:03 PM] Sundar IAMI: Medical Science education has to take responsibility for making medical science suitable for ethical, equitable and effective delivery. And in that direction I haven't seen much evidence. For example there are many "not clinically approved" techniques of detecting breathing issues. Can medical science be extended to include them in assessing the condition with some uncertainty?


[8/26, 1:15 PM] Aniruddha Nene: Some of the private teaching hospitals especially in Maharashtra, do face   bed occupancy mandate as a  challenge.  They can become navigators. Navigation is  a virtual clinic for the teaching institution / unit.  NMC should relax the bed occupancy norms in favour of navigations performed for  remote patients. I believe that learning is as strong an incentive as monetary benefits.  πŸ™‚

Now if a navigator discovers  some services that are likely to be rejected in the claim settlement, the Navigator can  question. Of course they cannot always control the outcome, but it will certainly deter blatant exploitation.
[8/26, 1:51 PM] Sundar IAMI: I was discussing with @⁨Rahul healthcare 2.0⁩ the other day. A GP gets 20 to 30 patients a day in OPD and gets to earn Rs 3000 to Rs 5000 per day. He cannot sustain at this level for long. He is aware that his advice opens up a value chain of Rs 1000 to Rs 10000 per patient. So he makes a measly 1% share of the wallet (SOW). This acute asymmetry needs to be addressed.
What does the GP do? He opens a pharmacy store in his spouse's name and lab in his uncle's name. So his SOW increases to 30%. How can he resist this? And probably his grandfather doctor used to have his own dispensary and biochemistry lab too in those days. All he has done is to adapt to the evolution of the players scaling their operations.
There is an unfair asymmetry of revenue that the prescribing doctor sees. And we want him to deny himself the share of the value he has unlocked. Are we not being unfair?


[8/26, 1:53 PM] Sundar IAMI: A CEO of a new age care provider put it brilliantly. Healthcare is a sum of parts. So the one who is able to bring together all the parts takes the major share of the wallet. That's why the hospitals are able to sustain and the individual doctor is not.


[8/26, 2:17 PM] Sundar IAMI: Yet, for quality healthcare to be equitably accessible, we need to grow the ecosystem outside the hospital. That is the conundrum


[8/26, 2:42 PM] Rakesh Biswas: @⁨Rahul healthcare 2.0⁩ @⁨Avinash Gupta Nepal⁩ Best description of our current role πŸ‘
[8/26, 2:45 PM] Rakesh Biswas: Yes we try to do that and could do it better if we could make the curriculum patient centered enough to support this. Currently we are swimming against the tide


[8/26, 2:47 PM] Rakesh Biswas: Also doing all this partly blended in an online platform with audit trails makes it transparent and accountable to all stakeholders who can be easily shown how to join the dots and learn how the learnings and earnings get utilized


[8/26, 2:51 PM] Rakesh Biswas: Here's is a very interesting write up in "national medical journal of India" from 2018 that appears even more relevant now : 


"That year, as Head of Gastroenterology, I had organized a professional conference and had called three foreign speakers for the same. This was done on assurance of sponsorship by a multinational corporation (MNC) with a big presence in India. But just a month before the conference, the MNC had some legal trouble in India and started thinking of withdrawing operations from this part of the world and also withdrew the offer of sponsorship.'

‘That must have been terrible!' I said.

‘I was left with no option but to inform my foreign friends about this, cancel their talks and lose face. But then I was informed that tickets and stay had already been booked by my residents by paying an advance. Even if I was to cancel all arrangements, it would still lead to huge financial loss. I was extremely tense those days because I was not good at collecting sponsorships.'

‘What did you do?' I asked.

‘I discussed with my wife and she suggested that we pool in all our savings to get out of this situation.'

‘Did you do that?' I asked.

‘Thankfully no. It was during that time that Ruchir came to thank me again after a successful bariatric surgery. He had lost 40 kg. And during our two-minute talk he sensed my tension and asked me about the problem. I told him everything.'

‘What did he do?' I asked.

‘He laughed out very loudly and told me another joke. And ended his discourse with “What are friends for?”'

‘Did he agree to sponsor the speakers?' I asked.

Professor DS said, ‘He not only agreed to sponsor the speakers, he insisted that he will organize the banquet in a hotel. I remember that I had protested, because I was not buying anything from his company then. He just said, “Sir, you don’t have to. My company is doing well, and I am buying goodwill from some good people”. '

‘So, he bailed you out in difficulty,' I said.

‘I think he did more than that. In that banquet, he arranged a musical evening and sang himself. That’s when I learnt that he sings very well.'

Professor DS went on, ‘And my conference was remembered for a long time for that banquet. I was even invited by my friends to Europe and USA in reciprocation.' After a short pause he added, ‘Much later, when I retired and I was looking back at my career, I felt good about everything I did, except two occasions when I was helped by Ruchir. He somehow made me feel corrupt, where I accepted things that I did not deserve. He says he runs his business on goodwill, and I remember someone has said ‘“Never underestimate the allure of the Goodwill."



