Literature DB >> 35771564

Development and Validation of a Machine Learning Algorithm Predicting Emergency Department Use and Unplanned Hospitalization in Patients With Head and Neck Cancer.

Christopher W Noel1,2,3, Rinku Sutradhar2,3, Lesley Gotlib Conn2,4, David Forner2,5, Wing C Chan3, Rui Fu2,3,4, Julie Hallet2,3,4,6, Natalie G Coburn2,3,4,6, Antoine Eskander1,2,3,4,6.   

Abstract

Importance: Patient-reported symptom burden was recently found to be associated with emergency department use and unplanned hospitalization (ED/Hosp) in patients with head and neck cancer. It was hypothesized that symptom scores could be combined with administrative health data to accurately risk stratify patients. Objective: To develop and validate a machine learning approach to predict future ED/Hosp in patients with head and neck cancer. Design, Setting, and Participants: This was a population-based predictive modeling study of patients in Ontario, Canada, diagnosed with head and neck cancer from January 2007 through March 2018. All outpatient clinical encounters were identified. Edmonton Symptom Assessment System (ESAS) scores and clinical and demographic factors were abstracted. Training and test cohorts were randomly generated in a 4:1 ratio. Various machine learning algorithms were explored, including (1) logistic regression using a least absolute shrinkage and selection operator, (2) random forest, (3) gradient boosting machine, (4) k-nearest neighbors, and (5) an artificial neural network. Data analysis was performed from September 2021 to January 2022. Main Outcomes and Measures: The main outcome was any 14-day ED/Hosp event following symptom assessment. The performance of each model was assessed on the test cohort using the area under the receiver operator characteristic (AUROC) curve and calibration plots. Shapley values were used to identify the variables with greatest contribution to the model.
Results: The training cohort consisted of 9409 patients (mean [SD] age, 63.3 [10.9] years) undergoing 59 089 symptom assessments (80%). The remaining 2352 patients (mean [SD] age, 63.3 [11] years) and 14 193 symptom assessments were set aside as the test cohort (20%). Several models had high predictive accuracy, particularly the gradient boosting machine (validation AUROC, 0.80 [95% CI, 0.78-0.81]). A Youden-based cutoff corresponded to a validation sensitivity of 0.77 and specificity of 0.66. Patient-reported symptom scores were consistently identified as being the most predictive features within models. A second model built only with symptom severity data had an AUROC of 0.72 (95% CI, 0.70-0.74). Conclusions and Relevance: In this study, machine learning approaches predicted with a high degree of accuracy ED/Hosp in patients with head and neck cancer. These tools could be used to accurately risk stratify patients and may help direct targeted intervention.

Entities:  

Mesh:

Year:  2022        PMID: 35771564      PMCID: PMC9247860          DOI: 10.1001/jamaoto.2022.1629

Source DB:  PubMed          Journal:  JAMA Otolaryngol Head Neck Surg        ISSN: 2168-6181            Impact factor:   8.961


  46 in total

1.  How to develop machine learning models for healthcare.

Authors:  Po-Hsuan Cameron Chen; Yun Liu; Lily Peng
Journal:  Nat Mater       Date:  2019-05       Impact factor: 43.841

2.  Overall Survival Results of a Trial Assessing Patient-Reported Outcomes for Symptom Monitoring During Routine Cancer Treatment.

Authors:  Ethan Basch; Allison M Deal; Amylou C Dueck; Howard I Scher; Mark G Kris; Clifford Hudis; Deborah Schrag
Journal:  JAMA       Date:  2017-07-11       Impact factor: 56.272

3.  Opioid prescription after pain assessment: a population-based cohort of elderly patients with cancer.

Authors:  Lisa Barbera; Hsien Seow; Amna Husain; Doris Howell; Clare Atzema; Rinku Sutradhar; Craig Earle; Jonathan Sussman; Ying Liu; Deborah Dudgeon
Journal:  J Clin Oncol       Date:  2012-02-27       Impact factor: 44.544

4.  Emergency department visits and unplanned hospitalizations in the treatment period for head and neck cancer patients treated with curative intent: A population-based analysis.

Authors:  A Eskander; M K Krzyzanowska; H D Fischer; N Liu; P C Austin; J C Irish; D J Enepekides; J Lee; E Gutierrez; E Lockhart; M Raphael; S Singh
Journal:  Oral Oncol       Date:  2018-06-19       Impact factor: 5.337

5.  Phase III Randomized Controlled Trial of eRAPID: eHealth Intervention During Chemotherapy.

Authors:  Kate Absolom; Lorraine Warrington; Eleanor Hudson; Jenny Hewison; Carolyn Morris; Patricia Holch; Robert Carter; Andrea Gibson; Marie Holmes; Beverly Clayton; Zoe Rogers; Lucy McParland; Mark Conner; Liz Glidewell; Barbara Woroncow; Bryony Dawkins; Sarah Dickinson; Claire Hulme; Julia Brown; Galina Velikova
Journal:  J Clin Oncol       Date:  2021-01-08       Impact factor: 44.544

6.  From Risk Prediction to Delivery Innovation: Envisioning the Path to Personalized Cancer Care Delivery.

Authors:  Arthur S Hong; Nathan R Handley
Journal:  JCO Oncol Pract       Date:  2021-10-12

7.  The association of physical and psychological symptom burden with time to death among palliative cancer outpatients.

Authors:  Winson Y Cheung; Niusha Barmala; Sanaz Zarinehbaf; Gary Rodin; Lisa W Le; Camilla Zimmermann
Journal:  J Pain Symptom Manage       Date:  2008-08-09       Impact factor: 3.612

8.  Symptom Monitoring With Patient-Reported Outcomes During Routine Cancer Treatment: A Randomized Controlled Trial.

Authors:  Ethan Basch; Allison M Deal; Mark G Kris; Howard I Scher; Clifford A Hudis; Paul Sabbatini; Lauren Rogak; Antonia V Bennett; Amylou C Dueck; Thomas M Atkinson; Joanne F Chou; Dorothy Dulko; Laura Sit; Allison Barz; Paul Novotny; Michael Fruscione; Jeff A Sloan; Deborah Schrag
Journal:  J Clin Oncol       Date:  2015-12-07       Impact factor: 44.544

9.  Screening, assessment, and management of fatigue in adult survivors of cancer: an American Society of Clinical oncology clinical practice guideline adaptation.

Authors:  Julienne E Bower; Kate Bak; Ann Berger; William Breitbart; Carmelita P Escalante; Patricia A Ganz; Hester Hill Schnipper; Christina Lacchetti; Jennifer A Ligibel; Gary H Lyman; Mohammed S Ogaily; William F Pirl; Paul B Jacobsen
Journal:  J Clin Oncol       Date:  2014-04-14       Impact factor: 44.544

Review 10.  Artificial intelligence for clinical oncology.

Authors:  Benjamin H Kann; Ahmed Hosny; Hugo J W L Aerts
Journal:  Cancer Cell       Date:  2021-04-29       Impact factor: 38.585

View more

北京卡尤迪生物科技股份有限公司 © 2022-2023.