Thursday 2 May 2024

29m quantified self pajr - 3

 1) [28/04, 7:43 pm] Dr.Dinesh Datta: Check out concept of SDA(Specific Dynamic Action)

[28/04, 7:50 pm] Dr. Avinash Kumar Gupta: Specific dynamic action (SDA), also known as the thermic effect of food (TEF), refers to the energy expenditure associated with the digestion, absorption, and metabolism of food. Essentially, it's the energy your body uses to process the food you eat. Different macronutrients have different SDA rates. For example, protein has a higher SDA compared to fats or carbohydrates. This means that your body burns more calories digesting and metabolizing protein compared to other nutrients.

[28/04, 7:50 pm] Dr. Avinash Kumar Gupta: How clinician can use this info for this case?

[28/04, 8:02 pm] Dr.Dinesh Datta: Basically..

BMR is the energy your body needs to function at rest.SDA(aka thermic effect/dietary induced thermogenesis) is extra energy your body burns to process food.It covers digestion,absorption and storage of nutrients from what you eat.Proteins have high SDA,requiring more energy to process compared to carbs and fats.

Sda is another layer over BMR in understanding total energy expenditure in body.


Total energy expenditure is BMR+SDA+Activity level



Basically we say,bmr is engine size of your metabolism and sda is fuel efficiency.


By understanding TEE,we can tailor/better understand weight gain/loss

[28/04, 8:03 pm] Dr. Avinash Kumar Gupta: Useful




2) To calculate your Basal Metabolic Rate (BMR), we can use the Harris-Benedict equation. 


For males:

BMR = 88.362 + (13.397 × weight in kg) + (4.799 × height in cm) - (5.677 × age in years)


First, we convert your height to centimeters:

5 feet 5 inches = 165.1 cm (1 foot = 30.48 cm, 1 inch = 2.54 cm)


Now, plug in the values:

BMR = 88.362 + (13.397 × 81.5) + (4.799 × 165.1) - (5.677 × 30)


BMR ≈ 88.362 + 1093.955 + 791.334 - 170.731

BMR ≈ 1803.92 calories per day


So, your Basal Metabolic Rate (BMR) is approximately 1803.92 calories per day. This is the number of calories your body needs to maintain basic physiological functions at rest.




3) [19/04, 7:06 am] Dr. Avinash Kumar Gupta: Cgpt


The estimation of calories burned during activities like walking involves several scientific methods and studies. The calorie expenditure for an activity like walking is typically determined through experiments that measure energy output in controlled settings. Here’s a brief outline of how scientists might arrive at such data:


1. **Metabolic Measurements**: One common method to determine calories burned is through direct and indirect calorimetry. Direct calorimetry measures the amount of heat the body emits, but it’s complex and not widely used. Indirect calorimetry is more common and measures oxygen consumption and carbon dioxide production. Since the body needs oxygen to burn nutrients for energy, and produces carbon dioxide as a byproduct, measuring these gases can give a reliable estimate of energy expenditure.


2. **Using Metabolic Equivalents (METs)**: The concept of METs (Metabolic Equivalents) is often used. One MET is defined as the energy it takes to sit quietly, equivalent to a calorie expenditure of 1 kcal/kg/hour. Physical activities are assigned MET values based on how much harder your body works relative to sitting quietly. For example, walking at a mild pace (about 3-4 mph) typically has a MET value of around 3.0 to 4.5 METs.


3. **Calculations Based on METs**:

   - First, the MET value is multiplied by the person’s body weight in kilograms.

   - Then, this number is multiplied by the duration of the activity in hours to find the total caloric expenditure.


   For instance, if walking at a mild pace has a MET value of 3.5, an 80 kg person walking for 1 km (which they might complete in about 10-15 minutes, or about 0.2 hours), the calculation would be:

   \[

   \text{Calories burned} = 3.5 \text{ METs} \times 80 \text{ kg} \times 0.2 \text{ hours} = 56 \text{ kcal}

   \]

   (Note: This is just an example; actual values might vary based on the specific speed and individual metabolism).


4. **Field Studies and Adjustments**: Scientists also conduct field studies where they monitor real-life activities rather than controlled laboratory settings. They might use portable devices that track physiological responses like heart rate, breathing rates, and even sweat rates to estimate energy expenditure more accurately in day-to-day activities.


5. **Calibration and Validation**: Any method used to calculate or estimate caloric expenditure is usually calibrated against more established methods (like those using laboratory equipment) and validated in different populations to ensure accuracy across age, body weight, and fitness levels.


When it comes to the provided data — an 80 kg person burning 80 calories walking 1 km — this might be a slightly simplified or rounded figure used for easy calculation. In actuality, the calories burned can be influenced by factors like walking speed, terrain, efficiency of movement, and individual metabolic differences. The figure could be derived from an average or estimated value that broadly fits the profile and activity described.

[19/04, 7:28 am] Dr. Avinash Kumar Gupta: "Definition

A MET is defined as the resting metabolic rate, that

is, the amount of oxygen consumed at rest, sitting quiet-

ly in a chair, approximately 3.5 ml 02/kg/min (1.2

kcallmin for a 70-kg person).* As such, work at 2 METS

requires twice the resting metabolism or 7.0 ml O,/kg/min

and three METS requires three times the resting

metabolism (10.5 ml 02/kg/min), and so on"




29 m quantified self pajr -2


Energy expenditure 











Weigh loss trend
2 may - 80.5 kg



Average energy expenditure daily by calculation (differs alot from values in Google fit)

BMR for 82kg weight, 29M = 1800

Calorie burnt in moderate speed walk is equal to weight of person for each km. So 80kcal per km.

Average daily walk - 7km

Average daily expenditure in walk = 560kcal

Average daily calorie expenditure = 2360kcal



Calorie intake data till 2 may from 7 April.