[8/26, 4:18 PM] Sundar IAMI: We will. But then we bear the consequence of a broken referral system that has no incentive to work. We are raising these matters here to find solutions to the root cause of the problem. Individuals are not bad. Every doctor who practices wants to do the best for the community. But the policies and structures force people to find unusual ways. The paper shared by Dr Rakesh is so insightful about how influences are exerted. The only way you can prevent such creative workarounds is to address the root cause - bring in fairness in remuneration. Then everything will settle down.


From creative commons licence accessed from and  attributed to the blooms taxonomy wiki  page 

Put on your diagnosing shoes



[8/27, 7:49 AM] AW : Someone posted a pic of shoes on side table of hospital ward and how his prof. (I would call Teacher) made diagnosis with one more more item on the table without even seeing the patient.


The art of Diagnosis!


[8/27, 8:58 AM] Thanga Prabhu: What was diagnosis? I would say dangerous Prof teaching and setting role model the wrong way. We should ever be humble and accept: katrathu kadugalavu, kalathathu kadal alavu. Tamil proverb


[8/27, 9:08 AM] Vijayasimha Ajarananda: OMG! Totally, over my head.


[8/27, 9:16 AM] +974 6642 7543: Remembering Dr. House


[8/27, 9:20 AM] Rakesh Biswas: Very famously taught by Sherlock Holmes and I quote, 

"SHERLOCK HOLMES:

 "Let him, on meeting a fellow mortal, learn at a glance to distinguish the
history of the man and the trade or profession to
which he belongs. By a man's finger-nails, by his
coat-sleeve, by his *boot*, by his trouser knees, by
the callosities of his forefinger and thumb, by his
expressions, by his shirt cuffs-by each of these
things a man's calling is plainly 
revealed"

JOHN H. WATSON, MD: "What ineffable twaddle!"

A. CONAN DOYLE

A Study in Scarlet


[8/27, 9:22 AM] Rakesh Biswas: "Inspection of the shoes is among the most re-
vealing and least used of all aspects of diagnostic
clothing analysis. As with other articles of cloth-
ing, shoes tell a story about their owner: work
shoes on an accident victim, for example, suggest
a different circumstance for an acute event than
slippers, dress shoes,- hunting boots or running
shoes. The presence of one slipper and one shoe
or of an open-toed shoe implies gout, trauma,
other arthritis or bunions on the unshod foot.
Shoes without laces, or laces undone, are more
comfortable to an edematous or inflamed foot.
Patients with Parkinson's disease or other motor
limitation may simply lack the dexterity and
flexibility to tie their shoelaces. A prosthetic shoe
lift is a more obvious clue to a chronically short-
ened leg than simple inspection of a supine pa-
tient. The pattern of wear on the soles of shoes
testifies to gait. For example, a rapid distinction
between old and new hemiparesis in a patient in
an emergency room can be achieved by examining
the shoes, in which the differential wear of a
long-standing limp is clear. Does a patient have
a backache? A glance at new or very high-heeled
shoes may solve the diagnostic mystery. In a
patient with diabetes, the source of sepsis may
be clarified by blood and serum stains seen on
socks or by the presence of ill-fitting shoes."


[8/27, 10:05 AM] Thanga Prabhu: Sir Dr Arthur Conan Doyle was a physician. Sherlock Holmes is his alter ego

[8/27, 10:05 AM] Thanga Prabhu: Elementary my dear Watson 😎


[8/27, 10:11 AM] AW : Will HCIT be able to pickup these contexts and make sense of it? 
That's y medicine is fuzzy and difficult to simulate.

[8/27, 10:14 AM] Sundar IAMI: Sure, these are good to arrive at a starting guess. Surely you cannot treat the patient based on such a diagnosis! So, how valuable is it when there are more deterministic methods?

[8/27, 10:16 AM] Rakesh Biswas: Left looks more worn out than the right? 

Now read the Sherlock Holmes quote shared above!

[8/27, 10:17 AM] AW : With such methods one could come pretty close to 2-3 Diff. Diags. And investigate only for those reducing need for compressive workup every time

[8/27, 10:20 AM] Sundar IAMI: And evenly worn out. So probably the left leg is shorter than the right. Chronic. Should be complaining of knee problems in the left leg


[8/27, 10:20 AM] Sundar IAMI: Would affect his gait too. So the hip joint would also wear out unevenly


[8/27, 10:21 AM] Sundar IAMI: Laceless shoes - pedal oedema


[8/27, 10:22 AM] Sundar IAMI: Difficulty in bending down


[8/27, 11:20 AM] Rakesh Biswas: The most important and easiest way perhaps one can make a diagnosis is to capture all the event data points in a timeline that led to the current problem events that require a diagnosis.

