Abstract
Objective:
To assess the feasibility of using large language models (LLM) to develop research questions about changes to the Special Supplemental Nutrition Program for Women, Infants, and Children (WIC) food packages.
Design:
We conducted a controlled experiment using ChatGPT-4 and its plugin, MixerBox Scholarly, to generate research questions based on a section of the U.S. Department of Agriculture (USDA) summary of the final public comments on the WIC revision. Five questions weekly for 3 weeks were generated using LLM under two conditions: fed with or without relevant literature. The experiment generated ninety questions, which were evaluated using the Feasibility, Innovation, Novelty, Ethics and Relevance criteria. t tests and multivariate regression examined the difference by feeding status, artificial intelligence model, evaluator and criterion.
Setting:
The United States.
Participants:
Six WIC expert evaluators from academia, government, industry and non-profit sectors.
Results:
Five themes were identified: administrative barriers, nutrition outcomes, participant preferences, economics and other topics. Feeding and non-feeding groups had no significant differences (Coeff. = 0·03, P = 0·52). MixerBox-generated questions received significantly lower scores than ChatGPT (Coeff. = –0·11, P = 0·02). Ethics scores were significantly higher than feasibility scores (Coeff. = 0·65, P < 0·001). Significant differences were found between the evaluators (P < 0·001).
Conclusions:
The LLM applications can assist in developing research questions with acceptable qualities related to the WIC food package revisions. Future research is needed to compare the development of research questions between LLM and human researchers.
Public aspects of medicine, Nutritional diseases. Deficiency diseases
Andrea D. Dorbu, Hannah B. Waddel, Manpreet K. Chadha
et al.
ABSTRACT Food fortification can deliver essential micronutrients to populations at a large scale, thereby reducing nutritional anemia. This study aimed to review and meta‐analyze the literature on the impact of wheat flour, maize flour, rice, and oil (singly or combined) fortification on women's (10–49 years) hemoglobin and anemia. A search of 17 databases yielded 2284 results. Longitudinal, pre‐post cross‐sectional, efficacy, and effectiveness studies were included. Primary outcomes were changes in hemoglobin concentration and anemia prevalence. Studies were synthesized using arm‐based network meta‐analysis. In women who consumed fortified rice, hemoglobin mean change was 3.24 g/L (95% credibility interval (CrI) 0.9, 5.98), higher than for women in the control, with a 99.1% probability that the true mean difference was > 0. Hemoglobin was 2.08 g/L (95% CrI −0.76, 4.35) higher in women who consumed wheat flour versus control, with a 93.5% probability that the true mean difference was > 0. After rice fortification, anemia prevalence in women was 1.38 percentage points (95% CrI −106.6, 99.2) lower than for control women, with a 51.2% probability that the true mean difference was < 0. Wheat flour fortification decreased anemia prevalence by 1.84 percentage points (95% CrI −93.4, 92.4) with a 52.72% probability that the true mean difference was < 0. The treatment effects of fortified maize flour and fortified oil could not be calculated due to the absence of control arms compared to the intervention arms. Fortified rice and wheat flour appear likely to modestly increase hemoglobin and may also reduce anemia in women of childbearing age.
Tharaka Fonseka, Buddhi Wijenayake, Athulya Ratnayake
et al.