2 may - 1300 kcal
1 may - 1800 kcal
30 apr - 1600 kcal
29 apr - 1040 kcal
28 apr - 2300 kcal 
27 apr - 950 kcal
26 apr - 1530 kcal
25 apr - 1280 kcal
24 apr - 1500 kcal
23 apr - 1400 kcal
22 apr - 2075 kcal
21 apr - 1200 kcal
20 - 
19 apr - 1200 kcal
18 apr - 1150 kcal
17 apr - 1500 kcal
16 apr - 1400 kcal
15 apr - 1500 kcal
14 apr - 1425 kcal
13 apr - 1250 kcal
12 apr - 700 kcal
11 apr - 1450 kcal
10 apr - 1400 kcal 
9 apr - 1200 kcal
8 apr - 1620 kcal 
7 apr - 1600 kcal


Pics of a few meals


Example of calorie counting on a day

Breakfast 
- litti (4) - 240 kcal

Lunch
- chhachh - 50 kcal
- tea with sugar - 50 kcal

Evening
- Lassi - 350 kcal
- mango Pana - 100 kcal

Night
- curd - 250 kcal

Total 
   - Calorie intake = 1040 kcal
  - walk = 8 km
  - calorie expense = 2520 kcal (google fit shows 2140 kcal)
  - calorie deficit = 1480 kcal.


Graph of calorie, spent and intake. From 7 April to 2 may. Spent Average is take as 2360, orange is intake and blue showing is deficit.


Height 5.5

Weight 80.5 from 87

BMI -  29.5 to 32

Abdominal girth - 102 from 112 cm

Waist circumference - 100 from 106 cm

MAMC 33 cm




Sunday 7 April 2024

29M quantified self PaJR

PaJR = patient journey record where patient advocate share a patient's updates according to guidance they get from their primary care provider who is supported by a group of volunteer medical professionals (ranging from medical innovators who may be engineers and  medical students, to residents and consultants. Basically a knowledge network). [Currently Implemented as a whatsapp group]

The patient advocate ensures privacy, data management, and continuity of care.

The updates are:

- lifestyle modification related eg. Calorie deficit

- medication adherence related,

- patient education queries,

etc.



The current case is a 29 year old otherwise healthy but obese man having weight of 86.5-87 kg even after being physically active. His height is 5 feet 5 inches, BMI is 32 and below is picture from Google fit (mobile) data about his daily walk (since many months his average is 5km daily).





All the analytics and charting below is done with help of ChatGPT (free version) and google collab (to run python code output given by chat gpt).


Estimated Basal Metabolic Rate (BMR) for this 29-year-old obese man is approximately 1877.22 kcal/day. 


For 1 month of calorie deficit (31 days)  patient maintained average daily total walk of 5km. Checked weight nearly every week - 86.5, 85, 84, 83, 82.5.


These are his daily calorie intake for 31 days. (Calorie counting done manually by patient advocate. )


1. 600 kcal

2. 750 kcal

3. 1200 kcal

4. 1000 kcal

5. 1100 kcal

6. 800 kcal

7. 900 kcal

8. 1700 kcal

9. 1300 kcal

10. 1400 kcal

11. 2000 kcal

12. 1500 kcal

13. 1250 kcal

14. 1500 kcal

15. 1800 kcal

16. 1450 kcal

17. 1150 kcal

18. 1400 kcal

19. 1450 kcal

20. 1500 kcal

21. 1800 kcal

22. 1500 kcal

23. 1400 kcal

24. 1300 kcal

25. 1200 kcal

26. 1250 kcal

27. 1700 kcal

28. 1900 kcal

29. 1150 kcal

30. 1000 kcal

31. 1350 kcal




Patient used to take around 2500 kcal daily before starting intervention. 


Here are some useful graphs. (The data is in reverse order in these graph 1, 2, & 4).







ChatGPT - One fascinating insight from this reverse order calorie counting data is the oscillation between higher and lower calorie days. By visualizing this data as a sine wave graph, with each day represented as a point along the curve, we see a rhythmic pattern emerge. The peaks and troughs represent days of higher and lower calorie intake respectively, creating a visually stunning wave pattern that illustrates the natural ebb and flow of dietary habits. This visualization highlights the balance between indulgence and restraint, offering a captivating depiction of the intricate dance of calorie consumption over time.




In simple words

- trend is useful to see it started Aggressive and plateau at around 1500 kcal
- seasonal indicate that after getting more strict patient is going back to less strict by variation of around -200 to +200 kcal range.

(Dates are incorrect in this graph).


This data also helps to predict calorie intake for next day it may have high inaccuracy. Regression analysis predicted next day calorie intake to be 1561 kcal.


Useful motivating / behavioural nudging messages are also possible which may also have good information to help reduce junk food intake by awareness. Like -

Day 1 - 600 calories intake: Equivalent to approximately 0.7 liters of petrol or 1.3 servings of chowmein.


Day 31 - Calorie deficit: 2500 - 1350 = 1150 calories

1) Equivalent to approximately 10,000 steps of brisk walking.

2) Equivalent to 45 minutes of high-intensity interval training (HIIT).



Requesting to share if any inputs/corrections in comment section below this blog post.

You may also like to check my precious work about fever charts here - https://classworkdecjan.blogspot.com/2021/02/some-tech-for-just-fever-sign.html

Wednesday 28 February 2024

A Session on Teaching critical appraisal for medicos and non-medicos

A Session on Teaching critical appraisal for medicos and non-medicos ( part 1)


(Part 2.0, 2.1, 2.2, and so on.. will be my blogs/links to student blogs having real patient with real problem having done critical appraisal. Feel free post link to your blog in comment section if you do this exercise.)


The key difference for medicos and non-medicos is just about the knowledge base.

