Mohamed Elfadil, Osman

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 Coronavirus Disease 2019 (COVID-19) has led to dramatic changes including social distancing, closure of schools, travel bans, and issues of stay-at-home orders. The health-care field has been transformed with elective procedures and on-site visits being deferred. Telemedicine has emerged as a novel mechanism to continue to provide care. However, there remains a paucity of data regarding its efficacy in nutrition support, especially in patients with chronic intestinal failure (CIF). Objective Describe the utilization of telehealth in the routine management of CIF, particularly in the initiation and training of home parenteral nutrition (HPN). Methods A case series presenting our experience with the use of telemedicine to provide training for HPN for three patients. The manuscript describes the utility of telehealth in providing remote and adequate training for patients commenced on HPN during COVID-19 pandemic. Results Since the onset of the COVID-19 pandemic, we have successfully provided virtual training to three patients, including two who were noted to be severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) positive and one patient who could not be transferred to our facility for training. For SARS-CoV-2 positive patients, the risk of transmission to nursing staff with 8–10 h of face-to-face training in two cases was felt to be too significant for in-person training. We determined that the best option would be to stabilize parenteral nutrition in the hospital and perform virtual training. Although virtual training was successfully performed, it was felt that training in this manner took much longer, required frequent adjustment of the tablet device to ensure patient remained in field of view, and made it difficult to connect with the patient emotionally. Conclusions Telemedicine has significantly improved care provided during COVID-19 as a modality for effective training on HPN, while in-person communication was significantly limited due to the pandemic. However, when possible, it should be used in a manner that complements but does not supplant standard care.

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: In addition to the morbidity and mortality associated with acute infection, COVID-19 has been associated with persistent symptoms (>30 days), often referred to as Long COVID (LC). LC symptoms often cluster into phenotypes, resembling conditions such as fibromyalgia, postural orthostatic tachycardiac syndrome (POTS), and myalgic encephalomyelitis/chronic fatigue syndrome (ME/CFS). LC clinics have been established to best address the needs of LC patients and continuity of care. We developed a cross-sectional survey to assess treatment response through our LC Clinic (LCC). Methods: A 25-question survey (1-10 Likert scale) was expert- and content-validated by LCC clinicians, patients, and patient advocates. The survey assessed LC symptoms and the helpfulness of different interventions, including medications and supplements. A total of 852 LCC patients were asked to complete the survey, with 536 (62.9%) responding. Results: The mean time from associated COVID-19 infection to survey completion was 23.2 ± 6.4 months. The mean age of responders was 52.3 ± 14.1 (63% females). Self-reported symptoms were all significantly improved ( P < .001) from the initial visit to the LCC (baseline) to the time of the follow-up survey. However, only 4.5% (24/536) of patients rated all symptoms low (1-2) at the time of the survey, indicating low levels of full recovery in our cohort. The patients rated numerous interventions as being helpful, including low-dose naltrexone (45/77; 58%), vagal nerve stimulation (18/34; 53%), and fisetin (28/44; 64%). Conclusions: Patients report general improvements in symptoms following the initial LCC visit, but complete recovery rates remain low at 23.2 ± 6.4 months.

Abstract Background With data demonstrating benefit, the prevalence of home enteral nutrition (HEN) has increased significantly over the last few decades. Despite this increase, there remains a paucity of data regarding real‐world use of HEN including clinical outcomes and complications. Methods Descriptive analysis of prospectively maintained database of our specialized HEN program was undertaken. Patients who received care in our program with HEN initiation date between January 1, 2018, and December 31, 2020, were included in the analysis. Data regarding demographic information, anthropometrics, enteral nutrition (EN) regimen, electrolytes, and nutrition therapy history were included and tracked until July 31, 2021. Results During the study period, 1600 patients initiated HEN treatment under our care. Majority of the study population needed EN therapy due to malignancy and its complications, including malignant dysphagia or mechanical obstruction (60.6%) followed by neurodegenerative diseases (7.5%). By the end of the study period, a majority of the patients (82%) stopped HEN treatment. Of these, 44.2% achieved EN goals and/or oral autonomy. Patients continued HEN treatment for a median of 100 (interquartile range, 32–301) days. Overall, 53.2% of patients experienced/reported at least one HEN‐related complication that was clinically managed by the HEN team. Complications included tube‐related, enteral feeding intolerance (EFI), and electrolyte shifts. Conclusion In our study population, HEN was most utilized to manage malignancy‐related complications, including dysphagia. Unfortunately, complications, including EFI and tube‐related complications, remained quite prevalent. Further evaluation regarding risk factors for complications and preventive mechanisms, such as increased education, is indicated.

