Programs

Twelve research projects

Search by project number, name or data source. Open a record to read its question, target, data, results and limits.

12 / 12 projects

5-1Computational

Structure-Based AI Small-Molecule Discovery

Link public protein structures and small-molecule activity records to assess how well computational scores transfer to unseen molecules.

Internal research targetBinding free-energy error of 1 kcal/mol or less

Synthetic checks matchedEvaluation data partly established

8-1Computational

Early Boost for Core Health R&D Technology

Measure how much statistical structure and predictive information synthetic multiomics and clinical data retain.

Internal research targetAt least 95% of downstream predictive performance retained

Synthetic checks matchedEvaluation data ready

18-2Computational

Medication Administration and Dispensing Safety

Evaluate pill identification and prescription checks independently, then verify the evidence behind each error flag.

Internal research targetZero missed contraindications or look-alike medication errors

Synthetic checks matchedEvaluation data partly established

19-1Computational

Rare Disease Diagnostic Research

Combine public variant evidence with a phenotype ontology and evaluate the ranks and supporting evidence for candidate genes.

Internal research targetAt least 90% of causal genes in the top five

Synthetic checks matchedPublished-case evaluation recorded

16-2Cohort and simulation

Non-Pharmacological Dementia Research

Evaluate how adaptive cognitive training changes difficulty in a simulated cohort.

Internal research targetDifficulty convergence in at least 95% of simulated episodes

Synthetic checks matchedEvaluation data partly established

16-3Cohort and simulation

Multimodal Dementia Diagnostic Research

Study whether imaging and speech features retain their predictive value across hospitals and equipment.

Internal research targetExternal cohort AUROC of at least 0.90

Synthetic checks matchedEvaluation data partly established

18-1Cohort and simulation

Fall Prediction and Prevention

Replay acceleration and gait records to measure warning lead time and distinguish falls from everyday movement.

Internal research targetAt least 92% early-warning sensitivity in the high-risk group

Synthetic checks matchedEvaluation data partly established

18-3Cohort and simulation

Surgical Environment Error Prevention

Replay instrument labels and surgical phases to evaluate instrument state tracking and alert conditions.

Internal research targetZero instrument count omissions on the fixed test

Synthetic checks matchedEvaluation data partly established

12-1Cohort and simulation

Suicide Prevention Research for People with Mental Illness

Evaluate event timing and references to supporting evidence in synthetic longitudinal records.

Internal research targetAt least 90% recall for acute crisis signals

Synthetic checks matchedEvaluation data partly established

12-2Cohort and simulation

Suicide Prevention Research for Bereaved People and Attempt Survivors

Use synthetic replay to check the flow of a safety plan and transitions to designated responses.

Internal research targetZero clinically disallowed response events on the fixed test

Synthetic checks matchedEvaluation data partly established

12-3Cohort and simulation

Social Isolation and Suicide Prevention Research

Assess whether changes in everyday routines can serve as indicators of sustained isolation.

Internal research targetAt least 85% precision for detecting transitions into sustained isolation

Synthetic checks matchedEvaluation data partly established

12-4Cohort and simulation

Student Suicide Prevention Research

Test whether a designated screen opens promptly following a marked crisis state in synthetic counselling records.

Internal research target100% immediate handoff after a detected crisis state

Synthetic checks matchedEvaluation data partly established