A non medico person may know less than a non medico patient, A non medico patient may know less than a medico, a medico may know less than a specialist, and a specialist may know less than a medico patient (or a self taught & empowered patient citizen scientist)

So, as we begin learning *critical appraisal* so we can progress further to practice and develop skill in it to be good at *evidence based medicine*

My first question is, should there be learning of medicine without a patient at the center of the exercise?

No. I guess, everyone agrees.

So, let's start with the person at center. A person who may be sick and so came to us to provide us a learning opportunity.

We have a video about patient as a teacher, as all patients are our teachers giving us, the medico fraternity, lifelong learning opportunities. It's not important watch the video right now, but it have a glimpse of everything we are going to learn ahead.

https://youtu.be/xvE5b8Xk3vM?si=2GE-4ehkcO8Whmjo

A person is there with us now. We need to know their problems. Is that all?

No. We need to make them comfortable, be empathetic, respectful, make them feel supported, etc etc. Refer to AETCOM.

So, the first step for active learning - *taking patient history*

History is story of the patient.  It can be taken as taught in medical school to take in detail, or can be in narrative format which is easier for non-medicos and even medico newbies. A good history can be detailed, with a timeline, from reliable source/sources, etc. Refer to any clinical medicine book and you will find more in initial chapters. Patient problems can be detailed

- qualitatively (eg. shooting pain), 


- quantitatively (eg. 100 degree temperature),


- narrative way (eg. paining so badly since morning that unable to do household work).

Updating patient history with time is important, and you must note that a good patient history (data capture) is extremely useful and most important part of our efforts.

Step 2 is *clinical examination* (look, feel, touch, etc. Refer to any clinical medicine book to learn more)

You can also take pictures, record audio/video, etc.

With history and examination alone, most of diseases happening to mankind can be identified.

Next step is investigations as they help us conform our provisional diagnosis, and look more deeply into the human body to get clear picture of the problems.

All these cover 2 important concerns for our patient.

- *What is the problem* (listen)


- *Where is the problems* (examine)

Now, as we go to the next patient concern, we gets our hands dirty into EBM. But wait, was taking history and examination were not EBM? They were. The examinations have their sensitivity, specificity, protocols, etc. The history taking helps us understand patient priorities and lot more.

So the next concern is

- *what can be done about it*

Or the treatment plan, or the questions that we may get from our patient or ourselves when trying to create a robust treatment plan.

Before diving deep into it, let me first tell you about

- *SOAP notes*


- *PaJR*


- Identifying fake news.

*SOAP notes*.

SOAP means Subjective, Objective, Assessment and Plan.

It's a way of documentation and hence communication, for medical team providing care.

To simplify,

S means write in your narrative way about what is patient concern today/now.

O means write objective values like temperature readings, investigation outcomes, etc.

A means your observation/examination/assessment of the patient now.

P treatment plan.

So as a medico/non-medico/patient/caretaker you can also follow this template for recording daily data. Detailed and good data is important.

*PaJR* - patient journey record. The concept is applied in many way, but what I want to convey is, you can document the patient's journey as

daily patient update + picture of their food plates + sleep routine + exercise routine etc. Can add as many parameters as patient and you want but keeping it focused on clinically meaningful parameters relevant to patient may increase adherence to regularly updating data.

*Identifying fake news*

How can you do it? Fake news are so common that there is a term for it now called infodemic. I think you may be already doing it by

1) checking the news to know if it's not a clickbait

2)checking same news from multiple source.

3) checking news from authentic and more reliable source.

So, by doing any of these steps, you kept skepticism and didn't accept the information as it is, and also you critically analysed it to confirm it's authenticity. This is an example of critical appraisal of information. We are going to do same for medical evidence published in research papers. It's going to be exciting.


EBM is not just the information from best research.


When we look into research, these are types of clinical research studies. There are invitro and invivo studies at pre-clincial levels too. They can go at the bottom below the pyramid. The pyramid gives an idea about levels of clinical usefulness of type of study but it must not create an illusion that something at lower levels is useless in comparison to something at higher level, as every study type have it's pros and cons and so all have their importance and the raking gets blurred.


Even a type of research study can have sub types, having it's own pros and cons.

Eg. For clinical trials

Above 3 images gives basic idea for anyone to go ahead. It's advised to dive deeper as you learn by doing critical appraisal of evidence around clinical questions.

So, I will first share the easy way of critical appraisal and then I will also share the hard way.

Easy way is quick and gives important details. Hard way is time consuming and gives more understanding.

Here comes the easy way -

- identify the type of study (in research paper you are going to practice critical appraisal)


- download the critical appraisal tool for that type of study, from any of these websites and try it.

https://www.cebm.ox.ac.uk/resources/ebm-tools/critical-appraisal-tools

https://casp-uk.net/casp-tools-checklists/

(There are many, can search on internet "critical appraisal tools")

The easy way can get you started quickly, the hard way is to go through paper in detail, look for data and statistical analysis in detail, look for even the data about individual patients, look for possible biases and fundings, etc. It may be overkill sometimes.

Pro tip - various CDSS apps (clinical decision support system) are available that have pre-appriased evidence summaries to common clinical questions.

Ohh, are we missing something?

Yes..  The clinical question..or we are also missing the patient.. damn..that is what happen frequently in medical education where the key beneficiary goes out of the picture, that's so bad.. 

Let's stop here and I give you home work to

1) bring your patient to us by sharing the patient story and findings (or can also say it history and examination) in form of a blog where you have consent from the patient for doing it and whole of it is properly de-identfied.

2) share patient's/your clinical questions so we can start looking into evidence for it.

If you want an example case record, here it is - https://classworkdecjan.blogspot.com/2019/05/42-f-with-severe-regular-edema-with_17.html

Pro tip - there is a giant website where we can search most of medical research papers. https://pubmed.ncbi.nlm.nih.gov/ (Googling is not a bad idea though)

https://classworkdecjan.blogspot.com/2017/11/de-identifying-patient-data.html


Tuesday 5 September 2023

Archive of an intern's work for AI based evaluation.

