ABSTRACT: Objectives: To evaluate the proportion of persistent inflammatory refractory rheumatoid arthritis (PIRRA) and noninflammatory refractory rheumatoid arthritis (NIRRA) of difficult-to-treat rheumatoid arthritis (D2T-RA) using musculoskeletal ultrasound (MSUS) and to compare clinical characteristics across PIRRA, NIRRA, and disease-controlled refractory rheumatoid arthritis (RA) subgroups. Methods: A retrospective single-centre cohort study identified patients (May 2021 to December 2022) with inadequate response to ≥2 different mechanism of action biologic/targeted synthetic disease-modifying antirheumatic drugs (b/tsDMARDs) and disease activity score in 28 joints-erythrocyte sedimentation rate (ESR) of >3.2 as European Alliance of Associations for Rheumatology-defined D2T-RA. MSUS classified this group into PIRRA (power Doppler present) or NIRRA (no power Doppler synovitis). A comparator group of controlled refractory RA (≥2 b/tsDMARD failures but sustained low disease activity) was also assessed. Clinical data were collected and analysed. Results: Of the 85 patients, 45 had D2T-RA (25 [56%] PIRRA; 20 [44%] NIRRA), and 40 had controlled refractory RA. PIRRA subgroup had higher C-reactive protein (CRP), but NIRRA subgroup higher ESR. Fibromyalgia was more prevalent in PIRRA and NIRRA than that in controlled refractory RA (48%, 40%, and 17.5%, respectively; P = .02). Nearly half of patients in the controlled refractory group (17/37 [46%]) had subclinical synovitis on MSUS. Rates of radiographic erosions were similar across PIRRA, NIRRA, and controlled refractory groups. Conclusions: MSUS-based stratification of D2T-RA into PIRRA and NIRRA reveals distinct associations to CRP and ESR and comparable chronic pain. Subclinical inflammation is present even in ostensibly controlled disease, suggesting risk of re-falling into an active D2T-RA state. Identifying such subphenotypes can inform on monitoring strategies, support mechanistic investigation, and enable more targeted treatments to improve outcomes of D2T-RA.
Abstract Background The hexapod external fixator (HEF) allows for precise three-dimensional reduction of tibial fractures, but its therapeutic efficacy is highly dependent on the accuracy of postoperative mounting parameters. Currently, X-ray and computed tomography (CT) are the primary imaging modalities, each with distinct trade-offs between accuracy and efficiency in clinical use. This study compares the accuracy of postoperative X-ray and CT in measuring mounting parameters for HEF in tibial fracture treatment and assesses the associated clinical outcomes. Methods This single-center retrospective cohort study included 71 patients with tibial fractures treated with HEFs at our institution between June 2021 and June 2023. The cohort consisted of 40 males and 31 females, aged 30 to 60 years. Patients were divided into two groups based on the imaging method used for postoperative measurement of the hexapod fixator’s mounting parameters: the X-ray group (n = 34, using 2D measurements from standard anteroposterior (AP) and lateral radiographs) and the CT group (n = 37, using CT scans and 3D reconstruction). Baseline characteristics—including age, sex, mechanism of injury, AO/OTA fracture classification, and Gustilo-Anderson classification—were comparable between groups (all P > 0.05). Primary outcomes were the number of electronic prescriptions, time to fracture reduction (from the first postoperative electronic correction prescription to radiographic confirmation of satisfactory reduction), and measurement operation time. Secondary outcomes included final radiological outcome, time to fracture union, and Johner-Wruhs score at final follow-up. Results All 71 patients were followed up for a mean of 24.5 months (range: 18–36 months). The number of electronic prescriptions was lower in the CT group (median [IQR]: 1 [1]-[1]) than in the X-ray group (2 [1-2]). Time to fracture reduction was shorter in the CT group (3.3 ± 0.6 days vs. 4.8 ± 0.8 days). Measurement operation time was shorter in the X-ray group (12.9 ± 2.1 min vs. 14.1 ± 1.5 min). All these between-group differences were statistically significant. In the CT group, 81.1% (30/37) achieved satisfactory reduction with a single prescription, significantly higher than the 55.9% (19/34) in the X-ray group (P < 0.05). No statistically significant group differences were seen in time to fracture union (X-ray: 26.1 ± 3.2 weeks, CT: 25.7 ± 2.3 weeks), final radiological outcomes (displacement and angulation on AP and lateral views), or Johner-Wruhs scores (excellent and good rate: 82.4% for X-ray, 89.2% for CT; P > 0.05). No severe vascular or nerve injuries occurred in either group. Clinical trial number Not applicable. Conclusion Both X-ray and CT can successfully guide hexapod fixator correction for tibial fractures. CT measurement was associated with greater efficiency in the correction process, requiring fewer adjustments and less time to achieve reduction. However, this did not lead to differences in final radiographic or functional outcomes. The decision to use CT should therefore balance its potential for streamlining the early correction phase against considerations of cost, radiation exposure, and local resources. For many routine cases, X-ray-based measurement remains a robust and effective standard approach.