Understanding the relationship between population dynamics and disease-specific mortality is central to evidence-based health policy. This study introduces two novel metrics, PoPDivergence and PoPStat, one to quantify the difference between population pyramids and the other to assess the strength and nature of their association with the mortality of a given disease. PoPDivergence, based on Kullback-Leibler divergence, measures deviations between a countrys population pyramid and a reference pyramid. PoPStat is the correlation between these deviations and the log form of disease-specific mortality rates. The reference population is selected by a brute-force optimization that maximizes this correlation. Utilizing mortality data from the Global Burden of Disease 2021 and population statistics from the United Nations, we applied these metrics to 371 diseases across 204 countries. Results reveal that PoPStat outperforms traditional indicators such as median age, GDP per capita, and Human Development Index in explaining the mortality of most diseases. Noncommunicable diseases (NCDs) like neurological disorders and cancers, communicable diseases (CDs) like neglected tropical diseases, and maternal and neonatal diseases were tightly bound to the underlying demographic attributes whereas NCDs like diabetes, CDs like respiratory infections and injuries including self-harm and interpersonal violence were weakly associated with population pyramid shapes. Notably, except for diabetes, the NCD mortality burden was shared by constrictive population pyramids, while mortality of communicable diseases, maternal and neonatal causes and injuries were largely borne by expansive pyramids. Therefore, PoPStat provides insights into demographic determinants of health and empirical support for models on epidemiological transition. Code and scripts: https://github.com/Buddhi19/DevisingPoPStat.git
With the advancement of internet communication and telemedicine, people are increasingly turning to the web for various healthcare activities. With an ever-increasing number of diseases and symptoms, diagnosing patients becomes challenging. In this work, we build a diagnosis assistant to assist doctors, which identifies diseases based on patient-doctor interaction. During diagnosis, doctors utilize both symptomatology knowledge and diagnostic experience to identify diseases accurately and efficiently. Inspired by this, we investigate the role of medical knowledge in disease diagnosis through doctor-patient interaction. We propose a two-channel, knowledge-infused, discourse-aware disease diagnosis model (KI-DDI), where the first channel encodes patient-doctor communication using a transformer-based encoder, while the other creates an embedding of symptom-disease using a graph attention network (GAT). In the next stage, the conversation and knowledge graph embeddings are infused together and fed to a deep neural network for disease identification. Furthermore, we first develop an empathetic conversational medical corpus comprising conversations between patients and doctors, annotated with intent and symptoms information. The proposed model demonstrates a significant improvement over the existing state-of-the-art models, establishing the crucial roles of (a) a doctor's effort for additional symptom extraction (in addition to patient self-report) and (b) infusing medical knowledge in identifying diseases effectively. Many times, patients also show their medical conditions, which acts as crucial evidence in diagnosis. Therefore, integrating visual sensory information would represent an effective avenue for enhancing the capabilities of diagnostic assistants.
The intricate relationship between genetic variation and human diseases has been a focal point of medical research, evidenced by the identification of risk genes regarding specific diseases. The advent of advanced genome sequencing techniques has significantly improved the efficiency and cost-effectiveness of detecting these genetic markers, playing a crucial role in disease diagnosis and forming the basis for clinical decision-making and early risk assessment. To overcome the limitations of existing databases that record disease-gene associations from existing literature, which often lack real-time updates, we propose a novel framework employing Large Language Models (LLMs) for the discovery of diseases associated with specific genes. This framework aims to automate the labor-intensive process of sifting through medical literature for evidence linking genetic variations to diseases, thereby enhancing the efficiency of disease identification. Our approach involves using LLMs to conduct literature searches, summarize relevant findings, and pinpoint diseases related to specific genes. This paper details the development and application of our LLM-powered framework, demonstrating its potential in streamlining the complex process of literature retrieval and summarization to identify diseases associated with specific genetic variations.
Despite the impressive capabilities of Large Language Models (LLMs) in general medical domains, questions remain about their performance in diagnosing rare diseases. To answer this question, we aim to assess the diagnostic performance of LLMs in rare diseases, and explore methods to enhance their effectiveness in this area. In this work, we introduce a rare disease question-answering (ReDis-QA) dataset to evaluate the performance of LLMs in diagnosing rare diseases. Specifically, we collected 1360 high-quality question-answer pairs within the ReDis-QA dataset, covering 205 rare diseases. Additionally, we annotated meta-data for each question, facilitating the extraction of subsets specific to any given disease and its property. Based on the ReDis-QA dataset, we benchmarked several open-source LLMs, revealing that diagnosing rare diseases remains a significant challenge for these models. To facilitate retrieval augmentation generation for rare disease diagnosis, we collect the first rare diseases corpus (ReCOP), sourced from the National Organization for Rare Disorders (NORD) database. Specifically, we split the report of each rare disease into multiple chunks, each representing a different property of the disease, including their overview, symptoms, causes, effects, related disorders, diagnosis, and standard therapies. This structure ensures that the information within each chunk aligns consistently with a question. Experiment results demonstrate that ReCOP can effectively improve the accuracy of LLMs on the ReDis-QA dataset by an average of 8%. Moreover, it significantly guides LLMs to generate trustworthy answers and explanations that can be traced back to existing literature.