Traces of his work during his internship (original post here - https://kandrucherishrollno68.blogspot.com/2023/09/traces-of-my-work-during-my-internship.html )
 
September 04, 2023
 
Case 1
 

 
 
 
 [31/08/23, 10:33:04 AM] intern1: soap notes 
 
 
 
31:8:23 
 
 
 
ICU Bed 3
 
 
 
Dr.resident1SR)
 
 
 
Dr.resident2(PGY2)
 
 
 
DR.resident3(PGY1)
 

 
 
S: No Fever Spikes
 
 
 
O: Pt is Sedated and Intubated
 
 
 
GCS- E1V1M1
 
 
 
PR-80bpm
 
 
 
RR-15cpm
 
 
 
BP-60/40 mmhg
 
 
 
@20ml/hr NORAD
 
 
 
@14ml/hr DOBU
 
 
 
ACMV Mode
 
 
 
FiO2 @70
 
 
 
SPO2 98%
 
 
 
RS: BLAE +
 
 
 
NVBS
 
 
 
CVS: S1S2 +, No murmurs
 
 
 
CNS: 
 
 
 
Tone :Normal B/L both UL&LL
 
 
 
Power : Unable to elicit
 
 
 
Reflexes: Absent B/L in both UL & LL
 
 
 
I/O 1900/200ml
 
 
 
GRBS 327mg/DK
 
 
 
 
 
 
 
A: 3 weeks old L5 burst Fracture & Unstable with PLC injury Planned for L4-L5 S1 Fixation with Heart Failure with Reduced Ejection Fraction (44%) with k/c/o DM since 20 years, k/c/o CAD (PTCA done) 2 years back
 
 
 
 
 
 
 
P: 
 
 
 
 1. INJ NORADRENALINE 4ml + 46ml NS @ 10 ml/ hr 
 
 
 
 2. INJ DOBUTAMINE 1AMP (5ml) + 45ml NS @ 10 ml /hr 
 
 
 
3. INS 3% NACL @ 50 ml/hr I.V /stat
 
 
 
4. INJ PIPTAZ 2.25 gm IV/TID 
 
 
 
5. TAB AZITHROMYCIN 500 mg RT/OD 
 
 
 
6. NEB WITH BUDECORT + IPRAVANT 6 Th hourly 
 
 
 
7. RT FEEDS 100 ml water 2 nd hourly
 
 
 
200 ml milk 4 Th hourly 
 
 
 
8. MONITOR VITALS TEMP; PR; RR ; spo2
 
 
 
9. POSITION CHANGE EVERY HOURLY
 
 
 
 10. INJ. Vasopressin 1ml + 39 ml NS @0.4 ml/hr
 
 
 
 11. INJ. Midazolam 30ml+ INJ Fentanyl 4ml + 16ml NS @4ml/hr
 
 
 
 12. INJ HAI ACC to GRBS
 
 
 
 
 
 
 
[31/08/23, 3:44:59 PM] Prof: Please share the post admission transfer events of yesterday in detail as to how and why the patient had to undergo CPR @intern2 @intern3
 
 
 
 
 
[31/08/23, 3:52:38 PM] Prof: Did he have any recent trauma @inter2 ?
 
 
 
 
 
 
 
That's not clear! In the description it's mentioned years and here it's mentioned weeks. Please clarify
 
 
 
 
 
[31/08/23, 6:04:12 PM] intern1: Yes Sir H/0 trauma (slip and fall from steps) 3 weeks back and also 
 
 
 
H/o Rt proximal femur fracture Intramedullary Interlocking nailing done 10 years back
 
 
 
 
 
[31/08/23, 6:28:04 PM] intern1: Sir the Patient t was shifted from Ortho ward at around 11:30 am in an altered state but the patient was responding when called by his name and obeying commands. At that time the Vitals were
 
 
 
PR-134bpm
 
 
 
BP-60/40mmhg
 
 
 
RR-10cpm
 
 
 
Then Patient was shifted to ICU immediately and ABG and S.Electrolytes were sent.Ionotropic support was started with INJ. DOBUTAMINE and INJ. NORAD. On reporting Sod was found to be 122mEq/L and diagnosis was Altered Sensorium secondary to hyponatraemia. Further Sodium correction was given. After giving correction of 3%Nacl, Sodium was found to be 124mEq/L and patient’s condition didn’t improve. Again Sodium Correction was kept with 3%Nacl @ 30ml/hr. On auscultation grunting was observed and saturations decreased to below 90% with O2 support and also Neb with Budecort and Ipravent was done. Inspite of all these efforts patient’s saturations didn’t improve and continuously decreased to around 78% to 80% and decision to intubate was taken. During intubation Patient went to cardiac arrest and 3 cycles of CPR was done, ROSC was achieved and patient was kept on ventilator ACMV VC mode with FiO2 100%.
 
 
 
 
 
[01/09/23, 9:37:14 AM] intern1: soap notes 
 
 
 
1:9:23
 
 
 
ICU Bed 3
 
 
 
Dr.resident1(SR)
 
 
 
DR.resident3(PGY2)
 
 
 
DR.resident5(PGY1)
 
 
 
 
 
 
 
S: No Fever Spikes
 
 
 
 
 
 
 
O: Pt is on Mechanical Ventilator 
 
 
 
GCS- E1V1M1
 
 
 
PR-130bpm
 
 
 
RR-14cpm
 
 
 
BP-100/60 mmhg
 
 
 
@10ml/hr NORAD
 
 
 
@10ml/hr DOBU
 
 
 
ACMV Mode
 
 
 
FiO2 @30
 
 
 
SPO2 99%
 
 
 
RS: BLAE +
 
 
 
Decreased BS in IAA with crepts present in Lt IMA; Rt MA, IMA, IAA
 
 
 
CVS: S1S2 +, No murmurs
 
 
 
