AI resources related to research or healthcare

Jenny TipsforME · Apr 18, 2023

I’m getting quite obsessed with the AI Revolution stuff and thought it could be worth starting a thread to share resources which could be applied to ME in some way. I know some of the ME researchers do keep up with the forum. It might be that some others on the forum have skills to use existing research data and analyse it differently with the advent of open source AI tools?

The first is https://owkin.com/substra/

Substra is a ready-to-use, open source federated learning (FL) software developed by Owkin, now hosted by the Linux Foundation for AI and Data. Substra enables the training and validation of machine learning models on distributed datasets. It includes a flexible Python interface and a web application to run federated learning training at scale. Academic research centers and Biopharma companies deploy Substra (formerly Owkin Connect) in a wide variety of federated learning settings for clinical research, drug discovery and development.
Click to expand...

Jenny TipsforME · Apr 20, 2023

https://glass.health/ai/

Welcome to Glass.
We've built the first digital notebook designed for the way doctors think, learn and practice.

Glass AI 2.0 combines a large language model (LLM) with a clinical knowledge database, created and maintained by clinicians, to create DDx and Clinical Plan outputs.

Glass has a Community Library of medical knowledge content.

This product is not intended for use by members of the general public for medical diagnoses or other purposes. Glass is available for use by clinicians, including physicians, pharmacists, nurse practitioners, physician assistants, and clinicians-in-training.
Click to expand...

I’m not a medic so I didn’t go further.

Jenny TipsforME · Apr 20, 2023

https://consensus.app/search/

Ask questions of research papers and also get a synthesise summary

But PACE stretches its evaluation limits:

Jenny TipsforME · Apr 21, 2023

A similar tool is elicit.org

SNT Gatchaman · Jul 8, 2023

Possibly of relevance to research around POTS —

Artificial intelligence-based model to classify cardiac functions from chest radiographs: a multi-institutional, retrospective model development and validation study (2023, The Lancet Digital Health)

Background
Chest radiography is a common and widely available examination. Although cardiovascular structures— such as cardiac shadows and vessels—are visible on chest radiographs, the ability of these radiographs to estimate cardiac function and valvular disease is poorly understood. Using datasets from multiple institutions, we aimed to develop and validate a deep-learning model to simultaneously detect valvular disease and cardiac functions from chest radiographs.
Click to expand...

Findings
We included 22 551 radiographs associated with 22 551 echocardiograms obtained from 16 946 patients. The external test dataset featured 3311 radiographs from 2617 patients with a mean age of 72 years [SD 15], of whom 49·8% were male and 50·2% were female. The AUCs, accuracy, sensitivity, and specificity for this dataset were 0·92 (95% CI 0·90–0·95), 86% (85–87), 82% (75–87), and 86% (85–88) for classifying the left ventricular ejection fraction at a 40% cutoff, 0·85 (0·83–0·87), 75% (73–76), 83% (80–87), and 73% (71–75) for classifying the tricuspid regurgitant velocity at a 2·8 m/s cutoff, 0·89 (0·86–0·92), 85% (84–86), 82% (76–87), and 85% (84–86) for classifying mitral regurgitation at the none-mild versus moderate-severe cutoff, 0·83 (0·78–0·88), 73% (71–74), 79% (69–87), and 72% (71–74) for classifying aortic stenosis, 0·83 (0·79–0·87), 68% (67–70), 88% (81–92), and 67% (66–69) for classifying aortic regurgitation, 0·86 (0·67–1·00), 90% (89–91), 83% (36–100), and 90% (89–91) for classifying mitral stenosis, 0·92 (0·89–0·94), 83% (82–85), 87% (83–91), and 83% (82–84) for classifying tricuspid regurgitation, 0·86 (0·82–0·90), 69% (68–71), 91% (84–95), and 68% (67–70) for classifying pulmonary regurgitation, and 0·85 (0·81–0·89), 86% (85–88), 73% (65–81), and 87% (86–88) for classifying inferior vena cava dilation.
Click to expand...

Interpretation
The deep learning-based model can accurately classify cardiac functions and valvular heart diseases using information from digital chest radiographs. This model can classify values typically obtained from echocardiography in a fraction of the time, with low system requirements and the potential to be continuously available in areas where echocardiography specialists are scarce or absent.
Click to expand...

Log in or Sign up

AI resources related to research or healthcare

Jenny TipsforME Senior Member (Voting Rights)

Jenny TipsforME Senior Member (Voting Rights)

Jenny TipsforME Senior Member (Voting Rights)

Jenny TipsforME Senior Member (Voting Rights)

SNT Gatchaman Senior Member (Voting Rights)

Share This Page

Log in or Sign up

AI resources related to research or healthcare

Jenny TipsforME Senior Member (Voting Rights)

Jenny TipsforME Senior Member (Voting Rights)

Jenny TipsforME Senior Member (Voting Rights)

Jenny TipsforME Senior Member (Voting Rights)

SNT Gatchaman Senior Member (Voting Rights)

Share This Page

Useful Searches