Rare diseases, despite their low individual incidence, collectively impact around 300 million people worldwide due to the vast number of diseases. The involvement of multiple organs and systems, and the shortage of specialized doctors with relevant experience, make diagnosing and treating rare diseases more challenging than common diseases. Recently, agents powered by large language models (LLMs) have demonstrated notable applications across various domains. In the medical field, some agent methods have outperformed direct prompts in question-answering tasks from medical examinations. However, current agent frameworks are not well-adapted to real-world clinical scenarios, especially those involving the complex demands of rare diseases. To bridge this gap, we introduce RareAgents, the first LLM-driven multi-disciplinary team decision-support tool designed specifically for the complex clinical context of rare diseases. RareAgents integrates advanced Multidisciplinary Team (MDT) coordination, memory mechanisms, and medical tools utilization, leveraging Llama-3.1-8B/70B as the base model. Experimental results show that RareAgents outperforms state-of-the-art domain-specific models, GPT-4o, and current agent frameworks in diagnosis and treatment for rare diseases. Furthermore, we contribute a novel rare disease dataset, MIMIC-IV-Ext-Rare, to facilitate further research in this field.
Abstract Background Randomized controlled trials have found that once-weekly insulin resulted in greater glycemic control compared to once-daily insulin in patients with type 2 diabetes. However, no direct comparisons have been made between different types of once-weekly insulin thus far. This systematic review and network meta-analysis aimed to evaluate the effect of the two most advanced once-weekly insulin analogues, namely insulin icodec and insulin Fc, in patients with type 2 diabetes. Methods We conducted a thorough search in the databases PubMed, Embase, and the Cochrane Central Register of Controlled Trials. The search included articles published from the beginning to October 10, 2023, with no language limitations. Our aim was to conduct a systematic review of randomized controlled trials that investigated the effectiveness and safety of once-weekly insulin in individuals with type 2 diabetes. Our primary outcome was to evaluate excellent glycemic control, defined as patients achieving glycated hemoglobin levels below 7%. Results We identified a total of 7 trials involving 2829 patients. The results showed that once-weekly insulin icodec is more effective than once-weekly insulin Fc (RR 1.59 [95% CI 1.08–2.38]), once-daily degludec (RR 1.43 [95% CI 1.14–1.83]), and once-daily glargine (RR 1.15 [95% CI 1.00-1.41]). Moreover, the incidence of severe hypoglycemia was lower with once-weekly insulin icodec compared to once-daily degludec (RR 0.00016 [95% CI 0 to 0.41]). However, no significant difference in the incidence of severe hypoglycemia was observed between once-weekly insulin icodec and once-daily glargine (RR 0.39 [95% CI 0.03 to 4.83]). Conclusions In patients with type 2 diabetes, once-weekly insulin icodec achieved superior glycemic control compared to once-weekly insulin Fc, with no significant difference in the occurrence of hypoglycemia. The ranking probability results have shown that one weekly icodec seems to be the preferred option in patients with type 2 diabetes. Trial registration PROSPERO Identifier: CRD42023470894.
Background: In Indonesia, Acute respiratory infection (ARI) and diarrhea-related morbidity and mortality in children less than five years old still remain a significant public health concern. In this relation, energy, protein, zinc, and vitamins C, B, D, E, and A are essential nutrients to mitigate morbidity and mortality. Vitamin A was shown to play a crucial role in human development, growth, and immune function that can protect infants against infectious diseases such as ARI and diarrhea. So this study aimed to compare the effect of beef
liver and vitamin A supplementation for breastfeeding mothers on the incidence of ARI and diarrhea in infants.
