Phenotyping severity of patient‐centered outcomes using clinical notes: A prostate cancer use case

Abstract

Introduction: A learning health system (LHS) must improve care in ways that are meaningful to patients, integrating patient-centered outcomes (PCOs) into core infrastructure. PCOs are common following cancer treatment, such as urinary incontinence (UI) following prostatectomy. However, PCOs are not systematically recorded because they can only be described by the patient, are subjective and captured as unstructured text in the electronic health record (EHR). Therefore, PCOs pose significant challenges for phenotyping patients. Here, we present a natural language processing (NLP) approach for phenotyping patients with UI to classify their disease into severity subtypes, which can increase opportunities to provide precision-based therapy and promote a value-based delivery system. Methods: Patients undergoing prostate cancer treatment from 2008 to 2018 were identified at an academic medical center. Using a hybrid NLP pipeline that combines rule-based and deep learning methodologies, we classified positive UI cases as mild, moderate, and severe by mining clinical notes. Results: The rule-based model accurately classified UI into disease severity categories (accuracy: 0.86), which outperformed the deep learning model (accuracy: 0.73). In the deep learning model, the recall rates for mild and moderate group were higher than the precision rate (0.78 and 0.79, respectively). A hybrid model that combined both methods did not improve the accuracy of the rule-based model but did outperform the deep learning model (accuracy: 0.75). Conclusion: Phenotyping patients based on indication and severity of PCOs is essential to advance a patient centered LHS. EHRs contain valuable information on PCOs Selen Bozkurt and Rohan Paul shared first authorship.

Hsa_circ_0030586 promotes epithelial–mesenchymal transition in prostate cancer via PI3K-AKT signaling

“…Despite improvements in diagnostic and therapeutic treatments, several patients still developed advanced PCa at the time of diagnosis and missed the chance for in-time treatment because of a lack of effective early diagnostic markers [ 23 , 24 ]. Therefore, it is necessary to explore new early diagnostic molecular markers for PCa [ 25 , 26 ].…”

Natural Language Processing and Machine Learning Methods to Characterize Unstructured Patient-Reported Outcomes: Validation Study

“…Multimodal sentiment analysis [58], which investigates affective states by extracting textual and audio features, can be combined with the semantic features from NLP to obtain a comprehensive understanding of survivors' PROs. The successful application of NLP/ML for PRO assessment ideally requires the implementation of integrated platforms that interconnect the EHR-based medical note systems, NLP/ML analytics, and supportive tools for result display, clinical interpretation, and treatment recommendation [20,[59][60][61]. The integrated platforms will facilitate clinicians in clinical decision-making for caring for survivors of cancer whose complex late medical effects can be predicted by the deterioration of symptoms and clinical parameters.…”

Why does human phenomics matter today?

“…Patient‐centred outcomes (PCOs) are recognised as a challenge for phenotyping due to the lack of relevant structured information that can serve as the basis for phenotyping algorithms. Hernandez‐Boussard et al 9 suggest natural language processing (NLP) as a mechanism for integrating PCOs into phenotype definitions in a structured manner. Severity‐based phenotypes introduce additional complexity, which the authors address by combining NLP with rule‐based models.…”