Mundi, Manpreet S

Abstract Background Personalized meal planning by registered dietitian nutritionists (RDNs) is time‐intensive. Large language models (LLMs) may automate drafting meal plans, but their nutritional accuracy in clinical practice is uncertain. Methods In this proof‐of‐concept study, five outpatient RDNs and four LLMs (Gemini, CoPilot, ChatGPT 4.0, and customized ChatGPT 4.0) each generated 3‐day meal plans for five validated clinical scenarios. Effectiveness was defined as accuracy in meeting pre‐specified energy, protein, carbohydrate, fat, and sodium targets. Time to create plans and RDN comfort (self‐rated confidence in nutritional accuracy and clinical appropriateness on 1–5 Likert scale) were recorded. Three independent RDNs, blinded to source, analyzed nutrient content using Nutritionist Pro. Group differences were assessed with t ‐test and ANOVA. Results All LLMs and RDNs produced feasible meal plans. LLMs generated meal plans in under 1 min, whereas RDNs required a mean of 44 min per scenario. RDNs reported comfort levels ranging from 3.8 to 4.8. Across most scenarios, LLM plans delivered a smaller proportion of requested energy than RDN plans, which more consistently approached energy targets. Both groups performed similarly for the Mediterranean diet scenario. Overall, protein accuracy did not differ. However, in chronic kidney disease, LLMs undershot the guideline‐based protein target, while RDNs tended to modestly exceed it. Accuracy for low‐carbohydrate, fat, and sodium diets was comparable. Conclusion LLMs can rapidly generate clinically plausible meal plans but are less reliable than RDNs in achieving prescribed energy and selected macronutrient goals. Prompt precision is essential for nutrient‐specific targets. A hybrid model in which RDNs refine LLM‐generated drafts may leverage efficiency without sacrificing clinical accuracy.

Home enteral nutrition (HEN) is essential for patients with a functioning gastrointestinal tract who cannot meet nutritional needs orally, yet outpatient management remains complex, resource-intensive, and supported by a limited evidence base. Artificial intelligence (AI) may augment HEN care by extending monitoring, education, risk assessment, documentation support, and operational coordination into the home environment. Consistent with the narrative review format, this article uses a pragmatic, transparent synthesis of influential HEN-specific literature, relevant clinical nutrition evidence, and background knowledge from adjacent fields, including home healthcare, chronic disease management, oncology nutrition, telehealth, and software regulation. Direct evidence in established HEN populations remains scarce; therefore, most AI applications should be considered hypotheses or early implementation opportunities rather than proven standards of care. The strongest near-term opportunities are clinician-supervised patient education, symptom triage, adherence support, remote monitoring, and workflow automation. Predictive analytics, smart pumps, and precision enteral prescription tools are promising but require prospective HEN-specific validation, interoperability with electronic health records and home-infusion systems, reimbursement pathways, and governance safeguards. Key barriers include dataset bias, limited external validation, alert fatigue, privacy and regulatory concerns, unclear accountability, digital equity, cost uncertainty, and the risk of dehumanizing care. AI should be viewed as a complement to multidisciplinary HEN expertise. Priorities for the near future include HEN registries, standardized outcomes, prospective validation, pragmatic implementation trials, health-economic evaluation, and transparent oversight that preserves clinician accountability and patient-centered care.

Background: Artificial intelligence (AI) is increasingly being integrated into healthcare, with applications ranging from predictive analytics to clinical decision support. In clinical nutrition, AI tools offer opportunities to improve workflow efficiency, enhance dietary assessment, and personalize nutrition care. Despite growing interest, little is known about registered dietitian nutritionists’ (RDNs) perceptions of AI in clinical practice. The aim of the present study was to assess RDNs’ attitudes toward AI use within a large healthcare system, along with their perceived barriers in this regard. Methods: A cross-sectional survey was developed through expert review and distributed electronically via REDCap to RDNs across Mayo Clinic’s academic campuses and affiliated health system sites. The 23-item survey included Likert-scale items addressing AI’s potential utilization within clinical care, perceived benefits and risks, and readiness for adoption. Responses were summarized using descriptive statistics. Factor analysis identified underlying constructs related to AI attitudes. Differences stratified by age and years of experience were evaluated using ANOVA. Results: Of the 185 RDNs invited, 64 (35%) responded. Two factors emerged: optimism regarding AI usage (Cronbach’s α = 0.94) and skepticism about implementation (α = 0.76). The overall mean ± SD score for optimism was 0.1 ± 0.6 (neutral), while skepticism averaged 1.0 ± 0.6 (moderate). Skepticism differed by years of experience (p = 0.012), with the lowest levels observed among RDNs with ≥21 years of practice. No significant differences were observed across age groups. Discussion: RDNs demonstrated neutral attitudes toward AI use but expressed concerns about accuracy, training, and implementation challenges. Addressing these concerns through education and structured implementation strategies may facilitate successful adoption of AI in dietetic practice.