Methods: In a randomized control trial design, 40 participants aged 20-35 years were allocated into two groups of beef liver and vitamin A supplementations. The beef liver supplementation group received eight servings during two months postpartum, or no later than the 7th day after giving birth; while the vitamin A supplementation group received two vitamin A capsules no later than the 7th day postpartum.
Results: The incidence of ARI significantly differed, while there was no significant difference in incidence of infant diarrhea between the two groups.
Conclusion: In breastfeeding mothers, administering beef liver (75 grams/ day equivalent to 402,000 IU) could reduce the frequency of ARI and infant diarrhea more effectively than supplementation with two vitamin A capsules (equivalent to 400,000 IU). There was no difference in morbidity of infant diarrhea for mothers who received two vitamin A capsules.
M. Yogesh, Jay Nagda, Nirmalkumar Shaileshbhai Patel
et al.
Abstract Background Hypertension and muscle strength are known to be associated; however, identifying simple clinical indicators of this relationship is challenging. Relative muscle strength (RMS), defined as strength per unit muscle mass, has been proposed as a potential indicator, but its association with hypertension is unclear. This study aimed to estimate the prevalence of hypertension and determine its association with RMS in an adult Indian population attending a tertiary care center in Gujarat. Methods This hospital-based cross-sectional study included 430 adults aged 18 years and older who were admitted to outpatient medicine clinics between January and October 2023. Grip strength and appendicular lean muscle mass (ALM), estimated using a validated formula, were measured. The RMS was calculated as grip strength/ALM. Hypertension was defined using standard criteria. Logistic regression was used to analyze the association between RMS (analyzed continuously and categorically in tertiles) and hypertension, adjusting for confounders. A p value of < 0.05 was considered significant. Results The prevalence of prehypertension and hypertension was 187 (43%) and 96 (23%), respectively. Compared to participants in the low RMS tertile (0.00–2.45 kg/kg ALM), those in the high tertile (3.79–6.12 kg/kg ALM) had 26% lower odds of hypertension (OR 0.74, 95% CI 0.59–0.89) and 33% lower odds of prehypertension (OR 0.67, 95% CI 0.49–0.91) after adjusting for confounders. The RMS also showed strong negative correlations with systolic and diastolic blood pressure (r = − 0.559 and − 0.418, respectively; p < 0.001). Conclusion Increased RMS was significantly protective against prehypertension and hypertension. These findings highlight the potential importance of muscle quality, beyond muscle mass, in blood pressure regulation.
Nutritional diseases. Deficiency diseases, Public aspects of medicine
Jeffery L Heileson, Michael J Macartney, Nora L Watson
et al.
Summary: Background: Accumulating evidence has highlighted the acute and chronic impact of repetitive subconcussive head impacts (rSHIs) in contact sports. Neurofilament-light (Nf-L), a brain-derived biomarker of neuroaxonal injury, elevates in concert with rSHI. Recently, long-chain ω-3 polyunsaturated fatty acids (LC ω-3 PUFAs) supplementation has been suggested to mitigate brain injury from rSHI as reflected by attenuation of Nf-L concentrations within contact sport athletes. Objective: Using a systematic review with a meta-analysis, we aimed to determine the effect of LC ω-3 PUFA supplementation on Nf-L concentrations in athletes routinely exposed to rSHI. Methods: Electronic databases (PubMed and CINAHL) were searched from inception through January 2024. One-stage meta-analysis of individual participant-level data was used to detect changes in Nf-L concentrations between LC ω-3 PUFA and control/placebo (PL) groups from baseline to midseason (MS) and postseason (PS). Least square means (±SE) for Nf-L change from baseline were compared by treatment group for MS/PS using contrast t tests. Significance was set a priori at adjusted P ≤ 0.05. Results: Of 460 records identified, 3 studies in collegiate American football players (n = 179; LC ω-3 PUFA = 105, PL = 71) were included in the meta-analysis. Compared with PL, the change in Nf-L concentrations was statistically similar at MS [mean difference (MD) = –1.66 ± 0.82 pg·mL–1, adjusted P = 0.09] and significantly lower at PS (MD = –2.23 ± 0.83 pg·mL–1, adjusted P = 0.02) in athletes following LC ω-3 PUFA supplementation. Conclusions: Our findings demonstrate preliminary support for the prophylactic administration of LC ω-3 PUFA in contact sport athletes exposed to rSHI; however, further research is required to determine the effective dosage required.This trial was registered at OSF (DOI: https://doi.org/10.17605/OSF.IO/EY5QW).
