National Implementation of an Artificial Intelligence-Based Virtual Dietitian for Patients With Cancer.

PURPOSE: Nutritional status is an established driver of cancer outcomes, but there is an insufficient workforce of registered dietitians to meet patient needs for nutritional counseling. Artificial intelligence (AI) and machine learning (ML) afford the opportunity to expand access to guideline-based nutritional support. METHODS: An AI-based nutrition assistant called Ina was developed on the basis of a learning data set of >100,000 expert-curated interventions, peer-reviewed literature, and clinical guidelines, and provides a conversational text message-based patient interface to guide dietary habits and answer questions. Ina was implemented nationally in partnership with 25 advocacy organizations. Data on demographics, patient-reported outcomes, and utilization were systematically collected. RESULTS: Between July 2019 and August 2023, 3,310 users from all 50 states registered to use Ina. Users were 73% female; median age was 57 (range, 18-91) years; most common cancer types were genitourinary (22%), breast (21%), gynecologic (19%), GI (14%), and lung (12%). Users were medically complex, with 50% reporting Stage III to IV disease, 37% with metastases, and 50% with 2+ chronic conditions. Nutritional challenges were highly prevalent: 58% had overweight/obese BMIs, 83% reported barriers to good nutrition, and 42% had food allergies/intolerances. Levels of engagement were high: 68% texted questions to Ina; 79% completed surveys; median user retention was 8.8 months; 94% were satisfied with the platform; and 98% found the guidance helpful. In an evaluation of outcomes, 84% used the advice to guide diet; 47% used recommended recipes, 82% felt the program improved quality of life (QoL), and 88% reported improved symptom management. CONCLUSION: Implementation of an evidence-based AI virtual dietitian is feasible and is reported by patients to be beneficial on diet, QoL, and symptom management. Ongoing evaluations are assessing impact on other outcomes.

A prospective study of dysgeusia and related symptoms in patients with multiple myeloma after autologous hematopoietic cell transplantation.

BACKGROUND: Dysgeusia is a common but understudied complication in patients undergoing autologous hematopoietic cell transplantation (auto-HCT). We assessed the feasibility of using chemical gustometry (CG) to measure dysgeusia and explored its associations with symptom burden, nutrition, chemotherapy pharmacokinetics (PK), and the oral microbiome. METHODS: We conducted a single-center, prospective feasibility study (NCT03276481) of patients with multiple myeloma undergoing auto-HCT. CG was performed longitudinally testing five flavors (sweet, sour, salty, bitter, umami) to calculate a total taste score (maximum score, 30). We measured caloric intake and patient-reported symptoms, assessing their correlation with oral microbiota composition and salivary and blood melphalan PK exposure. RESULTS: Among all 45 patients, 39 (87%) completed at least four (>60%) and 22 (49%) completed all six CG assessments. Median total CG scores remained stable over time but were lowest at day +7 (27, range 24-30) with recovery by day +100. Symptom burden was highest by day +10 (area under the curve, 2.9; range, 1.0-4.6) corresponding with the lowest median overall caloric intake (1624 kcal; range, 1345-2267). Higher serum/salivary melphalan levels correlated with higher patient-reported dysgeusia and lower caloric intake. Oral microbiota α-diversity was stable early and increased slightly by day +100. CONCLUSIONS: Assessment of dysgeusia by CG is feasible after auto-HCT. Most dysgeusia, symptom burden, and lowest caloric intake occurred during the blood count nadir. Higher melphalan concentrations correlated with more dysgeusia and poorer caloric intake. Future studies will aim to modulate melphalan exposure by PK-targeted dosing and characterize patient taste preferences to personalize diets for improved nutritional intake. LAY SUMMARY: Taste changes after cancer treatments are very common. We used chemical gustometry (taste testing) to study taste changes and to better understand why patients with multiple myeloma experience this symptom after autologous hematopoietic cell transplantation. We found that taste testing was feasible, taste changes peaked when blood counts were lowest, and most patients recovered their taste by 100 days after transplantation. Taste changes correlated with lower food intake and with higher levels of chemotherapy in the body. Future work will focus on using personalized chemotherapy doses to reduce taste changes and to match patients' individual taste preferences with their diets.

Unlocking the Complex Flavors of Dysgeusia after Hematopoietic Cell Transplantation.

Dysgeusia is a frequently occurring symptom after hematopoietic cell transplantation (HCT) that has important long-term effects on physical, nutritional, and immunologic recovery, as well as on quality of life. Despite the relevance of this symptom, the study of dysgeusia in patients undergoing HCT has been limited, owing in part to its complexity. In this article, we review normal taste function and its clinical evaluation, discuss how dysgeusia uniquely affects patients undergoing HCT, and examine distinct, transplantation-related contributors to dysgeusia that may help elucidate strategies to ultimately reduce this symptom burden after transplantation.

Nutrition Literacy among Cancer Survivors: Feasibility Results from the Healthy Eating and Living Against Breast Cancer (HEAL-BCa) Study: a Pilot Randomized Controlled Trial.

Knowledge of nutrition among breast cancer patients is insufficient, despite their motivation to seek valid information about healthy food choices. This study examines the feasibility of nutrition education workshops for cancer survivors, to inform the design of a multi-center intervention. Fifty-nine female English-speaking breast cancer patients, who had completed treatment, were enrolled. Participants were randomized to the intervention or control group. The intervention group attended six nutrition education sessions, and the control group received brochures. Measurements were done at baseline and 3-month follow-up and included the Assessment Instrument for Breast Cancer (NLit-BCa), fruit/vegetable and general health literacy screeners. Height and weight were measured. Changes in nutrition literacy, health literacy, and food intake from baseline to follow-up (within-group change) were calculated for both groups (effect sizes were reported as Cohen's d). Participants were mostly white, with a mean age of 58 years, BMI of 31.6 kg/m2, and had college degrees. Follow-up rates were high (89% = control and 77% = intervention group). At baseline, participants scored high for most NLit-BCa assessment components except food portions in both groups. At the 3-month follow-up, effect sizes (d) on the NLit-BCa ranged from -0.5 to 0.16. The study met its recruitment goals within 6 months. Focus groups indicated that (a) attending six sessions was acceptable, (b) patients found social/emotional support, (c) improvements should include information for special diets and booster sessions. This pilot study suggests that the intervention was acceptable and that scaling up of this intervention is feasible and could provide benefit to breast cancer survivors.