CNS: 
 
 
 
Tone :Normal B/L both UL&LL
 
 
 
Power : Unable to elicit
 
 
 
Reflexes: Absent B/L in both UL & LL
 
 
 
Brain stem reflexes:
 
 
 
Pupillary reflex- absent
 
 
 
Corneal reflex- absent
 
 
 
Conjunctival reflex- absent
 
 
 
Gag reflex- Present
 
 
 
Occulocephalic reflex- Present
 
 
 
P/A- Soft, NT
 
 
 
I/O 1900/200ml
 
 
 
GRBS 327mg/DK
 
 
 
 
 
 
 
A: 3 weeks old L5 burst Fracture & Unstable with PLC injury Planned for L4-L5 S1 Fixation with Heart Failure with Reduced Ejection Fraction (44%) with k/c/o DM since 20 years, k/c/o CAD (PTCA done LAD Lcx Territory) 2 years ago
 
 
 
S/P Post CPR status with chronic calcific Pancreatitis 
 
 
 
 
 
 
 
P: 
 
 
 
1. INJ NORADRENALINE 4ml + 46ml NS @ 10 ml/ hr 
 
 
 
2. INJ DOBUTAMINE 1AMP (5ml) in 45ml NS @ 10 ml /hr 
 
 
 
3. INJ. Vasopressin 1ml + 39 ml NS @0.4 ml/hr
 
 
 
4. INJ. Midazolam 30ml+ INJ Fentanyl 4ml + 16ml NS @4ml/hr
 
 
 
5.TAB AZITHROMYCIN 500 mg RT/OD 
 
 
 
6.NEB WITH BUDECORT + IPRAVANT 6 Th hourly 
 
 
 
7.INJ THIAMINE 1 Amp In 100 ml NS IV/BD
 
 
 
8.RT FEEDS 200 ml water 2 nd hourly
 
 
 
200 ml milk 4 Th hourly 
 
 
 
9.MONITOR VITALS TEMP; PR; RR ; spo2
 
 
 
10.POSITION CHANGE EVERY HOURLY
 
 
 
11.INJ HAI ACC to GRBS
 
 
 
12.INJ.MEROPENEM 500mg IV/BD
 
 
 
13.INJ HEPARIN 500 IU S.c/ QID
 
 
 
15.INJ LEVIPIL 1gm IV/BD
 
 
 
 
 
[01/09/23, 9:45:27 AM] Prof: 👆The EF is much more than 44% in this video taken yesterday @919676979003 where it appears to be 60% and the only other prominent finding is the LVH that appears absent in his Ecg (but that just reflects the 30% sensitivity of Ecg to pick up LVH) 
 
 
 
 
 
 
 
Possible that he may have developed cardiogenic shock pre arrest which is when the 44% Echo was done? Can you share that video if possible?
 
 
 
 
 
[01/09/23, 9:46:13 AM] intern1: Yes sir 
 
 
 
 
 
[01/09/23, 10:06:09 AM] intern1: Sir the video wasn’t taken sir I’ll try to find the report
 
 
 
 
 
[01/09/23, 10:07:07 AM] intern1: Update @9am Sir
 
 
 
Temp is 101
 
 
 
 
 
 
 
[02/09/23, 4:10:15 PM] Prof: Please share all the events that happened around him from falling 3 weeks back to presenting at our hospital
 
 
 
 
 
[03/09/23, 10:04:28 AM] intern1: Sir the patient fell from staircase 1 month back. Then he had severe pain of lower back radiating to his lower limbs. So he was taken to a nearby hospital in Nalgonda where X-rays and they were told that no fracture was found, he was also taken to another hospital and the same happened again. Then CT scan was done wherein they found the L5 unstable burst fracture with PLC injury and a belt was given to contain the fracture along with some analgesics for the pain. As the patient wasn’t compliant to the treatment given and the pain was severe he was brought to our hospital and he was advised L4 L5 S1 posterior stabilisation.
 
 
 
[03/09/23, 10:16:36 AM] intern1: Sir the whole 3 weeks span of him coming to our hospital he was having good appetite, he was compliant with his OHAs, he had no other complaints except for his pain
 
 
 
[03/09/23, 10:17:02 AM] intern1: Should I ask the attenders anything in particular sir?
 
 
 
[03/09/23, 10:21:40 AM] Prof: Ask them what was he doing hourly in the past three weeks and was it any different from before he fell down
 
 
 
[03/09/23, 10:22:25 AM] intern1: After coming to our hospital he had three episodes of vomiting, non bilious, non foul smelling ,food particles as content. The morning before he was shifted to ICU
 
 
 
[03/09/23, 10:47:00 AM] intern1: He used to just lie down on bed the entire day sir and there were no irregularities observed by the attenders sir
 
 
 
[03/09/23, 11:20:49 AM] Prof: Was he bedridden before the fall three weeks ago?
 
 
 
[03/09/23, 11:23:15 AM] intern1: No sir
 
 
 
[03/09/23, 11:24:07 AM] intern1: He wasn’t bedridden, he used to do his daily activities sir
 
 
 
[03/09/23, 11:44:02 AM] Prof: What were his hourly daily activities?
 
 
 
[03/09/23, 12:01:43 PM] intern1: Sir He used to wake up at 6 Am
 
Does his daily activities by 7:30 Am
 
Breakfast around 9:00 Am
 
Has lunch by 1:00 Pm
 
And then takes a nap
 
Evening he chats with neighbours and has his dinner around 8:30pm 
 
And sleeps by 9:30 pm
 
 
 
[03/09/23, 12:35:43 PM] Prof: These were same even after the fall since last three weeks?
 
 
 
[03/09/23, 6:46:36 PM] intern1: Yea sir but he used to not do his daily activities and he used to just lie down on bed the whole day
 
 
 
[03/09/23, 7:49:34 PM] Prof: That means he was bed ridden after the fall
 
 
 
Case 2: 
 
 
 
 
 
[31/08/23, 7:00:29 AM] Prof: 58 is a strange pulse rate for a person in pain @919676979003 ?
 
