Lisa DiMartino1, Thomas Miano2, Kathryn Wessell3, Buck Bohac4, Laura C Hanson5. 1. RTI International, Translational Health Sciences Division (L.D.), Research Triangle Park, NC, USA. Electronic address: ldimartino@rti.org. 2. RTI International, Center for Data Science (T.M.), Research Triangle Park, NC, USA. 3. Cecil G. Sheps Center for Health Services Research, University of North Carolina at Chapel Hill (K.W., L.C.H.), Chapel Hill, NC, USA. 4. North Carolina Translational and Clinical Sciences Institute, University of North Carolina at Chapel Hill (B.B.), Chapel Hill, NC, USA. 5. Cecil G. Sheps Center for Health Services Research, University of North Carolina at Chapel Hill (K.W., L.C.H.), Chapel Hill, NC, USA; Division of Geriatric Medicine, University of North Carolina at Chapel Hill (L.C.H.), Chapel Hill, NC, USA.
Abstract
CONTEXT: For patients with cancer, uncontrolled pain and other symptoms are the leading cause of unplanned hospitalizations. Early access to specialty palliative care (PC) is effective to reduce symptom burden, but more efficient approaches are needed for rapid identification and referral. Information on symptom burden largely exists in free-text notes, limiting its utility as a trigger for best practice alerts or automated referrals. OBJECTIVES: To evaluate whether natural language processing (NLP) can be used to identify uncontrolled symptoms (pain, dyspnea, or nausea/vomiting) in the electronic health record (EHR) among hospitalized cancer patients with advanced disease. METHODS: The dataset included 1,644 hospitalization encounters for cancer patients admitted from 1/2017 -6/2019. We randomly sampled 296 encounters, which included 15,580 clinical notes. We manually reviewed the notes and recorded symptom severity. The primary endpoint was an indicator for whether a symptom was labeled as "controlled" (none, mild, not reported) or as "uncontrolled" (moderate or severe). We randomly split the data into training and test sets and used the Random Forest algorithm to evaluate final model performance. RESULTS: Our models predicted presence of an uncontrolled symptom with the following performance: pain with 61% accuracy, 69% sensitivity, and 46% specificity (F1: 69.5); nausea/vomiting with 68% accuracy, 21% sensitivity, and 90% specificity (F1: 29.4); and dyspnea with 80% accuracy, 22% sensitivity, and 88% specificity (F1: 21.1). CONCLUSION: This study demonstrated initial feasibility of using NLP to identify hospitalized cancer patients with uncontrolled symptoms. Further model development is needed before these algorithms could be implemented to trigger early access to PC.
CONTEXT: For patients with cancer, uncontrolled pain and other symptoms are the leading cause of unplanned hospitalizations. Early access to specialty palliative care (PC) is effective to reduce symptom burden, but more efficient approaches are needed for rapid identification and referral. Information on symptom burden largely exists in free-text notes, limiting its utility as a trigger for best practice alerts or automated referrals. OBJECTIVES: To evaluate whether natural language processing (NLP) can be used to identify uncontrolled symptoms (pain, dyspnea, or nausea/vomiting) in the electronic health record (EHR) among hospitalized cancer patients with advanced disease. METHODS: The dataset included 1,644 hospitalization encounters for cancer patients admitted from 1/2017 -6/2019. We randomly sampled 296 encounters, which included 15,580 clinical notes. We manually reviewed the notes and recorded symptom severity. The primary endpoint was an indicator for whether a symptom was labeled as "controlled" (none, mild, not reported) or as "uncontrolled" (moderate or severe). We randomly split the data into training and test sets and used the Random Forest algorithm to evaluate final model performance. RESULTS: Our models predicted presence of an uncontrolled symptom with the following performance: pain with 61% accuracy, 69% sensitivity, and 46% specificity (F1: 69.5); nausea/vomiting with 68% accuracy, 21% sensitivity, and 90% specificity (F1: 29.4); and dyspnea with 80% accuracy, 22% sensitivity, and 88% specificity (F1: 21.1). CONCLUSION: This study demonstrated initial feasibility of using NLP to identify hospitalized cancer patients with uncontrolled symptoms. Further model development is needed before these algorithms could be implemented to trigger early access to PC.
Authors: Wendy H Oldenmenger; Pleun J de Raaf; Cora de Klerk; Carin C D van der Rijt Journal: J Pain Symptom Manage Date: 2012-09-25 Impact factor: 3.612
Authors: Suzanne Tamang; Manali I Patel; Douglas W Blayney; Julie Kuznetsov; Samuel G Finlayson; Yohan Vetteth; Nigam Shah Journal: J Oncol Pract Date: 2015-05 Impact factor: 3.840
Authors: Stijn Van de Velde; Annemie Heselmans; Nicolas Delvaux; Linn Brandt; Luis Marco-Ruiz; David Spitaels; Hanne Cloetens; Tiina Kortteisto; Pavel Roshanov; Ilkka Kunnamo; Bert Aertgeerts; Per Olav Vandvik; Signe Flottorp Journal: Implement Sci Date: 2018-08-20 Impact factor: 7.327