Varayil, Jithinraj Edakkanambeth

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.

Primary care is a language-intensive environment where clinicians frequently synthesize, document, and communicate large amounts of information. Given the amount of information in primary care, large language models (LLMs) have emerged as tools to support primary care clinician workflows, aiming to reduce administrative burden and augment patient care. LLMs are artificial intelligence tools that can generate text and assist with chart summarization, message drafting, and clinical decision support. However, because LLMs are probabilistic, identical inputs may yield inconsistent responses. The LLMs output can be significantly improved through prompt engineering. Prompt engineering is the intentional design of text entered into the LLM to help produce better LLM results. Prompting is best approached as an iterative process where a clinician defines the task, the LLM generates output, and the clinician critically reviews and refines the results. Low-quality prompts are often vague and produce generic or misleading responses. High-quality prompts are specific, context-rich, and well-structured. Using structured prompting frameworks can improve the LLMs response. Including core elements, such as the LLMs role, the clinical context, the requested task, and the desired output formatting, can help improve the LLMs response by providing situational background and framing response formatting. Additional frameworks, such as Ask-Context-Expectation and PICO+O, can be utilized for specific patient circumstances and cases. However, despite their promise, LLMs have important limitations. They may generate inaccurate or hallucinated information and produce inconsistent results. Given these limitations, LLMs should not be viewed as knowledge authorities but rather as cognitive assistants. Thoughtful prompt design can help reduce these limitations and improve response accuracy, always keeping in mind that LLMs should not replace human judgment or clinical reasoning. As LLMs continue to be integrated into primary care, prompt engineering will become an increasingly important clinical skill. Careful prompt design and critical appraisal of LLM responses will be key to maintaining excellent patient care in the AI era.

Objective To evaluate patient satisfaction with the experience of using an autonomous wheelchair to transport patients in a large outpatient clinical environment. Methods The autonomous wheelchair pilot was approved as a feasibility pilot by the institutional committees and deemed a quality improvement project by the Institutional Review Board (IRB). A total of 409 adult patients using an autonomous wheelchair at a large academic medical center who volunteered to complete a paper survey were included. The survey was administered immediately after autonomous wheelchair use, using a cross-sectional, anonymous survey, between 15 Oct 2025 and 14 Jan 2026. Of 409 completed surveys, six were excluded because participants did not identify their endpoint for stratification purposes. Descriptive analysis included frequencies and percentages of responses. Results No collisions or adverse events were observed during the pilot, and the system operated reliably within the predefined routes. Most survey respondents were first-time users (335/402 [83.3%]). A majority reported they would use the autonomous wheelchair again (341/395 [86.3%]) and would recommend it to others (364/397 [91.7%]). Overall, the experience was rated better than expected by 293 of 393 participants (74.6%). When given a choice, 271 of 379 respondents (71.5%) preferred the autonomous wheelchair over a staff-operated wheelchair. Conclusion These findings suggest that autonomous wheelchairs are feasible and acceptable to patients in a controlled outpatient setting and support continued piloting and prospective evaluation.

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 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.

Peri- and postmenopausal women often experience unexplained weight gain despite maintaining consistent dietary and lifestyle habits. While the biological mechanisms underlying this phenomenon remain poorly understood, physiological and pathophysiological changes during the menopausal transition are likely contributors. Proteomic profiling holds potential for revealing key molecular pathways involved in the pathogenesis of obesity in this population. This review synthesizes current evidence on proteomic alterations linked to overweight and obesity in peri- and postmenopausal women. A structured literature search was performed across Ovid MEDLINE®, EMBASE, the Cochrane Library, and Scopus for studies published between October 2010 and March 2025. Eligible studies included original research involving overweight or obese peri- or postmenopausal women that reported proteomic data. Extracted information encompassed study design, participant characteristics, sample types, and proteomic findings. Identified proteins were cross-referenced with a prior review of consistently dysregulated proteins in obesity. Five studies met the inclusion criteria, collectively revealing consistent proteomic patterns associated with inflammation, metabolic dysfunction, and endothelial dysregulation. These included C-reactive protein, Tissue necrotic factor-alpha, interleukins, adiponectin, and endocan. Notably, one study demonstrated that weight loss led to reductions in IL-6, IL-1 receptor antagonist, and CRP, suggesting that obesity-related inflammation may be at least partially reversible. This review provides preliminary evidence linking chronic inflammation, metabolic dysregulation, and vascular stress to obesity in peri- and postmenopausal women. These proteomic signatures enhance understanding of menopausal weight gain and highlight the potential of proteomics to guide personalized interventions. However, larger, well-designed prospective studies are needed to confirm these associations and clarify causal pathways.

