AI Science Tracker
EN

Department of Population Health Science and Policy, Icahn School of Medicine at Mount Sinai

2 discoveries from 2020 to 2021

Discoveries

Estimating heterogeneous survival treatment effects of lung cancer screening approaches: A causal machine learning analysis.

Source check: Source checked. Not independent scientific confirmation.

Finding: In 53,454 participants, the paper reported no statistically significant overall lung-cancer or overall-mortality benefit, while describing exploratory subgroup patterns. The subgroup patterns are exploratory retrospective causal-inference estimates, not confirmed treatment effects or prospective screening benefit.

Technology: AFT-BART estimated censored survival counterfactuals from National Lung Screening Trial data, and a tree summarized heterogeneous subgroup treatment-effect estimates.

Publication: Peer-reviewed paper · Test context: retrospective or benchmark. Catalog categories, not an evidence grade.

AI contribution
AFT-BART estimated censored survival counterfactuals from National Lung Screening Trial data, and a tree summarized heterogeneous subgroup treatment-effect estimates.
Test and result
In 53,454 participants, the paper reported no statistically significant overall lung-cancer or overall-mortality benefit, while describing exploratory subgroup patterns.
Limitation / still unknown
The subgroup patterns are exploratory retrospective causal-inference estimates, not confirmed treatment effects or prospective screening benefit.
Evidence sources and annotation context

Evidence context (descriptions follow the cited sources; test type is a catalog classification):

Evidence sources: https://pmc.ncbi.nlm.nih.gov/articles/PMC8463451/

Source checked · editorial details

The source page was checked against this entry. Independent confirmation is not assessed by this label.

Source type: paper. Paper: linked separately.

Review date: 22 Nov 2026. Review scope: Primary result-bearing material for the stated method, result and evaluation, with bibliographic version information..

No follow-up recorded; this is not a claim that no follow-up exists. Follow-up review scope and date are not recorded. No source-supported relationships recorded.

Editorial assessment: Impact 2/5 · Validation 2/5 · Novelty 2/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.

Identifying and understanding determinants of high healthcare costs for breast cancer: a quantile regression machine learning approach.

Source check: Source checked. Not independent scientific confirmation.

Finding: In 2,938 episodes from 2012–2018, chemotherapy drug and interval were prominent high-cost correlates; quantile analysis attributed 77% of reduced out-of-bag quantile loss to chemotherapy variables. Retrospective associations do not establish that changing a treatment or cost driver will causally reduce healthcare expenditures.

Technology: Quantile regression forests ranked variables associated with high-tail breast-cancer care expenditures in Oncology Care Model episodes.

Publication: Peer-reviewed paper · Test context: retrospective or benchmark. Catalog categories, not an evidence grade.

AI contribution
Quantile regression forests ranked variables associated with high-tail breast-cancer care expenditures in Oncology Care Model episodes.
Test and result
In 2,938 episodes from 2012–2018, chemotherapy drug and interval were prominent high-cost correlates; quantile analysis attributed 77% of reduced out-of-bag quantile loss to chemotherapy variables.
Limitation / still unknown
Retrospective associations do not establish that changing a treatment or cost driver will causally reduce healthcare expenditures.
Evidence sources and annotation context

Evidence context (descriptions follow the cited sources; test type is a catalog classification):

Evidence sources: https://link.springer.com/article/10.1186/s12913-020-05936-6

Source checked · editorial details

The source page was checked against this entry. Independent confirmation is not assessed by this label.

Source type: paper. Paper: linked separately.

Review date: 22 Nov 2026. Review scope: Primary result-bearing material for the stated method, result and evaluation, with bibliographic version information..

No follow-up recorded; this is not a claim that no follow-up exists. Follow-up review scope and date are not recorded. No source-supported relationships recorded.

Editorial assessment: Impact 2/5 · Validation 2/5 · Novelty 2/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.

Open the interactive profile for the timeline, or browse all organizations and model families.