The hottest Diagnostics Substack posts right now

Sequencing B and T cell receptors can help diagnose autoimmune diseases. This kind of testing is much faster and could lead to more accurate diagnoses.
Using machine learning and AI makes analyzing the complex data from these receptors easier. The technology can find patterns and help doctors understand patients' conditions better.
In the future, a full immunome could be a standard test to check how well someone's immune system is working. This could help prevent diseases before they become serious.

A.I. is often outperforming doctors in diagnosing medical conditions, even when doctors use A.I. as a tool. This means A.I. can sometimes make better decisions without human involvement.
Doctors might not always trust A.I. and often stick to their own judgment even if A.I. gives correct information, leading to less accurate diagnoses.
Instead of having doctors and A.I. work on every case together, we should find specific tasks for each. A.I. can handle simple cases, allowing doctors to focus on more complex problems where their experience is vital.

Many doctors are not keen on genetic tests because they believe the tests do not change how patients are treated. This attitude makes it hard for patients to get the tests they need.
It's not just about the cost of testing; the main issue is that doctors often don't like running tests if they feel there's no direct benefit to patients.
To improve the situation, we need to raise awareness among doctors and patients about the benefits of whole genome sequencing, especially for those with rare diseases. Grassroots efforts can help push for more understanding and acceptance of these tests.

Genopore is an Israeli company focused on a new way to detect proteins. They are more interested in detection methods rather than just fingerprinting or sequencing proteins.
The technology they are developing is considered novel, suggesting it could bring new advancements to protein detection.
Their patents and website indicate they have a clear direction towards enhancing protein detection capabilities.

Neurotech commercial market segments are challenging to define accurately due to numerous reports and estimates about various topics like BCI, neuromodulation, productivity tech, diagnostics, imaging, monitoring, and AI.
Important commercial market segments in neurotech include consumer wearables, clinical diagnostics & monitoring, clinical treatment & intervention, life sciences, and research & manufacturing.
Market research in neurotech often focuses on technology rather than who is actually paying for and using the tech to help people, leading to a need for critical thinking about the real market landscape.

Get a weekly roundup of the best Substack posts, by hacker news affinity:

Funding for surveillance is lacking, so focusing on diagnostics may not be practical.
Existing methods can detect new pathogens, reducing the need for meta-genomic sequencing.
Challenges exist in making meta-genomic sequencing platforms affordable and appealing compared to traditional methods.

Sequencers should be as boring and simple as qPCR machines for easy use and accessibility.
Automation in sequencing should focus on sample-to-answer approaches like the GeneXpert in diagnostics.
Broader adoption of sequencing in clinical applications may require a cultural shift towards valuing diagnosis even without immediate treatment options.

Japan has been integrating AI into healthcare since about 15 years ago. This started as a move to tackle issues related to an aging population.
The government is now focused on using AI to create 'AI hospitals' and improve patient care. This includes tools for diagnostics and automating tasks to help healthcare workers.
A big breakthrough is using AI to detect pancreatic cancer early. Early detection is crucial since this type of cancer is usually diagnosed too late when it's harder to treat.

Sensitivity and specificity are important for medical tests, but they don’t tell the whole story. While sensitivity checks for illness, specificity avoids falsely alarming healthy people, but we also need to consider how trustworthy those positive results are.
Positive Predictive Value (PPV) is crucial because it determines how many positive test results are actually true. Even tests that seem great on paper can lead to many false alarms if the condition is rare in the tested population.
New standards are needed for screening tests, especially since broad screening is becoming more common. Tests should not just catch many cases, but also provide real accuracy, avoiding unnecessary stress and procedures for patients.