Predicting activities of daily living for cancer patients using an ontology-guided machine learning methodology

• Published in: Journal of biomedical semantics Vol. 8; no. 1; pp. 39 - 8
• Main Authors: Min, Hua, Mobahi, Hedyeh, Irvin, Katherine, Avramovic, Sanja, Wojtusiak, Janusz
• Format: Journal Article
• Language: English
• Published: London BioMed Central 16.09.2017; BioMed Central Ltd; Springer Nature B.V; BMC
• Subjects: Activities of Daily Living; Aged; Aged, 80 and over; Algorithms; Analysis; Artificial Intelligence; Big Data; Bio-ontologies; Bioinformatics; Biological Ontologies; Biomedical data; BioOntologies SIG; Cancer; Cancer patients; Cohort Studies; Combinatorial Libraries; Computational Biology/Bioinformatics; Computer Appl. in Life Sciences; Computer Science; Data analysis; Data Mining; Data Mining and Knowledge Discovery; Data processing; Diagnosis; Disabilities; Female; Health aspects; Histology; Humans; Information systems; International conferences; Knowledge discovery; Knowledge management; Knowledge representation; Language; Learning algorithms; Logic programming; Machine Learning; Male; Mathematical models; Mathematics; Mathematics and Statistics; Methods; Middle Aged; Minority & ethnic groups; Natural language processing; Neoplasms; Ontology; Patients; Pattern recognition; Performance prediction; Prostate cancer; Quality of life; Retrospective Studies; SEER-MHOS; Semantic web; Semantics; Smoking; Statistics; Activities of daily living; Bio-ontologies; Machine learning; SEER-MHOS; Quality of life; Machine learning Bio-ontologies Quality of life Activities of daily living SEER-MHOS
• ISSN: 2041-1480; 2041-1480
• DOI: 10.1186/s13326-017-0149-6

Background Bio-ontologies are becoming increasingly important in knowledge representation and in the machine learning (ML) fields. This paper presents a ML approach that incorporates bio-ontologies and its application to the SEER-MHOS dataset to discover patterns of patient characteristics that impact the ability to perform activities of daily living (ADLs). Bio-ontologies are used to provide computable knowledge for ML methods to “understand” biomedical data. Results This retrospective study included 723 cancer patients from the SEER-MHOS dataset. Two ML methods were applied to create predictive models for ADL disabilities for the first year after a patient’s cancer diagnosis. The first method is a standard rule learning algorithm; the second is that same algorithm additionally equipped with methods for reasoning with ontologies. The models showed that a patient’s race, ethnicity, smoking preference, treatment plan and tumor characteristics including histology, staging, cancer site, and morphology were predictors for ADL performance levels one year after cancer diagnosis. The ontology-guided ML method was more accurate at predicting ADL performance levels ( P  < 0.1) than methods without ontologies. Conclusions This study demonstrated that bio-ontologies can be harnessed to provide medical knowledge for ML algorithms. The presented method demonstrates that encoding specific types of hierarchical relationships to guide rule learning is possible, and can be extended to other types of semantic relationships present in biomedical ontologies. The ontology-guided ML method achieved better performance than the method without ontologies. The presented method can also be used to promote the effectiveness and efficiency of ML in healthcare, in which use of background knowledge and consistency with existing clinical expertise is critical.