Olivia K. Ottone, Jorge J. Mundo, Boahen N. Kwakye
et al.
ABSTRACTDespite the high prevalence of age‐dependent intervertebral disc calcification, there is a glaring lack of treatment options for this debilitating pathology. We investigated the efficacy of long‐term oral K3Citrate supplementation in ameliorating disc calcification in LG/J mice, a model of spontaneous age‐associated disc calcification. K3Citrate reduced the incidence of disc calcification without affecting the vertebral bone structure, knee calcification, plasma chemistry, or locomotion in LG/J mice. Notably, a positive effect on grip strength was evident in treated mice. FTIR spectroscopy of the persisting calcified nodules indicated K3Citrate did not alter the mineral composition. Mechanistically, activation of an endochondral differentiation in the cartilaginous endplates and nucleus pulposus (NP) compartment contributed to LG/J disc calcification. Importantly, K3Citrate reduced calcification incidence by Ca2+ chelation throughout the disc while exhibiting a differential effect on NP and endplate cell differentiation. In the NP compartment, K3Citrate reduced the NP cell acquisition of a hypertrophic chondrocytic fate, but the pathologic endochondral program was unimpacted in the endplates. Overall, this study for the first time shows the therapeutic potential of oral K3Citrate as a systemic intervention strategy to ameliorate disc calcification.
Tuhina Neogi, Maureen Dubreuil, Christine Peloquin
et al.
ObjectiveThe objective of this study was to assess the relation of physical therapy (PT) timing, dose, and type with risk of future intra‐articular therapy use in people with knee osteoarthritis (OA) who receive PT.MethodsWe used data from a deidentified claims database (Optum Labs Data Warehouse) from American adults with incident knee OA referred for PT within the first year of their knee OA diagnosis. We categorized people as having previously had intra‐articular therapies or not. We examined the association of timing of PT initiation, number of PT sessions, and type of PT (predominantly active or passive) with intra‐articular therapy use over a period of one year following the first year of diagnosis.ResultsOf the 67,245 individuals with knee OA (age 61.5 ± 11 years, 61% female, 10% Black, 6% Hispanic), 34,804 and 32,441 did and did not have prior intra‐articular therapies, respectively. Among those who had prior intra‐articular therapies, initiating PT at 9 to 12 months post diagnosis was associated with an adjusted risk ratio of 1.44 for future intra‐articular therapy (95% confidence interval 1.35–1.55) compared with those who initiated within a month. For both groups, ≥13 PT sessions was associated with a 10% and 12% lower risk, respectively, compared with 1 to 5 sessions. Active PT was not related to lower risk compared to passive PT interventions.ConclusionInitiating PT earlier and more than 12 PT sessions were significantly associated with lower risk of future intra‐articular therapy use in people with newly diagnosed knee OA.image
Eric J. Roseen, André Bussières, Rocky Reichman
et al.
Abstract Introduction Limited adoption of first line treatments for low back pain (LBP) in primary care settings may contribute to an overreliance on pain medications by primary care providers (PCPs). While chiropractic care typically includes recommended nonpharmacologic approaches (e.g., manual therapy, exercise instruction, advice on self-care), implementation strategies to increase adoption of chiropractic care for LBP in primary care clinics are understudied, particularly in underserved communities. Methods We will use a stepped-wedge cluster randomized controlled pilot trial design to evaluate the feasibility of a multi-level implementation strategy to increase adoption of chiropractic care for LBP in primary care clinics at community health centers. Key barriers and facilitators identified by site champions and other key stakeholders will help us to develop and tailor implementation strategies including educational materials and meetings, developing a network of local chiropractors, and modifying the electronic health record to facilitate referrals. Three primary care clinics will be randomized to receive the implementation strategy first, second, or third over a fourteen-month study period. At our first clinic, we will have a four-month pre-implementation period, a two-month implementation deployment period, and a subsequent eight-month follow-up period. We will stagger the start of our implementation strategy, beginning in a new clinic every two months. We will evaluate the proportion of patients with LBP who receive a referral to chiropractic care in the first 21 days after their index visit with PCP. We will also evaluate adoption of other guideline concordant care (e.g., other nonpharmacologic treatments) and non-guideline concordant care (e.g., opioids, imaging) over the study period. Discussion LBP is currently the leading cause of disability worldwide. While there are several treatment options available for individuals with LBP, patients in underserved populations do not often access recommended nonpharmacologic treatment options such as chiropractic care. The results from this study will inform the development of practical implementation strategies that may improve access to chiropractic care for LBP in the primary care context. Furthermore, results may also inform policy changes needed to expand access to chiropractic care in underserved communities. Clintrials.gov NCT# NCT06104605.