Now one may need to look at the fact that "diagnosis" itself is nothing but a compressed version of all the data points that have been brought together and tied to form an "ontology."

The diagnosis could be something known in the past (often labeled static ontology but a more appropriate term could be current dominant ontology).

Again need to be careful with this word "ontology" as it unfortunately has many usages across the spectrum of knowledge! In simple terms an  ontology depicts objects and it's ties and if objects are information-data, ontology are packets of bound knowledge (while epistemology is unbound although in it's popular usage it's often confused with ontology).

If no one gets the diagnosis, it's something new that changes past static ontology (that's the problem with this term, it can't be static if it can be changed @⁨Metapsychist Number 1 Kims 2015⁩) and once one is able to grow the diagnosis utilizing newer data points that till then may have been to quote, "from the static ontologies perspective, simply variations labeled statistical noise; from those discovering new ground, phenomena of central interest!" 


@⁨Vijayasimha Ajarananda⁩ the author is a physicist at TIFR who is working on computational thinking aka problem formulation, abstraction, complex-systems thinking, a subset of asynchronous intelligence (father of today's AI)! 

Coming to the main driver question from Sundar to the above Sunday stream of consciousness, our holy grail is reaching a singular diagnosis to the point where the treatment automatically becomes to the point but current medical ontologies are limited in terms of that as most of our diagnostic and therapeutic armamentarium have marginal efficacies at best and hidden harms and costs at worst!  


[8/27, 11:32 AM] Sundar IAMI: A great post, Doc. But isn't diagnosis more than a relational set of various datapoints? It is a set that embeds inferences and even biases the author towards a few directions. In that sense it is a set of vectors, derived from the related set of datapoints. It also builds on the past inferences. I agree - ontology doesn't describe it well. The inference vectors are also characterised by likelihood estimations.


[8/27, 11:45 AM] Sundar IAMI: Of course it can. It has demonstrated far more complex tasks. The question is - is it worth it? Will a doctor be willing to take in such observations or inferences from another person and proceed with differential diagnosis? Whenever I diagnosed a complex system (in system engineering), I could trust someone else's input and diagnose the fault only when I was away from the site. I couldn't bring myself to do that when I was present at the site. So I am able to relate to the discomfort of doctors in diagnosing remotely.

Saturday, September 2, 2023

Anatomy of a medical degree: a skeleton to be fleshed life long? You can check out but never leave?

 [8/29, 1:05 PM] Rakesh Biswas: 


Yesterday was the convocation ceremony of our MBBS 2017 entry batch and they placed this very interesting exhibit at the gate! 

Would be good to learn from your interpretation of the subconscious message they were trying to convey!



[8/29, 3:54 PM] SΔΉ : They like the anatomy department the most may be.  They want to share their memories during their convocation. Think positive πŸ™‚


[8/29, 4:10 PM] A: Maybe they got just the basic degree

[8/29, 4:13 PM] A : Add ons will be speciality,super speciality  and accessories like fellowships

[8/29, 4:19 PM] Rakesh Biswas: Yes @⁨~Dr A⁩ this appears to be the consensus as of now:

[8/29, 1:16 PM] S: My take - MBBS is a bare-bone degree


[8/29, 1:17 PM] Rakesh Biswas: One hypothesis:

Currently they have gotten the skeleton (similar to what the LLM provides to build upon) from their MBBS course and now post convocation they may be looking forward to see some flesh.


[8/29, 1:23 PM] SBB: You mean meat around the bones?


[8/29, 4:16 PM] Rakesh Biswas: All the way upto the skin πŸ‘


[8/29, 4:23 PM] S : Anatomy is cornerstone for all other medical depts/ subjects, where dead persons teach the live persons (apart from FMT) 😊

[8/29, 4:25 PM] Rakesh Biswas: Agree! Medical diagnosis begins with the anatomical diagnosis. πŸ™‚πŸ™

[8/29, 1:11 PM] Metapsychist Number 1 Kims 2015: There can be many interpretations based on eye of the beholder.To name a few.

1.Lifelong learning attitude.

2.You enter medical college as a live person,and leave as a dead person

[8/29, 1:12 PM] Rakesh Biswas: How does the image correlate with life long learning?

[8/29, 1:13 PM] Metapsychist Number 1 Kims 2015: That learning doesn't end with convocation.

[8/29, 1:14 PM] Rakesh Biswas: You mean currently they have gotten the skeleton (similar to what the LLM provides) and now post convocation they may be looking forward to see some flesh?

[8/29, 1:14 PM] Metapsychist Number 1 Kims 2015: Yep

[8/29, 1:15 PM] Pt HYD: If plants/trees are sufficiently available, thereby oxygen sufficiently available, there would not be any patients, then  Doctor's not needed, Hence they become skeleton

[8/29, 2:37 PM] AK : Something that AI cannot do is interpret the subconscious message.
[8/29, 2:38 PM] AK : atleast for now
[8/29, 2:38 PM] AK : continues from womb to tomb