Purpose of review This review aims to synthesize current evidence on the expanding role of glucagon-like peptide-1 (GLP-1) receptor agonists (RAs) beyond glycemic control, particularly in the context of critical illness. With growing recognition of their anti-inflammatory, immunomodulatory, and organ-protective properties, GLP-1RAs show promise in managing complications such as sepsis, acute respiratory distress syndrome (ARDS), acute kidney injury, and multiorgan dysfunction. This review explores their mechanisms across vital systems – including cardiovascular, pulmonary, renal, hepatic, neuropsychiatric, and gut-lung-microbiome axes – highlighting preclinical and clinical data. By consolidating emerging findings, this review aims to inform future translational research and support the integration of GLP-1RAs into critical care strategies. Recent findings Recent evidence highlights GLP-1RAs as promising adjuncts in critical illness due to their multiorgan protective effects. In cardiovascular systems, GLP-1RAs improve endothelial function, reduce ischemia-reperfusion injury, and modulate autonomic tone. In the CNS, they provide neuroprotection by reducing neuroinflammation and pyroptosis. In the lungs, they attenuate ARDS by decreasing cytokine production, enhancing surfactant secretion, and restoring alveolar-capillary integrity. Renally, they reduce acute injury and preserve filtration function. In the gut, GLP-1RAs modulate the microbiome, enhance barrier integrity, and lower systemic inflammation via the gut-lung axis. Additionally, they reduce hepatic inflammation and support pancreatic beta-cell survival, improving insulin sensitivity and metabolic stability in critical care. Summary GLP-1 receptor agonists hold promise as multiorgan protective agents in critical illness, offering benefits beyond glucose control. Their anti-inflammatory, metabolic, and vaso-protective properties may be harnessed to prevent or attenuate organ failure, support recovery, and improve long-term outcomes in critically ill patients. Further clinical trials are warranted to define their safety, efficacy, and optimal application across ICU populations.

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.

AbstractBackgroundAvascular necrosis (AVN) is a known adverse event associated with corticosteroid (CS) usage. Inflammatory bowel disease (IBD) is often treated with a CS for induction of remission. We sought to describe clinical features and outcomes of IBD patients with AVN.MethodsIn this retrospective, single-center, case-control study, patients with IBD who had a diagnosis of osteonecrosis, aseptic necrosis, or AVN from 1976 to 2009 were included, and each was matched with up to 2 controls (IBD but no AVN) on age, sex, IBD subtype, geographic area of residence, and date of IBD diagnosis. We abstracted risk factor data from the medical records. Conditional logistic regression was performed accounting for minor differences in age and date of first IBD visit to assess the relationship between putative risk factors and AVN, expressed as odds ratio and 95% confidence interval.ResultsEighty-five patients were diagnosed with IBD-AVN and were matched with 163 controls. The mean age at AVN diagnosis was 47.5 years. AVN was diagnosed a median of 12.2 years after IBD diagnosis, and the control group was followed for a median of 15 years after IBD diagnosis to ensure that they did not have AVN. Ten percent of patients with AVN did not have any CS exposure. History of arthropathy or estrogen use in Crohn’s disease and use of CS, osteoporosis, and history of arthropathy in ulcerative colitis were significantly associated with AVN.ConclusionsMost patients with IBD-AVN had multifocal involvement. Most had received CS, but many patients had other risk factors including arthropathy.

Abstract Background We sought to estimate the incidence of home parenteral nutrition (HPN) use in a population-based cohort of patients with Crohn disease (CD), and to assess clinical outcomes and complications associated with HPN. Methods We used the Rochester Epidemiology Project (REP) to identify residents of Olmsted County, who were diagnosed with CD between 1970 and 2011, and required HPN. Results Fourteen out of 429 patients (3.3%) with CD received HPN (86% female). Eleven patients (79%) had moderate–severe CD and 12 patients (86%) had fistulizing disease. Thirteen patients (93%) underwent surgery, primarily due to obstruction. Among CD incidence cases, the cumulative incidence of HPN from the date of CD diagnosis was 0% at 1 year, 0.5% at 5 years, 0.8% at 10 years, and 2.4% at 20 years. Indications for HPN included short bowel syndrome in 64%, malnutrition in 29%, and bowel rest in 21%. The median duration of HPN was 2.5 years. There was an average weight gain of 1.2 kg at 6 months, an average weight loss of 1.4 kg at 1 year, and a further weight loss of 2.2 kg at 2 years from the start of HPN. Patients were hospitalized a mean of 5 times after the start of HPN, mainly due to catheter-related bloodstream infections and thrombosis. Conclusions Less than 4% of patients with CD need HPN. Most have moderate to severe disease with short bowel syndrome or malnutrition. Possible reasons for the patients’ weight loss could be noncompliance, and increased metabolic needs because of active disease.