 
 
[31/08/23, 7:00:59 AM] Prof: Clinical images, blood sugars, CBC?
 
 
 
 
 
[31/08/23, 7:48:09 AM] intern1: Sir will update the fever chart and all the investigations now sir
 
 
 
[31/08/23, 7:50:08 AM] Prof: A standing image of lateral abdomen and biceps
 
 
 
[31/08/23, 7:51:05 AM] intern1: Yes sir
 
 
 
[31/08/23, 7:52:39 AM] intern1: Yes sir for someone in pain ,they are generally tachy
 
 
 
[31/08/23, 7:53:06 AM] intern1: Even the ECG showed Brady sir
 
 
 
[31/08/23, 7:53:35 AM] intern1: I’ll upload everything by 9 sir
 
 
 
 
 
[31/08/23, 9:34:50 AM] intern1: GRBS
 
12 pm - 200
 
8pm-208
 
 
 
10pm-125 
 
31/8
 
2AM-220
 
7AM-220
 
 
 
 
 
[31/08/23, 12:25:58 PM] intern1: 31/08/2023 
 
Ward : ward
 
Unit : 2
 
DOA : 30/08/2023  
 
 
 
S : 
 
C/o abdominal pain decreased
 
(Dull aching in lower abdomen)
 
Nausea+
 
Stools not passed
 
Flatus passes +
 
 
 
O:  
 
Patient is conscious, coherent
 
No Pallor, icterus,clubbing, cyanosis, lymphadenopathy, oedema.
 
 
 
Vitals :   
 
Temp Afebrile
 
BP- 130/90mmHg 
 
PR -86bpm 
 
RR-16 cpm 
 
CNS: NFND
 
CVS: S1,S2 heard , no murmurs.
 
RS: BAE, NVBS, no added sounds.
 
P/A: Rigid,NT
 
Pain in lower abdomen
 
Bowel sound 3/min
 
Sluggish
 
 
 
 
 
A: Acute Pancreatitis with alcoholic ketosis with k/c/o DM ll since 6 months with indirect hyperbilirubinemia
 
 
 
P:
 
IV fluids @75 ml/hr 
 
Inj. Neomol 1Amp in 500 ml NS/IV/BD
 
Inj pantop 40 mg IV/OD/BBF
 
Inj Zofer 4 mg IV/BD
 
 
 
 
 
[31/08/23, 5:03:45 PM] Prof: Is he really having lumbar lordosis or the image has been taken in that manner to match his suspected type 2 diabetes? Or is it type 3?
 
 
 
[01/09/23, 12:25:40 PM] intern1: Image has been taken like that sir
 
 
 
 
 
 
 
Case 3

 
[23/08/23, 2:28:52 PM] Prof: Update her FBS,PPBS And HBA1C @intern2 @intern3
 
 
 
 
 
[23/08/23, 2:47:50 PM] Prof: What is the difference between ionized and serum and how are both done separately?
 
 
 
[23/08/23, 2:51:09 PM] intern1: Sir S.Calcium is the total calcium in the blood whereas Ionised calcium is the active form of calcium or the free calcium
 
 
 
 
 
[25/08/23, 11:24:44 AM] intern1: soap notes 
 
25:8:23 
 
Female medical ward-8
 
Dr.resident6(SR)
 
Dr.resident2(PGY2)
 
DR.resident5(PGY1)
 
 
 
S:
 
Neck pain decreased compared to yesterday.
 
Headache decreased compared.
 
1 Episode of Vomiting- Yesterday night
 
No Fever spikes
 
Stools passed
 
O: 
 
pt is C/C/C 
 
No signs of pallor, Icterus, clubbing, cyanosis,lymphedenopathy, pedal edema 
 
BP: 120/80mmhg
 
PR: 78bpm 
 
RR: 18cpm
 
Temp: 96.2 F
 
Cvs: S1,S2 heard, No murmurs 
 
RS:BAE+
 
P/A: distended and non tender 
 
CNS: No FND 
 
Neck Examination 
 
Restriction of movements decreased
 
Able to flex and extend
 
Neck stiffness -
 
kernig’s sign -
 
Brudzinki sign -
 
A: 
 
NECK PAIN-CERVICAL RADICULOPATHY (C5-C6) with Paraspinal Spasm
 
K/C/O HTN SINCE 4 YEARS WITH PERIPHERAL VERTIGO secondary to Vertebro basilar insufficiency 
 
WITH DENOVO THYROID DISEASE (HYPOTHYRODISM) WITH Left CERVICAL LYMPHEDENOPATHY WITH DENOVO DMII
 
 
 
P: 
 
1.INJ. Diclofenac Im/sos
 
2.T.Dolo 650 mg po/sos
 
3.T. Nicardia 10 mg po/sos
 
4.T. Losartan+T. Hydrochlorothiazide 50mg/ 12.5 mg 
 
5.T. vertin 8 mg po/bd 
 
6.T. Thyronorm 75 mcg po/od 
 
7.T. Metformin 500 mg po/be
 
8.T. Cinod 10 mg po/od
 
9.T. Myoril 2ml IM/BD
 
10.INJ. Zofer 4mg IV/SOS
 
11.INJ.PAN 40mg/IV/OD
 
12.T.PREGABA 75MG/PO/HS
 
 
 
[25/08/23, 2:57:10 PM] Prof: Peripheral vertigo everyday since 4 years!!?
 
 
 
[25/08/23, 2:57:51 PM] Prof: You have updated just one patient today? 
 
 
 
You have only work responsibility for just one patient throughout the day?
 
 
 
[25/08/23, 3:03:43 PM] intern1: Sir as there are only 2 interns in each Unit we’ve been called to help The interns in OP sir.
 
