Empirical comparison of routinely collected electronic health record data for head and neck cancer‐specific survival in machine‐learnt prognostic models

• Published in: Head & neck 2023-02, Vol.45 (2), p.365-379
• Main Authors: Kotevski, Damian P., Smee, Robert I., Vajdic, Claire M., Field, Matthew
• Format: Article
• Language: English
• Subjects: Adult; cancer‐specific survival; Carcinoma, Squamous Cell - therapy; Datasets; Electronic Health Records; Electronic medical records; Head & neck cancer; head and neck cancer; Head and neck carcinoma; Head and Neck Neoplasms - therapy; Humans; Hypothyroidism; Larynx; Learning algorithms; Machine learning; Medical prognosis; Original; Oropharynx; Prediction models; Prognosis; prognostic factors; Squamous cell carcinoma; Tumors
• ISSN: 1043-3074; 1097-0347
• DOI: 10.1002/hed.27241

Background Knowledge of the prognostic factors and performance of machine learning predictive models for 2‐year cancer‐specific survival (CSS) is limited in the head and neck cancer (HNC) population. Methods Data from our facilities' oncology information system (OIS) collected for routine practice (OIS dataset, n = 430 patients) and research purposes (research dataset, n = 529 patients) were extracted on adults diagnosed between 2000 and 2017 with squamous cell carcinoma of the head and neck. Results Machine learning demonstrated excellent performance (area under the curve, AUC) in the whole cohort (AUC = 0.97, research dataset), larynx cohort (AUC = 0.98, both datasets), and oropharynx cohort (AUC = 0.99, both datasets). Tumor site and T classification were identified as predictors of 2‐year CSS in both datasets. Hypothyroidism and fitness for operation were further identified in the research dataset. Conclusions Datasets extracted from an OIS for routine clinical practice and research purposes demonstrated high utility for informing 2‐year head and neck CSS.