Chiropractic, Diseases of the musculoskeletal system
Abstract Background Thoracic hyperkyphosis (HK), common in older adults, has been linked to impairments in physical function, mobility, balance, gait, and falls. Our pilot study used a novel 4-week manual therapy and exercise intervention for HK and showed improved posture and function. This secondary analysis aims to explore 1) the changes in gait parameters after a novel intervention for HK, 2) the correlations between posture and gait variables at baseline, and 3) pre- to post intervention. Methods This secondary analysis uses data from a quasi-experimental, single group pilot study. Participants with HK underwent pre- and post intervention measurements in posture, function, and unique to this secondary analysis, gait parametrics of velocity (V), step length (SL), double limb support (DLS), and step width (SW) using the GAITRite® electronic walkway. Paired t-tests compared pre- and post intervention gait parameters. Pearson correlation coefficients were utilized to investigate correlations between all variables at baseline and in pre- and post intervention change values. Results Fourteen women and 8 men (aged 65.9 years ±9.2; range 52 - 90) completed 12 treatments (3 times/week for 4-weeks). Statistically significant improvement (p≤.001) occurred pre- to post for postural measures: height (M=0.73cm ±0.54), Kyphotic index (-2.41 ±2.96), Block (-1.17cm ±1.22), Acromion to table (ATT) (-1.85cm ±1.42), and 3 gait measures: V (M=0.087m/s ±0.09), SL (2.34cm ±2.55), and DLS (- 0.031sec ±0.04). SW improvement was not statistically significant. Block and ATT measures were moderately correlated with V, SL, SW (Block only), and DLS (ATT only) at baseline. Strong correlations were found among V, SL, and DLS at baseline and in pre- to post change scores, but no correlation between change scores of posture and gait. Conclusions This study shows that a clinically practical 4-week PT intervention may benefit older adults with HK by demonstrating improved posture and gait parameters. Further research is warranted. Trial registration This study was retrospectively registered on 16/09/2019 under ClinicalTrials.gov Identifier: NCT04114331.
Image segmentation plays a vital role in the medical field by isolating organs or regions of interest from surrounding areas. Traditionally, segmentation models are trained on a specific organ or a disease, limiting their ability to handle other organs and diseases. At present, few advanced models can perform multi-organ or multi-disease segmentation, offering greater flexibility. Also, recently, prompt-based image segmentation has gained attention as a more flexible approach. It allows models to segment areas based on user-provided prompts. Despite these advances, there has been no dedicated work on prompt-based interactive multi-organ and multi-disease segmentation, especially for Chest X-rays. This work presents two main contributions: first, generating doodle prompts by medical experts of a collection of datasets from multiple sources with 23 classes, including 6 organs and 17 diseases, specifically designed for prompt-based Chest X-ray segmentation. Second, we introduce Prompt2SegCXR, a lightweight model for accurately segmenting multiple organs and diseases from Chest X-rays. The model incorporates multi-stage feature fusion, enabling it to combine features from various network layers for better spatial and semantic understanding, enhancing segmentation accuracy. Compared to existing pre-trained models for prompt-based image segmentation, our model scores well, providing a reliable solution for segmenting Chest X-rays based on user prompts.
The temporomandibular joint (TMJ) involvement is an underestimated feature of juvenile idiopathic arthritis (JIA) since it is usually asymptomatic at presentation for an undeterminable time. Late diagnosis of TMJ arthritis in JIA patients leads to delayed treatment, long-term orofacial disturbances, and impaired health-related quality of life (HRQOL). Therefore, the detection of TMJ involvement is fundamental and represents a challenge. This perspective presents state-of-the-art current initiatives and available tools for early diagnosis of TMJ arthritis in children with JIA. Standardized protocols and multidisciplinary efforts for improving clinical skills in the assessment of TMJ in JIA are presented and commented on. An overview of imaging efforts for early detection of TMJ involvement in JIA is also provided, with a critical review of the advantages and limitations of different techniques, imaging protocols, and scoring systems. The perspective offers insights into the correct use and improvement of available and potential tools for early identification of TMJ arthritis in JIA subjects who deserve timely multidisciplinary treatment, avoiding both underestimation and over-diagnosis of TMJ arthritis in routine clinical practice.
