Pulse Brain · Growing Health Evidence Index
Tier 3 — Observational / field trialPeer-reviewed

Machine learning-based histological classification that predicts recurrence of peripheral lung squamous cell carcinoma

Yutaro Koike, Keiju Aokage, Kosuke Ikeda, Tokiko Nakai, Kenta Tane, Tomohiro Miyoshi, Masato Sugano, Motohiro Kojima, Satoshi Fujii, Takeshi Kuwata, Atsushi Ochiai, Toshiyuki Tanaka, Kenji Suzuki, Masahiro Tsuboi, Genichiro Ishii

Lung Cancer · 2020

Read source ↗ All evidence

Summary

This 2020 study describes the development of a machine learning classifier applied to histological image data from patients with peripheral lung squamous cell carcinoma to predict recurrence risk. The approach represents an application of computational pathology to prognostic stratification in thoracic oncology. The work does not directly address farming systems, soil health, nutrient density, or food-system outcomes and appears to have been catalogued in error; it belongs in oncology or medical informatics literature rather than a food systems research database.

UK applicability

The methodological approach (computational histopathology for cancer risk stratification) may be relevant to UK clinical pathology practice and NHS diagnostic algorithms, but the findings are specific to a Japanese patient cohort with peripheral squamous cell carcinoma and do not inform UK agricultural or nutritional policy.

Key measures

Recurrence-free survival, histological image features extracted by machine learning, performance metrics (sensitivity, specificity, area under receiver operating characteristic curve)

Outcomes reported

The study developed and validated a machine learning classifier trained on histological image features to predict recurrence risk in patients with peripheral lung squamous cell carcinoma. The model's performance in stratifying patients by recurrence probability was evaluated against conventional clinicopathological variables.

Theme
Nutrition & health
Subject
Other / interdisciplinary
Study type
Research
Study design
Observational cohort with retrospective model development and validation
Source type
Peer-reviewed study
Status
Published
Geography
Japan
System type
Human clinical
DOI
10.1016/j.lungcan.2020.07.011
Catalogue ID
SNmoi8o5ip-jw92qx

Topic tags

Pulse AI · ask about this record

Dig deeper with Pulse AI.

Pulse AI has read the whole catalogue. Ask about this record, its theme, or how the findings apply to UK farming and policy — every answer cites the underlying studies.