Nutrition. Foods and food supply, Nutritional diseases. Deficiency diseases
Nisar Ahmed, Hafiz Muhammad Shahzad Asif, Gulshan Saleem
et al.
Crop diseases are a major threat to food security and their rapid identification is important to prevent yield loss. Swift identification of these diseases are difficult due to the lack of necessary infrastructure. Recent advances in computer vision and increasing penetration of smartphones have paved the way for smartphone-assisted disease identification. Most of the plant diseases leave particular artifacts on the foliar structure of the plant. This study was conducted in 2020 at Department of Computer Science and Engineering, University of Engineering and Technology, Lahore, Pakistan to check leaf-based plant disease identification. This study provided a deep neural network-based solution to foliar disease identification and incorporated image quality assessment to select the image of the required quality to perform identification and named it Agricultural Pathologist (Agro Path). The captured image by a novice photographer may contain noise, lack of structure, and blur which result in a failed or inaccurate diagnosis. Moreover, AgroPath model had 99.42% accuracy for foliar disease identification. The proposed addition can be especially useful for application of foliar disease identification in the field of agriculture.
Jabir Al Nahian, Abu Kaisar Mohammad Masum, Sheikh Abujar
et al.
In this era, the moment has arrived to move away from disease as the primary emphasis of medical treatment. Although impressive, the multiple techniques that have been developed to detect the diseases. In this time, there are some types of diseases COVID-19, normal flue, migraine, lung disease, heart disease, kidney disease, diabetics, stomach disease, gastric, bone disease, autism are the very common diseases. In this analysis, we analyze disease symptoms and have done disease predictions based on their symptoms. We studied a range of symptoms and took a survey from people in order to complete the task. Several classification algorithms have been employed to train the model. Furthermore, performance evaluation matrices are used to measure the model's performance. Finally, we discovered that the part classifier surpasses the others.
Petchiammal A, Briskline Kiruba S, D. Murugan
et al.
One of the critical biotic stress factors paddy farmers face is diseases caused by bacteria, fungi, and other organisms. These diseases affect plants' health severely and lead to significant crop loss. Most of these diseases can be identified by regularly observing the leaves and stems under expert supervision. In a country with vast agricultural regions and limited crop protection experts, manual identification of paddy diseases is challenging. Thus, to add a solution to this problem, it is necessary to automate the disease identification process and provide easily accessible decision support tools to enable effective crop protection measures. However, the lack of availability of public datasets with detailed disease information limits the practical implementation of accurate disease detection systems. This paper presents \emph{Paddy Doctor}, a visual image dataset for identifying paddy diseases. Our dataset contains 16,225 annotated paddy leaf images across 13 classes (12 diseases and normal leaf). We benchmarked the \emph{Paddy Doctor} dataset using a Convolutional Neural Network (CNN) and four transfer learning based models (VGG16, MobileNet, Xception, and ResNet34). The experimental results showed that ResNet34 achieved the highest F1-score of 97.50%. We release our dataset and reproducible code in the open source for community use.
Early and precise diagnosis of diseases in plants can help to develop an early treatment technique. Plant diseases degrade both the quantity and quality of crops, thus posing a threat to food security and resulting in huge economic losses. Traditionally identification is performed manually, which is inaccurate, time-consuming, and expensive. This paper presents a simple and efficient model to detect grapes leaf diseases using transfer learning. A pre-trained deep convolutional neural network is used as a feature extractor and random forest as a classifier. The performance of the model is interpreted in terms of accuracy, precision, recall, and f1 score. Total 1003 images of four different classes are used and 91.66% accuracy is obtained.