ByBach Bui
Build a better online collaborative whiteboard system
3 years ago
6
Create newCreate new
Challenge
salemandreus May 24, 2021
Improving on medical care through global connectivity
Image credit: Photo available from https://wallpaperaccess.com/medicine-desktop.
Please leave the feedback on this challenge
Necessity
Is the problem still unsolved?
Conciseness
Is it concisely described?
Bounty for the best solution
Provide a bounty for the best solution
Bounties attract serious brainpower to the challenge.
One benefit of having so much access to data at our fingertips is easier access to specialised information shared by experts and researchers.
This has been especially evident with researchers and countries combining their efforts at solving the Covid19 pandemic.
What are the possibilities of medical knowledge-sharing and online connectivity to aid in improved medical care?
4
Creative contributions
Digitization of historical medical practices from local tradition
With increased global connectivity culture and access comes not only easier sharing of new knowledge and research but the immortalisation and distribution of historical human medical research and refined practises in local tradition which were historically ignored due to not having an existing counterpart yet discovered in western medical history.
The digitisation movements to preserve languages and cultures in danger of extinction further facilitate this capturing of information by cultures that have had little opportunity to pass on that knowledge before it is lost.
Please leave the feedback on this idea
Instant expert-facilitated in-consultation and diagnosis with your GP
Many medical conditions benefit from international research to gain specialised knowledge. I met a surgeon who travelled to a different continent to study gunshot wounds, as gun violence being less prevalent in her country meant fewer specialists had experience treating those wounds. Similarly, the USA has a high instance of obesity, leading to more research into conditions such as heart disease and Type II Diabetes.
Regions experiencing occupational hazards, climate-based health conditions, and genetic predispositions of native cultures towards certain illnesses also often facilitates specialised research becoming more attached to specific regions.
Rather than people having to choose between visiting a GP and the perils of online self-diagnosis weighed against the benefit of multiple medical perspectives and the potential pitfalls of navigating which information is valuable and how to interpret it as a layperson, we could have a “best of both worlds” scenario where visiting a GP could simultaneously get you access to a live session with other experts weighing in.
Picture this: You are concerned about a mole you think may be malignant. You visit a GP who examines you and then decides to consult a specialist. Rather than you having to make an appointment in advance, and hoping that the one local specialist in your area is available so you don’t have to drive far and take another day off work, your GP is already connected to an online subscription service where several international specialists are available for remote consultation. The GP can then ask the relevant dermatologist specialised in skin cancers the relevant questions right then and there. The dermatologist can then confirm observations from the GP about their in-person physical examination and instruct them on further tests that they can run on their side and can also speak to you directly.
In this way you receive the expertise of global specialists but your process is guided by your GP who can examine you in person a knows your medical history and how to communicate effectively with the specialists and what questions are relevant to ask to ensure you’re diagnosed correctly, doing the in-person examination and signing off on the vitals - similarly to how you can go to a lab and get the results sent to your doctor.
Please leave the feedback on this idea
Specialised bio scanning hardware using globally connected training data for image classification
In one of his videos, Dr Mike explains that when diagnosing patients, GPs are on the lookout for two main types of illness:
1) Those which are most common or likely given the symptoms (eg flu is common during the flu season) and
2) Conditions that present high risk to the patient if undiagnosed early even if symptoms are minimal.
For example, many of the symptoms of ovarian cancer are commonly in other, less severe medical problems however the risk of people with ovaries developing it during their lifetime is high, as is the risk of death from it therefore care must be taken to not dismiss symptoms particularly if the patient is over 40/post menopause and thus at higher risk.
Specialised hardware for scanning could help identify cancers without the need to go to a doctor or hospital each time.
A scanner would harnesses supervised image classification (machine learning), through an international public repository of images of benign and malignant tumours/moles/swelling of organs etc as training data for identifying certain cancers. Ideally, as this global repository of training data more training data would make it easier to identify cancers in the early stages, possibly before they would even be detectable to the doctor or patient.
Potentially, people would not even have to make an appointment to go to a doctor or specialist to get a mole checked out - portable scanners could be more easily made available, either for purchase particularly by high-risk individuals or those with a past history or genetic predisposition towards cancers, or available for the general public to use at facilities such as gyms, or non-profit organisations running testing drives to raise awareness, or other institutions seeking to promote health, such as medical aid companies in particular - since oncological treatment is one of the most financially devastating medical costs for patients and thus medical aids often place limits on how much they will cover for that reason and would be strongly incentivised to detect cancers early.
Please leave the feedback on this idea
Preventing future pandemics through spotting undeveloped research early: AI/ML identifying the highest risk and most critical studies needing future research
One of the greatest tragedies of the pandemic was the fact that existing research into a vaccine had already been in the pipeline years ago, but had been discontinued due to lack of interest.
The data was available but finding funding for a grant was difficult for the researchers. Having a way to raise these insights globally and calculate the actuality of these risks especially drawing apon data from past pandemics may have motivated significant change if more people were aware of the severity of the risks and the value of the research being done.
Having easy access to all the medical trials and studies performed for a relevant drug or researching a particular condition make it easier for the medical and scientific research world, and the journalistic world, to identify overlooked factors for study (eg the long-term effects of a certain illness or medication), or identify where results are yet to be conclusive (no peer review, small sample size).
Through devising computationally efficient means, potentially utilising AI, potentially with machine learning these factors could be brought to light far more easily and earlier - vulnerabilities that have not yet been properly investigated research grants could be put forth timeously and we can hopefully be able to better prepared for the next pandemic and other health risks.
Studies could also potentially be weighted or rated by expert reviewers (researchers with credentials), which could also propose ratings (in the form of a vote) for other researchers, similarly to youtube survey ads, on the shared medical network.
These could identify where data is being overly duplicated instead of being expanded on (eg if repeat studies still test the same demographics or do not have a large enough sample size and results vary widely).
Some constraints may include accessing licensed proprietary information from journals that may not be not widely available to all researchers or to the relevant medical professionals or other parties.