In the News stat
“Four types of bias in medical AI are running under the radar of the FDA and CHAI”Dr. Enes Hosgor

A CRO platform for clinical-grade AI

Train. Validate. Secure clearance.

The problem we are facing  

Medical AI adoption is lagging due to a lack of

compliant, scalable, and ML-friendly data access

About gesund.ai

Gesund.ai orchestrates the AI as-a-Medical Device lifecycle, providing privacy-centered access to diverse yet standardized medical data sources, and a unique analytical toolbox that fosters clinical validation, regulatory clearance and effective marketing

How it works

Standardized, unified and diversified data customized for your ML needs and regulatory requirements
Gesund assesses model validation needs and provides a suitable mix of high-quality data from its multiple and diverse clinical partner sites

1.

Model owner shares clinical study with Gesund for curation of appropriate dataset(s), and uploads their model onto Gesunds federated validation platform, which resides on hospital premise or private cloud.

2.

Model runs against a previously unseen validation data set that has been curated on the hospital side.

3.

Model accuracy metrics are produced and displayed on the Gesund platform for further examination with respect to patient characteristics, scenario analyses and stress testing.

4.

The model insights are exported into a report for the model owner to supplement their regulatory submission.

Request early access

Are you an academic researcher in medical AI?
Bring your own data or model and join the Gesund community. For free

No-hassle model exploration
and validation running models against
real-world data in a secure environment

No more dependency
on software engineers to
containerize or deploy models

Share models
and insights out of the
box with collaborators

Preview
Preview

Gesund’s CRO platform provides
end-to-end services for machine-learning algorithm development and validation

Dataset matching
according to case-specific
regulatory demands

Annotation
as-a-service

Assessment of demographic
characteristics for explanatory
purposes

Post-market validation
and evaluation

Update model via
re-training with prospective
studies against standard of care

Identify gaps
in algorithms

To tap proprietary data sources and reader expertise through our platform

Compliance

hipaadrata

Latest News

December 20th 2022

Merck Invests in Gesund, Launches Medical AI Platform on AWS

December 20th 2022

Gesund’s Platform for Immediately Generating Insights Into the Equity, Safety and Effectiveness of Medical AI Receives Acceptance to Merck Digital Sciences Studio

November 26th 2022

Evidence in Days, Not Years: Gesund Partners With ScanDiags to Supercharge the Process of Validating Radiology AI

Publications

Papers

An automated approach for machine learning model performance analysis on sub cohorts to assess for biases

Authors: Brian Ayers MD MBA, Ray Funahashi MD, Veysel Kocaman PhD, Enes Hosgor PhD

presented at
pdf_summary

1. Research Questions

Can an automated approach help identify clinically significant biases within machine learning prognostic models?

2. Findings

Of the 1,343 total patients included in the study, 179 (13%) patients died. The final model accuracy on the validation cohort overall was 80% (minority class F1 score=0.39, AUC=0.663). However, using our automated tool there were numerous clinically significant differences identified in model accuracy on different patient subsets. For example, the model was much more accurate for patients requiring the intensive care unit (86% accuracy) but was much worse for other sub cohorts such as current smokers (60% accuracy) and male patients (78% accuracy). Moreover, there were many sub cohorts with insufficient patient data to perform sufficient analysis.

3. Conclusions

These data demonstrate the high risk for model performance discrepancies on subset of patients with different characteristics. Using a standardized, automated approach for systematic model validation is instrumental in minimizing model biases before implementing a machine learning model in a clinical setting.

Backed by

merck
mckesson
northpond
500

Advisory Board

The HonorableDavid J. Shulkin, M.D.
Bryan Sivak
Prof. Paul Chang, M.D.
Vance Moore

Team

Enes Hosgor, Ph.D.
CEO & Founder
Veysel Kocaman
VP of Engineering
Marco Smit
VP of Business Development
Ray Funahashi, M.D.
Head of Clinical Affairs
Brian Ayers, M.D., MBA
Clinical Scientist
Peter Bucciarelli, M.D.
Clinical Scientist
Yashwanth Soundararaj
Regulatory Affairs Manager
Akson Sam
ML Engineer
Mehmet Burak Sayici
ML Engineer
Hammad Khalid
Jr. ML Engineer
Deniz Dugru
Jr. Python Developer
Resul Turan
Full-Stack Developer
Isa Sumer
Front-End Developer
Furkan Turkoglu
Front-End Developer
Necip Tahir Ozgan
Front-End Developer

Careers

DevOps Engineer/ Backend Engineer (Remote)

We are building a privacy-first MLOps platform for data-driven organizations in healthcare and life sciences. The platform is designed to support the entire lifecycle of machine learning (ML) efforts to accelerate breakthrough medical research and bring clinical-grade ML solutions to market. Our fast-expanding strategic network includes early clinical and technology partners and organizations in the US and Europe.

Machine Learning (Remote)

We are building a privacy-first MLOps platform for data-driven organizations in healthcare and life sciences. The platform is designed to support the entire lifecycle of machine learning (ML) efforts to accelerate breakthrough medical research and bring clinical-grade ML solutions to market. Our fast-expanding strategic network includes early clinical and technology partners and organizations in the US, Israel and Europe.

Frontend Developer (Remote)

Gesund.ai is building a privacy-first MLOps platform for data-driven organizations in healthcare and life sciences. The platform is designed to support the entire lifecycle of machine learning (ML) efforts to accelerate breakthrough medical research and bring clinical-grade ML solutions to market. Our fast-expanding strategic network includes early clinical and technology partners and organizations in the US, Israel and Europe.

Let's Connect

United States: 47 Thorndike St, Cambridge, MA 02141
Germany: Martin Opitz Str. 23, Berlin 13357
Germany: Martin Opitz Str. 23, Berlin 13357
© All rights reserved to gesund.ai
Gesund Platform