Abstract Background Head and neck cancer represents the seventh most common cancer diagnosis globally. Maintaining sufficient nutrition is important for preventing malnutrition (undernutrition) and muscle wasting, which contribute to worse outcomes, although many patients are unable to maintain adequate oral intake throughout treatment. This guideline provides practice guidance on nutrition care for patients with head and neck cancer. Methods An interdisciplinary team developed key questions and scanned results from a systematic search of the PubMed, EMBASE, CINAHL, and Cochrane Central databases back to 2001. Recommendations were created for key questions concerning timing and duration of nutrition support (early vs delayed enteral nutrition [EN], postoperative feeding, and perioperative dietitian intervention), frequency of dietitian and speech pathology consultations, nutrition screening and assessment, macronutrient requirements, enteral access devices, adjunctive strategies (appetite stimulants and continuation of oral intake alongside EN), specialized nutrients (arginine, glutamine, ω‐3, and immunonutrition), and interdisciplinary care. Results Ninety‐two studies were included. Recommendations were made supporting early initiation of EN when oral intake is inadequate, nutrition within 24 h after surgery, weekly consultation with a dietitian during radiotherapy, malnutrition screening and assessment with validated tools, interdisciplinary models of care, dietitian involvement before and after surgery, and when to consider use of specialized nutrients. Recommendations are also provided for protein intake (1.2–1.5 g/kg/day) and energy intake (≥30 kcal/kg/day). Conclusion This guideline provides guidance for the nutrition care of patients with head and neck cancer, identifies research gaps, and calls for standardized outcome reporting to further the state of the evidence. This paper was approved by the ASPEN Board of Directors.

Abstract Background Short bowel syndrome (SBS) is a chronic condition requiring parenteral nutrition (PN) support and multidisciplinary management. However, disparities in access to care and standardized treatment pathways, in addition to economic burden, remain considerable for patients. Understanding healthcare resource utilization (HCRU) and treatment patterns, especially in relation to patient‐reported outcomes (PROs), is critical for improving care. Methods A cross‐sectional, multiphase study was conducted in 2023. This analysis focuses on phase 3, using a deidentified database that integrated claims and PROs from 68 patients in phase 2. Twenty‐three patients were included in the analytic cohort after applying additional criteria. Descriptive statistics summarized patient demographics, HCRU, and treatment patterns for the overall cohort and stratified by median SBS–quality of life (QoL) score. Results The median age at SBS diagnosis was 35 years, and 91% of patients were female. Patients saw a median of 35 different healthcare providers and underwent approximately five procedures before diagnosis. In the 6 months after diagnosis, 39% had been hospitalized, and 26% had emergency room (ER) visits. Healthcare costs increased after diagnosis, with long‐term PN use accounting for 34% of total costs. Patients with worse QoL had a higher number of ER visits than patients with better QoL. Patients who self‐reported being treated by SBS specialists had lower healthcare costs than patients who did not receive specialized care. Conclusion SBS is associated with high HCRU and costs, particularly for patients with poor QoL. Multidisciplinary care, especially from SBS specialists, may help reduce healthcare costs and improve patient outcomes.

Abstract Background Clinical nutrition (CN) is becoming increasingly complex because of the rising prevalence of chronic illness, cancer, and malnutrition‐related conditions such as short bowel syndrome and refeeding syndrome. Despite its clinical significance, nutrition education among US physicians remains limited. Simultaneously, large language model (LLM)–based artificial intelligence assistants (AIAs) have emerged as tools to support complex clinical decision‐making but remain largely untested in CN. Methods This retrospective study evaluated four LLM‐based AIAs—ChatGPT (OpenAI), OpenEvidence (OpenEvidence Inc), Gemini (Google, Google DeepMind), and Copilot (Microsoft Corporation)—using five complex CN cases from our nutrition support service. Each AIA was queried with patient‐specific CN questions. Responses were blinded and reviewed by five physician CN experts using an eight‐item assessment tool evaluating clarity, relevance, evidence, and clinical utility. Results All AIAs produced clinically appropriate responses, with Gemini scoring highest in relevance (4.04) and clarity (4.16). Overall satisfaction scores ranged from 3.08 (Copilot) to 3.84 (Gemini). Citation quality and originality of insights varied and were generally limited, and no consistent differences in performance were observed across the five cases among the four AIAs. Conclusion LLM‐based AIAs can reliably replicate expert reasoning in CN. Although not yet a source of novel clinical insights, the true potential of this approach may lie in its application among physicians without specialized expertise in CN, helping to bridge existing knowledge gaps in nutrition care. Presenting full clinical cases, as shown in this study, could support AIA‐enabled e‐consultation in the future, thereby addressing gaps in CN education.

