Lets use AI to help people manage illness

2026-01-19 · Source: Ehud Reiter's Blog · Field: Technology & Digital — Artificial Intelligence & Machine Learning, Medical Devices & Health Technology, Clinical Care & Medical Practice · Depth: Intermediate, medium

Summary

The article advocates for novel AI applications in healthcare, particularly those focused on patient-managed illness, rather than replicating existing wellness apps. While 230 million people weekly use ChatGPT for health and wellness, and new offerings like ChatGPT Health focus on fitness, diet, and mental health, the author argues these may not significantly impact health outcomes. Instead, the focus should shift to areas like monitoring disease status, supporting treatment compliance, and providing personalized information. The ASICA project, for instance, uses computer vision and LLM chatbots to help melanoma patients take high-quality images for clinical review and provide contextual information, aiming to improve data quality rather than direct diagnosis. Another example involves using AI to improve medical device adherence through sensor data, camera input, and LLM-supported questionnaires. The Babytalk-Family project also demonstrated the value of personalized electronic patient record summaries for parents of NICU babies, reducing stress and improving quality of life.

Key takeaway

For healthcare innovators and app developers considering AI, prioritize novel applications that directly support illness management and improve patient outcomes. Focus your efforts on areas like disease monitoring, treatment adherence, or personalized patient information, as these offer greater potential for impact than replicating existing fitness or mental health apps. Your solutions should address data quality and provide tailored support to truly make a difference in patients' quality of life.

Key insights

AI's true impact in healthcare lies in novel applications for illness management, not just replicating existing wellness tools.

Principles

• Focus on new use cases for significant impact.
• Address data quality in patient-acquired data.
• Personalized information reduces patient stress.

Method

A general concept for AI in disease management involves acquiring individual data (sensors, cameras, questionnaires), addressing data quality issues, and analyzing data for disease insights.

In practice

• Use computer vision for image quality checks.
• Employ LLMs for contextual information and advice.
• Combine sensor data with patient questionnaires.

Topics

• AI in Healthcare
• Disease Management
• Patient Monitoring
• Treatment Adherence
• LLM Chatbots

Best for: Computer Vision Engineer, AI Product Manager, AI Engineer, Domain Expert

Related on AIssential

• Health-care AI is here. We don’t know if it actually helps patients. — Despite rapid AI adoption in healthcare, its impact on patient outcomes is largely unmeasured.
• Good News & Bad News: AI is better than most therapy for some people. You need to understand some nuance, but its genuinely extraordinarily valuable. — AI provides uniquely personalized, accessible, and nuanced mental health support, often surpassing traditional therapy for specific needs.
• Personalizing healthcare with AI — AI integration in healthcare aims to personalize experiences, empowering users for better outcomes.
• Humanising Healthcare - AI and Innovation at Optum — Human-centered innovation and responsible AI are crucial for transforming healthcare and improving patient outcomes.
• F Cancer — AI's impact on cancer is limited by technosolutionism, market failures, and insufficient biological understanding.
• How people use Copilot for Health — Conversational AI serves diverse health needs, from personal symptom checks to caregiving and system navigation, with usage patterns varying by device and time.

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by Ehud Reiter's Blog.