An Unsupervised Machine Learning Approach to Evaluating the Association of Symptom Clusters With Adverse Outcomes Among Older Adults With Advanced Cancer: A Secondary Analysis of a Randomized Clinical Trial.

Importance: Older adults with advanced cancer who have high pretreatment symptom severity often experience adverse events during cancer treatments. Unsupervised machine learning may help stratify patients into different risk groups. Objective: To evaluate whether clusters identified from baseline patient-reported symptom severity were associated with adverse outcomes. Design, Setting, and Participants: This secondary analysis of the Geriatric Assessment Intervention for Reducing Toxicity in Older Patients With Advanced Cancer (GAP70+) Trial (2014-2019) included patients who completed the National Cancer Institute Patient-Reported Outcomes version of the Common Terminology Criteria for Adverse Events (PRO-CTCAE) before starting a new cancer treatment regimen and received care at community oncology sites across the United States. An unsupervised machine learning algorithm (k-means with Euclidean distance) clustered patients based on similarities of baseline symptom severities. Clustering variables included severity items of 24 PRO-CTCAE symptoms (range, 0-4; corresponding to none, mild, moderate, severe, and very severe). Total severity score was calculated as the sum of 24 items (range, 0-96). Whether the clusters were associated with unplanned hospitalization, death, and toxic effects was then examined. Analyses were conducted in January and February 2022. Exposures: Symptom severity. Main Outcomes and Measures: Unplanned hospitalization over 3 months (primary), all-cause mortality over 1 year, and any clinician-rated grade 3 to 5 toxic effect over 3 months. Results: Of 718 enrolled patients, 706 completed baseline PRO-CTCAE and were included (mean [SD] age, 77.2 [5.5] years, 401 [56.8%] male patients; 51 [7.2%] Black and 619 [87.8%] non-Hispanic White patients; 245 [34.7%] with gastrointestinal cancer; 175 [24.8%] with lung cancer; mean [SD] impaired Geriatric Assessment domains, 4.5 [1.6]). The algorithm classified 310 (43.9%), 295 (41.8%), and 101 (14.3%) into low-, medium-, and high-severity clusters (within-cluster mean [SD] severity scores: low, 6.3 [3.4]; moderate, 16.6 [4.3]; high, 29.8 [7.8]; P < .001). Controlling for sociodemographic variables, clinical factors, study group, and practice site, compared with patients in the low-severity cluster, those in the moderate-severity cluster were more likely to experience hospitalization (risk ratio, 1.36; 95% CI, 1.01-1.84; P = .046). Moderate- and high-severity clusters were associated with a higher risk of death (moderate: hazard ratio, 1.31; 95% CI, 1.01-1.69; P = .04; high: hazard ratio, 2.00; 95% CI, 1.43-2.78; P < .001), but not toxic effects. Conclusions and Relevance: In this study, unsupervised machine learning partitioned patients into distinct symptom severity clusters; patients with higher pretreatment severity were more likely to experience hospitalization and death. Trial Registration: ClinicalTrials.gov Identifier: NCT02054741.

Effects of a Geriatric Assessment Intervention on Patient-Reported Symptomatic Toxicity in Older Adults With Advanced Cancer.

PURPOSE: Providing a geriatric assessment (GA) summary with management recommendations to oncologists reduces clinician-rated toxicity in older patients with advanced cancer receiving treatment. This secondary analysis of a national cluster randomized clinical trial (ClinicalTrials.gov identifier: NCT02054741) aims to assess the effects of a GA intervention on symptomatic toxicity measured by Patient-Reported Outcomes Common Terminology Criteria for Adverse Events (PRO-CTCAE). METHODS: From 2014 to 2019, the study enrolled patients age ≥ 70 years, with advanced solid tumors or lymphoma and ≥ 1 GA domain impairment, who were initiating a regimen with high prevalence of toxicity. Patients completed PRO-CTCAEs, including the severity of 24 symptoms (11 classified as core symptoms) at enrollment, 4-6 weeks, 3 months, and 6 months. Symptoms were scored as grade ≥ 2 (at least moderate) and grade ≥ 3 (severe/very severe). Symptomatic toxicity was determined by an increase in severity during treatment. A generalized estimating equation model was used to assess the effects of the GA intervention on symptomatic toxicity. RESULTS: Mean age was 77 years (range, 70-96 years), 43% were female, and 88% were White, 59% had GI or lung cancers, and 27% received prior chemotherapy. In 706 patients who provided PRO-CTCAEs at baseline, 86.1% reported at least one moderate symptom and 49.7% reported severe/very severe symptoms at regimen initiation. In 623 patients with follow-up PRO-CTCAE data, compared with usual care, fewer patients in the GA intervention arm reported grade ≥ 2 symptomatic toxicity (overall: 88.9% v 94.8%, P = .035; core symptoms: 83.4% v 91.7%, P = .001). The results for grade ≥ 3 toxicity were comparable but not significant (P > .05). CONCLUSION: In the presence of a high baseline symptom burden, a GA intervention for older patients with advanced cancer reduces patient-reported symptomatic toxicity.