Abstract Background Patients with short bowel syndrome–associated intestinal failure (SBS‐IF) require complex, personalized, and multidisciplinary care; however, there are disparities in access. This study measured the impact of unmet needs and treatment burden among patients and their caregivers. Methods This cross‐sectional, mixed‐method study included US adults self‐reporting SBS‐IF and receiving home parenteral nutrition for ≥6 months and their caregivers. One‐hour interviews informed the development of a 30‐min survey administered to participants from an online health community. Results Among 68 patients, the mean age was 42 years, 79% were female, and 88% were White. Most of the 16 caregivers were female (69%), and younger than 45 years (69%). Of 32 patients (47%) receiving care from an SBS specialist, only 19 (59%) were referred after diagnosis; in 58% of these, referral occurred >6 months after diagnosis. Depression was reported in 44 patients (65%), with 54% not receiving professional mental health care. Financial concerns were common, with 44 patients (65%) unable to work and 40 patients (59%) reporting annual household income of <$50,000. Of 32 patients reporting difficulty paying medical bills, 22 (32%) could not fill prescriptions and 19 (28%) canceled/delayed healthcare provider visits. Social determinant of health challenges were reported by 44 patients (65%). Caregivers' responsibilities impacted their ability to work (50%) and future outlook (63%). Conclusion Patients with SBS‐IF face difficulties accessing specialized healthcare, and are at risk of adverse healthcare outcomes, financial hardships, and poor quality of life. Mental health and work/financial issues were common among both patients and caregivers.

AbstractThe dual burden of undernutrition and overnutrition requires a greater understanding and commitment to physician training and specialization in nutrition support. Despite the significant healthcare need and existence of organizations focused on nutrition support such as the American Society for Parenteral and Enteral Nutrition (ASPEN), physician involvement in the nutrition care of high‐risk patients remains low. In an ASPEN survey of members, inadequate training among physicians was reported along with significant barriers to involvement in nutrition support, such as insufficient protected time, reduced reimbursement and financial support, inadequate support from administrators or supervisors, as well as a nationwide reduction in number of nutrition support teams. These changes in the healthcare landscape prompted the ASPEN Physician Engagement Committee to develop a critical review focused on domains of nutrition risk assessment, enteral and parenteral access and support, scholarly activities, board certification, administrative responsibilities, education and training opportunities, coding, and reimbursement. The aim of this critical review is to capacitate physicians to engage in nutrition support and enhance their acumen in clinical nutrition to improve patient care and enrich personal and professional development.

Background: Artificial intelligence (AI) platforms can potentially enhance clinical decision-making (CDM) in primary care settings. OpenEvidence (OE), an AI tool, draws from trusted sources to generate evidence-based medicine (EBM) recommendations to address clinical questions. However, its effectiveness in real-world primary care cases remains unknown. Objective: To evaluate the performance of OE in providing EBM recommendations for five common chronic conditions in primary care: hypertension, hyperlipidemia, diabetes mellitus type 2, depression, and obesity. Methods: Five patient cases were retrospectively analyzed. Physicians posed specific clinical questions, and OE responses were evaluated on clarity, relevance, evidence support, impact on CDM, and overall satisfaction. Four independent physicians provided ratings using a 0 to 4 scale. Results: OE provided accurate, evidence-based recommendations in all cases, aligning with physician plans. OE was scored on a scale of zero to four, where zero was very unclear, and four was very clear. Mean scores across cases were clarity (3.55 ± 0.60), relevance (3.75 ± 0.44), support (3.35 ± 0.49), and satisfaction (3.60 ± 0.60). However, the impact on CDM was limited (1.95 ± 1.05), as OE primarily reinforced rather than modified plans. Conclusion: OE was rated high in clarity, relevance, and evidence-based support, reinforcing physician decisions in common chronic conditions. While the impact on CDM was minimal due to the study’s retrospective nature, OE shows promise in augmenting the primary care physician. Prospective trials are needed to evaluate its utility in complex cases and multidisciplinary settings.