Sleep Study - Obstructive Sleep Apnea

 Low cost screening, diagnostic, monitoring device based on low-cost Spo2 sensor.

fever chart

 

We have been using such fever charts and manually analyzing for better care.

This chart if for covid case made by patient's relative.

Hypertension data vsiaulization

 

full details - https://youtu.be/xvE5b8Xk3vM

Some tech for just the Fever sign

Having a deep interest in medicine and computing, I found fever charts to be an amazing starting point to explore. Including the amazing strategy of how the doctors can use fever charts interpretation to predict the possible cause of sickness, also the easy opportunity to collect data or crowdsource and then simple challenge to analyse for the patterns with respect to time. 

1) Learnt about the fever charts and use during my BMJ Electives. (My learning portfolio here- https://classworkdecjan.blogspot.com/ )

2) Using google sheets to quickly digitize fever charts, also let other students and patients copy and utilize it to make charts digitally by themself. https://classworkdecjan.blogspot.com/2017/08/using-fever-chart.html

3) Using vision API to explore its application on fever charts. https://classworkdecjan.blogspot.com/2020/03/fever-charts-part-1-extracting-data.html

4) Collecting resources to utilize when sharing and discussing the idea. https://classworkdecjan.blogspot.com/2020/03/resources-for-fever-project.html

5) Discovering the question, "How we know normal body temperature is 37°C" and reading research and even found a small very old dataset and this interesting book which I am yet to read - "On the Temperature in Diseases: A Manual of Medical Thermometry". The 37 °C value was set by German physician Carl Reinhold August Wunderlich in his 1868 book,[34] which put temperature charts into widespread clinical use.[35] https://en.wikipedia.org/wiki/Human_body_temperature 

6) Trying to understand what analytics to apply for predicting the possible pattern correlating with disease/diseases.. Time series analysis? Clustering? Here I faced the roadblocks.. I understand the ML concepts but implementing them programmatically on a new challenge is something I haven't tried yet.. Discussed with some interested folks but the idea never took off as a digital health research project. Still hopeful and trying. 

7) During my last visit to same electives, I met with his another elective student Mr. Neelankit, who was doing his M. Tech and started researching on IoT device for fever charts and we had our elective days together. Later he came up with a device prototype and progressing with it ahead. There are many devices in the market for this purpose but we need something cheap and usable in the hospital setting in the rural area.

7) Found this today - http://feverprints.com/ , It's inspiring to see this happening in real and excited to see the clinical useful outcomes in future. This is a publication from the project "Using Smartphone Crowdsourcing to Redefine Normal and Febrile Temperatures in Adults: Results from the Feverprints Study" https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6258625/

We had been doing tasks like digitizing fever charts, helping patients learn making it, utilize the data to improve clinical accuracy for diagnosis and antibiotic use etc. with a few students, the IoT device maker and prof. Rakesh Biswas always helped us with data access and clinical reasoning but for large scale data we needed more resources.

8) Chat gpt for fever charts https://youtube.com/shorts/Ya_IE23uSyI?si=wV0dHgytVeSlX4T4

which next sign you would suggest to explore? and why?

Don't be a Social Murderer

Public health has grown and uplifted the quality of life everywhere in the world! The war against covid with everything in the swiss cheese model, from masks to vaccines are the wonders which are saving uncountable lives including us and our families. Having a central focus of doing the best possible for humanity as a collective good, it always ignores the individual's good to some extent and one brutal example of that was the quarantine strategy as an early step against the pandemic when it began. Being an archaic idea also called draconian measure against protection from diseases with high negative effects. It was impactful and still impactful now (all geographies for covid and any upcoming pandemic) but we also saw equally dangerous exaggerated negative effects too.

But 

a key point to note "the conditions created by privileged classes inevitably led to premature and “unnatural” death among the poorest classes." 

Ref- Covid-19: Social murder, they wrote—elected, unaccountable, and unrepentant. -Kamran Abbasi, executive editor https://www.bmj.com/content/372/bmj.n314

In this pandemic, I myself along with nearly all in the data science as well as public health and medical communities and labs were finding Quarantine to be a promising strategy (and it is to a great extent https://www.pslhub.org/learn/coronavirus-covid19/tips/the-swiss-cheese-respiratory-virus-pandemic-defence-r3379/ ) but the terrible adverse effects got exaggerated too and I saw many migrant workers walking even barefoot, hungry, since days, from 1000+ kilometres, with kids and sick elderly, and whatnot, and even after all the struggle had to face quarantine outside home town, or blocked entry due to stigma, etc. It's impossible to imagine the extent of sufferings.

Other than my real experience which is common for everyone worldwide, and cluelessness on what could have been a good enough strategy to prevent the disaster. Clueless even when I tried and still trying to follow some of the ocean of evidence ranging from minimalists to maximalists. The cluelessness of Uncertainty.

Calculation below is based on heavy approximation from non-precise non-latest data for my own understanding.

Annually deaths are 7 per thousand, and if we take approximate 2 million died in a year due to covid then death due to covid is 2.6 per 10 thousand which is around 3.7% of total deaths per annum which is around lowest among top 10 killers. Top 10 killers is a deadly number and that is just the mortality from the direct impact of covid as disease and not the indirect effects like missed treatment, missed essential services, lost jobs and stresses etc. and the morbidity of severe and mild covid sickness. Also, a worrying aspect of covid is the high-risk (age and comorbidities) group where most of the mortality is concentrated. 

Suggestion - 

1) Do not fear, do not help spread infodemic. Learn, educate, and practise basic safety measures, care plan (isolation, quarantine, home care, telecare, etc). Help, guide and promote all for following safety measures. Follow all this even when you are vaccinated. Follow all this to save INDIVIDUAL  LIVES.

2) Covid-19 is not ending anytime soon and can even take years, also vaccines are useful but they are not magic bullets. https://www.nature.com/articles/d41586-020-02278-5 

3) Its stressful year for all and there is no end to troubles yet, be nice and reduce covid stigma.

4) For all in power, "Don't be a social murderer."

PS- Public health ignores individual good to some extent based on the probabilities of risks and the catch is, the uncertainty of an individual lying into population saved group or individuals harmed group which we never know until its too late. Public health is good, follow it.

Question- What could have been good enough effort/strategy to be not considered a social murderer for those in power?

Looking forward to your answers in comments.

(I do not intend to justify the lack of good enough efforts, I specifically wish to discuss scientifically that when we are 1+ year into the pandemic, what do we know/learnt about strategising in way that could have been better and also may be good enough)