Cohort overviewiHigh-level stability summary for the full uploaded cohort across all patient-condition pairs and runs.
PatientsiNumber of unique patients loaded from the uploaded JSON dataset.
0
Items (patient × ICD-10)iCount of unique patient-condition pairs summarized across runs.
0
RunsiMaximum run count detected in the uploaded cohort.
—
MEAT threshold disagreementiCount of patient-condition items with at least one run at or above the MEAT threshold and at least one run below it.
0
Any runs ≥ 0.92 and any < 0.92
Presence threshold disagreementiCount of patient-condition items with at least one run at or above the presence threshold and at least one run below it.
0
Any runs ≥ 0.92 and any < 0.92
MEAT vote agreementiAgreement rate across all run-level MEAT threshold votes in the cohort.
0%
Disagree votes: 0 · low-consistency items: 0
Presence vote agreementiAgreement rate across all run-level presence threshold votes in the cohort.
0%
Disagree votes: 0 · low-consistency items: 0
MEAT swing (Med+High)iCount of items whose MEAT score range across runs is medium or high severity.
0
Med: 0 · High: 0 · Max: 0.000
Presence swing (Med+High)iCount of items whose presence score range across runs is medium or high severity.
0
Med: 0 · High: 0 · Max: 0.000
Scoring validation (optional)iMatched-row comparison between the dashboard’s thresholded predictions and the uploaded scoring reference.
Upload a scoring CSV/TSV to compare surfaced rows against labeled truth values for presence and MEAT.
Scoring file not loaded
Upload a reference scoring file to populate precision, sensitivity, false discovery rate, accuracy, and confusion counts for both Presence and MEAT.
Most troubling patient-condition pairsiTop-ranked patient-condition items ordered by disagreement, low consistency, swing severity, and opportunity-type instability.
Ranked by disagreement, low consistency, and swing.
Top 12
PatientiPatient label and internal patient ID for the ranked condition row.ICD-10iDiagnosis code associated with the ranked patient-condition pair.OppiConsensus or mixed opportunity type assigned to the condition across runs.MEAT rangeiDifference between the highest and lowest max MEAT score across runs.MEAT consistencyiAgreement strength of the thresholded MEAT vote across runs.Presence rangeiDifference between the highest and lowest clinical presence score across runs.Presence consistencyiAgreement strength of the thresholded presence vote across runs.
Upload a JSON dataset to populate.
Swing distributioniDistribution of score ranges across runs for each patient-condition pair. Higher buckets indicate more instability.
Range across runs per patient × ICD-10. Y-axis shows count.
001110–.020.02–.040.04–.060.06–.080.08–.100>.100Count
Buckets: 0–.02, .02–.04, .04–.06, .06–.08, .08–.10, >.10