Abstract The use of enteral nutrition (EN) continues to increase given benefits. However, with this increase in use, it is also becoming evident that enteral feeding intolerance (EFI) is also quite prevalent, leading to the inability to meet nutrition needs in many patients. Given the wide variability in the EN population as well as the number of formulas available, there is not a clear consensus regarding the best approach to EFI management. One approach that is emerging to improve EN tolerance is the use of peptide‐based formulas (PBFs). PBFs refer to enteral formulas containing proteins that have been enzymatically hydrolyzed to dipeptides and tripeptides. These hydrolyzed proteins are often combined with higher medium‐chain triglyceride content to generate an enteral formula that is essentially easier to absorb and utilize. Emerging data demonstrate that the use of PBF in patients with EFI may improve clinical outcomes along with a corresponding reduction in healthcare utilization and potentially the cost of care. This review aims to navigate through key clinical applications and benefits of PBF and to discuss relevant data shared in the literature.

Abstract Intestinal failure (IF) is a rare disease that requires ongoing intravenous supplementation to sustain growth and health. Advancements in parenteral nutrition (PN) and central venous access in the 1960s and 1970s transformed a life‐limiting disease to a chronic one in which patients are able to administer hydration, electrolytes, micronutrients, and macronutrients in the comfort of their home. However, despite ongoing advancements in the field of home PN (HPN), complications—whether related to central venous catheters or PN itself—remain common and can be associated with significant morbidity and mortality. Central venous access can be associated with thrombosis, central line–associated bloodstream infection, or damage and can result in loss of access over time. PN can be associated with IF‐associated liver disease or hyperglycemia. The key to preserving central venous access and quality of life and maintaining health for patients with chronic IF (CIF) is education focused on prevention and prompt management of CIF complications as they arise. This education typically takes place at the time of initiation of HPN, either in the hospital setting or in the patient's home. The present manuscript describes the historical progression of HPN, prevalence and characteristics of CIF, and an in‐depth discussion of the most common catheter‐related and PN‐related complications and their management, along with a discussion of our education and training process.

Hospitalized patients are at an increased risk of malnutrition due to multiple factors including, but not limited to, acute and chronic diseases especially those affecting gastrointestinal tract, surgery, appetite, and frequent nil per os while undergoing diagnostic workup. Because of this, guidelines suggest the use of oral nutritional supplements (ONS) in hospitalized patients to reduce the risk of malnutrition and its complications. The current report aims to highlights key findings from a cross-sectional survey of 99 hospitalized patients who were at risk for or diagnosed with malnutrition and prescribed ONS. Data regarding ONS prescriber information as well as number ordered and consumed were collected. Of the 2.4 ± 1.5 supplements ordered per person each day, only 1.3 ± 1.1 were consumed, and there was 48% wastage of prescribed ONS. However, dietitian involvement was associated with significant reduction in wastage. Given the need and benefit, it is imperative for the nutrition community to further explore best practices to improve ONS consumption.

AbstractBackgroundGastrostomy tubes placed radiologically, endoscopically or surgically facilitate long‐term home enteral nutrition (HEN). Patient‐specific clinical factors may affect placement techniques, confounding direct comparisons between radiologically inserted gastrostomy (RIG) and percutaneous endoscopic gastrostomy (PEG) outcomes. This study sought to evaluate the differences in clinical outcomes in patients undergoing gastrostomy tube placement by interventional radiologists or gastroenterologists.MethodsA single‐center prospective trial randomizing patients initiating HEN to RIG or PEG was conducted between March 2018 and June 2021. Patients were followed until the time of gastrostomy removal or until 9 months after tube placement. Tracked complications included peritonitis, abscess, bleeding, bowel perforation, and tube occlusion, malposition, or damage. Periprocedural pain rating and quality of life (QoL) surveys were collected.ResultsForty‐two patients were randomized to RIG or PEG. Twenty patients underwent RIG (mean age, 63.0 ± 11.7 years; 85% male; 95% with head and neck cancer) and 22 patients underwent PEG (mean age, 66.3 ± 10.9 years; 81.8% male; 90.9% with head and neck cancer). RIG and PEG groups had 4.18 ± 5.49 and 2.80 ± 5.82 complications per 1000 HEN days, respectively (P = 0.357). The most frequent complications were tube malposition and abscess formation for the RIG and PEG groups, respectively. No major complications occurred in either group. There was no difference in the average of pain ratings in all pain inventory components across both groups. Both groups reported improvement in overall QoL after gastrostomy tube placement (P = 0.532).ConclusionRIG is noninferior to PEG regarding complication rates, pain, and QoL when compared in a prospective randomized fashion.