Recent advances in prototypical learning have shown remarkable potential to provide useful decision interpretations associating activation maps and predictions with class-specific training prototypes. Such prototypical learning has been well-studied for various single-label diseases, but for quite relevant and more challenging multi-label diagnosis, where multiple diseases are often concurrent within an image, existing prototypical learning models struggle to obtain meaningful activation maps and effective class prototypes due to the entanglement of the multiple diseases. In this paper, we present a novel Cross- and Intra-image Prototypical Learning (CIPL) framework, for accurate multi-label disease diagnosis and interpretation from medical images. CIPL takes advantage of common cross-image semantics to disentangle the multiple diseases when learning the prototypes, allowing a comprehensive understanding of complicated pathological lesions. Furthermore, we propose a new two-level alignment-based regularisation strategy that effectively leverages consistent intra-image information to enhance interpretation robustness and predictive performance. Extensive experiments show that our CIPL attains the state-of-the-art (SOTA) classification accuracy in two public multi-label benchmarks of disease diagnosis: thoracic radiography and fundus images. Quantitative interpretability results show that CIPL also has superiority in weakly-supervised thoracic disease localisation over other leading saliency- and prototype-based explanation methods.
Akeem Temitope Otapo, Alice Othmani, Ghazaleh Khodabandelou
et al.
The integration of Artificial Intelligence (AI) and the Internet of Medical Things (IoMT) in healthcare, through Machine Learning (ML) and Deep Learning (DL) techniques, has advanced the prediction and diagnosis of chronic diseases. AI-driven models such as XGBoost, Random Forest, CNNs, and LSTM RNNs have achieved over 98\% accuracy in predicting heart disease, chronic kidney disease (CKD), Alzheimer's disease, and lung cancer, using datasets from platforms like Kaggle, UCI, private institutions, and real-time IoMT sources. However, challenges persist due to variations in data quality, patient demographics, and formats from different hospitals and research sources. The incorporation of IoMT data, which is vast and heterogeneous, adds complexities in ensuring interoperability and security to protect patient privacy. AI models often struggle with overfitting, performing well in controlled environments but less effectively in real-world clinical settings. Moreover, multi-morbidity scenarios especially for rare diseases like dementia, stroke, and cancers remain insufficiently addressed. Future research should focus on data standardization and advanced preprocessing techniques to improve data quality and interoperability. Transfer learning and ensemble methods are crucial for improving model generalizability across clinical settings. Additionally, the exploration of disease interactions and the development of predictive models for chronic illness intersections is needed. Creating standardized frameworks and open-source tools for integrating federated learning, blockchain, and differential privacy into IoMT systems will also ensure robust data privacy and security.
UAVs emerge as the optimal carriers for visual weed iden?tification and integrated pest and disease management in crops. How?ever, the absence of specialized datasets impedes the advancement of model development in this domain. To address this, we have developed the Pests and Diseases Tree dataset (PDT dataset). PDT dataset repre?sents the first high-precision UAV-based dataset for targeted detection of tree pests and diseases, which is collected in real-world operational environments and aims to fill the gap in available datasets for this field. Moreover, by aggregating public datasets and network data, we further introduced the Common Weed and Crop dataset (CWC dataset) to ad?dress the challenge of inadequate classification capabilities of test models within datasets for this field. Finally, we propose the YOLO-Dense Pest (YOLO-DP) model for high-precision object detection of weed, pest, and disease crop images. We re-evaluate the state-of-the-art detection models with our proposed PDT dataset and CWC dataset, showing the completeness of the dataset and the effectiveness of the YOLO-DP. The proposed PDT dataset, CWC dataset, and YOLO-DP model are pre?sented at https://github.com/RuiXing123/PDT_CWC_YOLO-DP.
