IntroductionEuropean Society for Clinical Nutrition and Metabolism guidelines recommend that patients with cancer should be screened for malnutrition at diagnosis. The dietetic assessment and intervention in lung cancer study investigated the nutritional status of patients with non-small cell lung cancer (NSCLC) and the need for dietetic intervention.MethodsIn this observational cohort pilot study, patients with stage 3b and 4 NSCLC were assessed prior to starting first line systemic anticancer therapy (SACT) with a range of measurements and questionnaires. We report the outcomes related to the Patient Generated Subjective Global Assessment tool (PG-SGA),Results96 patients were consented between April 2017 and August 2019. The PG-SGA identified that 78% of patients required specialist nutritional advice; with 52% patients having a critical need for dietetic input and symptom management. Results were dominated by symptom scores. As a screening test, one or more symptoms or recent weight loss history had a sensitivity of 88% (95% CI 78.44% to 94.36%) and specificity of 95.24% (95% CI 76.18% to 99.88%) for need for dietetic intervention.ConclusionA large proportion of patients with NSCLC have a high symptom burden and are at risk of malnutrition prior to starting SACT and would benefit from dietetic review. It is imperative that oncologists and healthcare professionals discuss weight loss history and symptoms with lung cancer patients to correct nutritional deficiencies and resolve symptoms prior to starting treatment.

ObjectivesThe Dietetic Assessment and Intervention in Lung Cancer (DAIL) study was an observational cohort study. It triaged the need for dietetic input in patients with lung cancer, using questionnaires with 137 responses. This substudy tested if machine learning could predict need to see a dietitian (NTSD) using 5 or 10 measures.Methods76 cases from DAIL were included (Royal Surrey NHS Foundation Trust; RSH: 56, Frimley Park Hospital; FPH 20). Univariate analysis was used to find the strongest correlates with NTSD and ‘critical need to see a dietitian’ CNTSD. Those with a Spearman correlation above ±0.4 were selected to train a support vector machine (SVM) to predict NTSD and CNTSD. The 10 and 5 best correlates were evaluated.Results18 and 13 measures had a correlation above ±0.4 for NTSD and CNTSD, respectively, producing SVMs with 3% and 7% misclassification error. 10 measures yielded errors of 7% (NTSD) and 9% (CNTSD). 5 measures yielded between 7% and 11% errors. SVM trained on the RSH data and tested on the FPH data resulted in errors of 20%.ConclusionsMachine learning can predict NTSD producing misclassification errors <10%. With further work, this methodology allows integrated early referral to a dietitian independently of a healthcare professional.

No abstract

No abstract

No abstract