endocrine · condition_status

Hypothyroidism Status

Valid comparisons for this clinically grounded task are grouped by fixed information set.

Per-track results

Benchmark Tracks

hypothyroidism_status/0bd9bda402a1

Scored split: test. Primary metric: roc_auc (higher is better).

#	Predictor	Method	Absolute test AUROC	Test n
1	HPP Curated Panel	TabDPT Classifier	0.6872	1542
2	HPP Curated Panel	Logistic Delta Auc	0.6793	1542
3	HPP Curated Panel	TabPFN 3.5 Classifier	0.6789	1542
4	HPP Curated Panel	TabICL Classifier	0.6779	1542
5	HPP Curated Panel	TabFM Classifier	0.6765	1542
6	HPP Curated Panel	RealMLP Classifier	0.6749	1542
7	HPP Curated Panel	TabSwift Classifier	0.6643	1542
8	HPP Curated Panel	TabPFN v2 Classifier	0.6567	1542
9	HPP Curated Panel	GBDT Delta Auc	0.6469	1542

hypothyroidism_status/5a0e79c56e15

Scored split: test. Primary metric: roc_auc (higher is better).

#	Predictor	Method	Absolute test AUROC	Test n
1	HPP Curated Panel	TabPFN v2 Classifier	0.676	1351
2	HPP Curated Panel	TabICL Classifier	0.6698	1351
3	HPP Curated Panel	TabSwift Classifier	0.6698	1351
4	HPP Curated Panel	TabPFN 3.5 Classifier	0.6685	1351
5	HPP Curated Panel	TabFM Classifier	0.6665	1351
6	HPP Curated Panel	Logistic Delta Auc	0.6641	1351
7	HPP Curated Panel	TabDPT Classifier	0.663	1351
8	HPP Curated Panel	RealMLP Classifier	0.6414	1351
9	HPP Curated Panel	GBDT Delta Auc	0.6217	1351