 
 
[25/08/23, 3:10:49 PM] intern1: Vertigo only since the past 10 days Sir
 
 
 
[25/08/23, 4:38:18 PM] Prof: If there is two interns and one patient in the ward it's logical to have one intern go and help in opd
 
 
 
[25/08/23, 4:38:58 PM] intern1: Yes Sir we are helping Unit 5 on their OP days
 
 
 
[25/08/23, 4:40:31 PM] Prof: Not we. Only one of the two interns who doesn't have a patient in the ward
 
 
 
[25/08/23, 4:41:07 PM] intern1: Yes Sir
 
 
 
[28/08/23, 9:03:06 AM] intern1: soap notes 
 
28:8:23 
 
Female medical ward-8
 
Dr.resident4(SR)
 
Dr.resident2(PGY2)
 
DR.resident5(PGY1)
 
 
 
S:
 
Neck pain decreased .
 
No Episodes of Vomiting since yesterday and Na
 
No Fever
 
sleep adequate 
 
Stools not passed
 
O: 
 
pt is C/C/C 
 
No signs of pallor, Icterus, clubbing, cyanosis,lymphedenopathy, pedal edema 
 
BP: 120/80mmhg
 
PR: 82bpm 
 
RR: 16cpm
 
Temp: Afebrile 
 
Cvs: S1,S2 heard, No murmurs 
 
RS:BAE+
 
P/A: soft and non tender 
 
CNS: No FND 
 
Neck Examination 
 
Restriction of movements decreased
 
Neck stiffness -
 
kernig’s sign -
 
Brudzinki sign -
 
Finger finger incoordination absent
 
Finger nose incoordination absent
 
Spine tenderness absent
 
Nystagmus absent
 
EOM movements absent
 
Diplopia absent
 
No Increased ICT features
 
Cervical LN palpable in Lt occipital triangle 
 
No palpable axillary LN
 
A: 
 
NECK PAIN-CERVICAL RADICULOPATHY (C5-C6) with Paraspinal Spasm
 
K/C/O HTN SINCE 4 YEARS WITH PERIPHERAL VERTIGO secondary to Vertebro basilar insufficiency 
 
WITH DENOVO THYROID DISEASE (HYPOTHYRODISM) WITH Left CERVICAL LYMPHEDENOPATHY WITH DENOVO DMII with Migraine
 
 
 
P: 
 
1.INJ. Diclofenac Im/sos
 
2.T.Dolo 650 mg po/sos
 
3.T. Nicardia 10 mg po/sos
 
4.T. Losartan+T. Hydrochlorothiazide 50mg/ 12.5 mg 
 
5.T. vertin 8 mg po/bd 
 
6.T. Thyronorm 75 mcg po/od 
 
7.T. Metformin 500 mg po/be
 
8.T. Myoril 2ml IM/BD
 
9.INJ. Zofer 4mg IV/SOS
 
10.INJ.PAN 40mg/PO/OD
 
11.T.PREGABA 75MG/PO/HS
 
12.T.Clonazepam 0.25mg PO/HS
 
 
 
 
 

 

Monday 4 September 2023

Using bard with prompt for qualitative evaluation of cbble/udhc/pajr/case records analysis

Prompt:- 

A medical student is given task to create case records for patients and analyse it, research it and find ways to improve care process while collaborating with the healthcare staff. Analyse the case record data given by student below and give me  insight on how many levels of bloom's taxonomy the student have covered and how many he have missed so i can grade him for his effort.

Also find if student have done critical appraisal of any research articles and show me all the article links.

Also show me if student have presented critical appraisal in pico format.

_____________________


https://bard.google.com/share/a36ade450575  this is output of prompt for qualitative evaluation of cbble/udhc/pajr records analysing separately,  all 3 case records presented here http://classworkdecjan.blogspot.com/2023/09/archive-of-interns-work-for-ai-based.html?m=1

This can also be a method for self analysis for students to improve their case records as well as for evaluators/educators, and there is scope for further automation to grade quantitatively based on qualitative analytical by bard.

There are no hallucinations noted by me.

*Limitation* of LLM/bard based portfolio grading - a student can find a hack by playing at each level once to score highest rather than playing for the patient benefits and prioritise and let scores be byproduct of it.

Solution - case mentor eg. As we have @⁨Dr. Rakesh Biswas sir, or interns may be having PGs and sir being aware of it and so keeping students directed towards patient priorities.

Analytics by bard can be automated and even real time by Integrating bard in an app/excel sheets.

___________


Thursday 10 August 2023

Dpdp for UDHC/PaJR

 [10/08, 11:38 am] Dr. Avinash Kumar Gupta: Project idea - Dpdp bill impact on UDHC/PaJR model. (If anyone wanna try) 


+ve/-ve/recommendations.

[10/08, 11:40 am] Dr. Rakesh Biswas sir: Will mention it today in the SWOT time permitting 


What do you feel? 


Would the bill be a threat to what we are doing?

[10/08, 11:41 am] Dr. Avinash Kumar Gupta: Thanks sir!


Not a barrier but an enabler I feel. (Based on my prior exposure with hipaa in context of UDHC)

[10/08, 11:42 am] Dr. Rakesh Biswas sir: Enabler in what way? Share in the context of the bill

[10/08, 11:42 am] Dr. Avinash Kumar Gupta: Sure sir, I am yet to open it's pdf and read. I will try today and update in a few hours.

