AI, clinical trial design, patient stratification
0-100 chain-logic scale · 15 dimensions · scored on public evidence
Investigate concepts related to disrupting the aging process.
Publication-level research program; specific intervention or assay is not described in the supplied material.
2019 publication titled "Disrupting the Aging Process."
Uncover heterogeneity in Alzheimer's disease progression using machine intelligence.
Machine intelligence analysis of Alzheimer's disease progression data.
2020 publication titled "Using machine intelligence to uncover Alzheimer’s disease progression heterogeneity."
Identify novel gene targets in bipolar disorder from postmortem microarray data.
Comparison of traditional data analysis and artificial intelligence applied to postmortem microarray datasets.
2021 publication in ScienceDirect on bipolar disorder microarray data identifying novel gene targets.
The supplied title states that AI analysis revealed novel gene targets, but no detailed results are provided.
Optimize clinical trial design and late-stage decision-making by identifying hidden patient correlations, treatment efficacy, toxicity, placebo response, and causal variables of patient response; support enrichment, inclusion/exclusion criteria design, disease heterogeneity analysis, and smaller Phase III studies.
Explainable AI platform using proprietary long-range attractor algorithms, dynamical-systems modeling, evolutionary feature selection, and LLM-generated insights applied to clinical trial and patient datasets.
NetraMark lists NetraAI as its core platform and 2025 publications describe its use for precision clinical trial enrichment and meta-evolutionary AI for clinical trials.
The supplied material says NetraAI is intended to uncover clinically actionable patient subgroups and optimize clinical development workflows.
Demonstrate whether NetraAI can identify high-effect-size patient subpopulations and improve treatment-response prediction in a Phase II ketamine trial for treatment-resistant depression.
Retrospective AI analysis of a Phase II ketamine trial dataset with 63 patients, psychiatric scale data, and MRI-derived features; NetraAI generated patient Personas and predictive feature models.
2025 publication titled "Explainable AI-driven precision clinical trial enrichment: demonstration of the NetraAI platform with a phase II depression trial."
Reported approximately 25-30% improvement in predictive accuracy over traditional ML, a 10-clinical-variable model with AUC improved by 0.32, and an 8-MRI-feature model with 95% accuracy and 100% specificity.
Identify genetic drivers and classify non-small cell lung cancer patient subtypes from small datasets.
Machine learning and quantum/classical machine learning approaches applied to non-small cell lung cancer patient data.
2023 publication on small patient datasets revealing genetic drivers of NSCLC subtypes; related 2020 publication on quantum and classical machine learning classification of NSCLC patients.
Use AI-based methods to address placebo response in clinical trials and improve trial design or interpretation.
AI-based analysis methods for placebo response, disease definition, and patient stratification.
2022 publication titled "Using Artificial Intelligence-based Methods to Address the Placebo Response in Clinical Trials."
Use machine learning hypothesis generation to stratify patients and discover potential therapeutic protein targets in ALS and rare disease datasets.
Machine learning analysis of small patient datasets in an Open Science setting for patient stratification and target discovery.
2024 publication titled "Machine learning hypothesis-generation for patient stratification and target discovery in rare disease: our experience with Open Science in ALS."
The supplied abstract excerpt states the work aimed to show that small patient datasets can provide insights and potential therapeutic protein targets usually requiring larger datasets.