[10/08, 11:44 am] Dr. Rakesh Biswas sir: Will be looking forward to your quotes from this

[10/08, 11:44 am] Dr. Avinash Kumar Gupta: Sure sir

[10/08, 12:29 pm] Dr. Avinash Kumar Gupta: Page 3



(t) “personal data” means any data about an individual who is identifiable by or

in relation to such data;

(u) “personal data breach” means any unauthorised processing of personal

data or accidental disclosure, acquisition, sharing, use, alteration, destruction or loss

of access to personal data, that compromises the confidentiality, integrity or availability

of personal data;

[10/08, 12:35 pm] Dr. Avinash Kumar Gupta: *CHAPTER II*

OBLIGATIONS OF DATA FIDUCIARY

4. Grounds for processing personal data.

5. Notice.

6. Consent.

7. Certain legitimate uses.

8. General obligations of Data Fiduciary.

9. Processing of personal data of children.

10. Additional obligations of Significant Data Fiduciary.

*CHAPTER III*

RIGHTS AND DUTIES OF DATA PRINCIPAL*)

11. Right to access information about personal data.

12. Right to correction and erasure of personal data.

13. Right of grievance redressal.

14. Right to nominate.

15. Duties of Data Principal.

[10/08, 12:41 pm] Dr. Avinash Kumar Gupta: Page 9 ( _we don't have good mechanism for this but its doable_ )


(1) The Data Principal shall have the right to obtain......

....(a) a summary of personal data which is being processed by such Data Fiduciary

and the processing activities undertaken by that Data Fiduciary with respect to such

personal data;

(b) the identities of all other Data Fiduciaries and Data Processors with whom

the personal data has been shared by such Data Fiduciary, along with a description of

the personal data so shared; and

(c) any other information related to the personal data of such Data Principal and

its processing, as may be prescribed.

[10/08, 12:45 pm] Dr. Avinash Kumar Gupta: _With PaJR approach (whatsapp) we don't have deletion mechanism_ but it's not needed as we already remove personal data (I.e. identifiers)



(3) A Data Principal shall make a request in such manner as may be prescribed to the

Data Fiduciary for erasure of her personal data, and upon receipt of such a request, the Data

Fiduciary shall erase her personal data unless retention of the same is necessary for the

specified purpose or for compliance with any law for the time being in force.

[10/08, 12:54 pm] Dr. Avinash Kumar Gupta: _Enabler point_


“Data Fiduciary” means any person who alone or in conjunction with other

persons determines the purpose and means of processing of personal data;

[10/08, 12:56 pm] Dr. Avinash Kumar Gupta: _Enabler point_


(g) “Consent Manager” means a person *registered with the Board*, who acts as

a single point of contact to enable a Data Principal to give, manage, review and

withdraw her consent through an accessible, transparent and interoperable platform

[10/08, 1:02 pm] Dr. Avinash Kumar Gupta: _Enabler point_ (we already mention about open sourcing data in consent and more importantly its already deidentified so no "personal data")



4. (1) A person may process the personal data of a Data Principal only in accordance

with the provisions of this Act and for a lawful purpose,—

(a) for which the Data Principal has given her consent; or

(b) for certain legitimate uses.

[10/08, 1:11 pm] Dr. Avinash Kumar Gupta: *Summary*


This bill clearly defines 1) personal data, 2) data fiduciary, 3) consent manager. 



We do not share or process personal data explained in the bill as we already remove it by deidentification.


I need to understand more about consent manager, we already have consent management in place though there is always scope for improvement.



This bill doesn't clearly list what is a personal data and what is not as in hipaa but it's understandable based on the definition. Our deidentification process is robust for that.



This bill doesn't talks about deidentified data and also about its open sharing, but if we are deidenfying responsibly then we are correct with our process.



So overall we don't need to make any changes in the process to be compliant to it (except probably *board registered consent manager person* )

[10/08, 1:15 pm] Dr. Avinash Kumar Gupta: Yes. In that case all rights of data principle will be applicable and must be done. 


But you may recall, we don't add the patient but a patient advocate/care manager who knows the patient. This way the patient is deidentified.

[10/08, 1:53 pm] Dr. Avinash Kumar Gupta: If the bill had a line that open sharing of data after removing "personal data" is allowed with consent then it could be 100% fit for us. 


People dealing with hipaa and gdpr do share open access data 


*Recommendations and conclusion*

We have several recommendations for sharing sensitive healthcare data within the EU (Fig. 4). First, it is important to have a multidisciplinary team of experts with in-house knowledge to tackle legal, ethical, economic, and technical issues. Second, external parties can be involved in assessing the privacy and data protection risks to acquire unbiased risk assessments. Third, the risk of re-identification (for both anonymised and pseudonymised data) should be adequately accounted for. The de-identification methodology we recommend is K-anonymisation, as performed by AmsterdamUMCdb. Fourth, patient consent is not always required by the GDPR, as indicated in Fig. 1. Fifth, adherence to transparency when publishing open data and trust between patients and other stakeholders is crucial when sharing health data30,31. This includes the legal obligation for the hosting institution to inform patients through its privacy statement that their data can be shared and reused for investigation purposes. Sixth, the commitment of the hosting institution is required for a successful publication process. The institution should be willing to back up the project when unforeseen obstacles present themselves (i.e., costs and/or effort). Ultimately, data should be stored and analysed in the cloud, if possible, so the data cannot be downloaded. If infeasible, strict governance should be implemented. To guide future initiatives in sharing open healthcare data, we included a Gantt chart in the supplementary information14 as a planning guideline. In conclusion, publishing open health data in the EU might be challenging, but it is essential for developing modern-day healthcare. The experiences and lessons learned from these four successful databases can guide the development of new open European ICU databases.



Reference to above paragraph.  It's not from dpdp bill. It's from "A guide to sharing open healthcare data under the General Data Protection Regulation" https://www.nature.com/articles/s41597-023-02256-2

[10/08, 2:00 pm] Dr. Avinash Kumar Gupta: Ref - https://www.nature.com/articles/s41597-023-02256-2

[10/08, 2:01 pm] Dr. Avinash Kumar Gupta: Reference to above paragraph.  It's not from dpdp bill. It's from "A guide to sharing open healthcare data under the General Data Protection Regulation"