Genetic diseases can be classified according to their modes of inheritance and their underlying molecular mechanisms. Autosomal dominant disorders often result from DNA variants that cause loss-of-function, gain-of-function, or dominant-negative effects, while autosomal recessive diseases are primarily linked to loss-of-function variants. In this study, we introduce a graph-of-graphs approach that leverages protein-protein interaction networks and high-resolution protein structures to predict the mode of inheritance of diseases caused by variants in autosomal genes, and to classify dominant-associated proteins based on their functional effect. Our approach integrates graph neural networks, structural interactomics and topological network features to provide proteome-wide predictions, thus offering a scalable method for understanding genetic disease mechanisms.
Tala Al Shrbaji, Mário Bou-Assaf, Rosa Andias
et al.
Abstract Background Action observation (AO) has emerged as a potential neurorehabilitation therapy for patients with neck pain (NP), but evidence of its effectiveness is scarce. This study aims to assess the effect of a single session of AO when compared to observing a natural landscape on NP intensity, fear of movement, fear-avoidance beliefs, neck muscles’ strength, pressure pain threshold, and tactile acuity. Methods Sixty participants with NP were randomly allocated to the AO group (n = 30) or control group (n = 30). Both groups watched an 11-minute video: the AO group watched a video of a person matched for age and sex performing neck exercises, while the control group watched a video of natural landscapes. Neck pain intensity, fear of movement, fear-avoidance beliefs, tactile acuity, pressure pain thresholds, and neck muscle strength were assessed both at baseline and post-intervention. General linear models of repeated measures (ANCOVA of two factors) were used to explore between-group differences at post-intervention. Results There was a significant main effect of time for pain intensity (p = 0.02; η2p = 0.09; within-group mean change and 95% CI: AO=-1.44 (-2.28, -0.59); control=-1.90 (-2.74, -1.06), but no time versus group interaction (p = 0.46). A time versus group significant interaction was found for one out of the six measurement sites of two-point discrimination and the neck flexors strength (p < 0.05) favoring the control group. No other statistically significant differences were found for the remaining variables). Conclusions Results suggest a similar acute benefit for both a single session of AO and observing natural landscapes for promoting hypoalgesia, but no impact on kinesiophobia, fear-avoidance beliefs, or pressure pain thresholds. Also, AO had no positive effect on two-point discrimination and muscle strength. Further research is needed, with longer interventions. Trial registration Clinialtrials.gov (NCT05078489).
Abstract Objective To estimate the global prevalence of hip osteoarthritis (HOA) through a systematic review and meta-analysis, and to determine by regression analysis the respective relationships between age and sex, and sex and prevalence. Methods EMBASE, PubMed, Web of science, CINAHL, and SCOPUS were searched from inception until August 2022. Two authors independently extracted data and assessed the quality of the retrieved literature. Random-effects meta-analysis was performed to derive the pooled prevalence. Variations in the prevalence estimate in different subgroups, including diagnostic methods, region, and patient sex, were examined by subgroup meta-analysis. Meta-regression was used to construct the age-specific prevalence of HOA. Results A total of 31 studies were included in our analysis, involving 326,463 participants. Quality evaluation showed that all studies included in the analysis had a Quality Score of at least 4. The most frequently used method for diagnosing HOA was the Kellgren–Lawrence (K-L) grade classification, accounting for 19/31 (61.3%) studies. The pooled prevalence of HOA diagnosed based on the K-L grade ≥ 2 criterion was 8.55% (95% CI 4.85–13.18) worldwide. The prevalence of HOA was lowest in Africa at 1.20% (95% CI: 0.40–2.38), followed by Asia at 4.26% (95% CI 0.02–14.93) and North America at 7.95% (95% CI 1.98–17.36), and highest in Europe at 12.59% (95% CI 7.17–19.25). There was no statistically significant difference in HOA prevalence between men (9.42%, 95% CI:4.81–15.34) and women at (7.94%, 95% CI: 3.57–13.81). The regression model showed a correlation between age and the prevalence of HOA. Conclusion HOA has high prevalence worldwide and increases with age. The prevalence varies significantly by region but not by patient sex. High-quality epidemiological studies are warranted to more accurately estimate the prevalence of HOA.
Abstract Background In minimally invasive lateral plate osteosynthesis of the humerus (MILPOH) the plate is introduced through a deltoid split proximally and advanced through the central portion of the deltoid insertion and between bone and brachial muscle to the distal aspect of the humerus. The fracture is then indirectly reduced and bridged by the plate. Whereas it has been shown that the strong anterior and posterior parts of the distal deltoid insertion remain intact with this maneuver, its impact on deltoid muscle strength and muscular morphology remains unclear. It was the aim of this study to evaluate deltoid muscle function and MR-morphology of the deltoid muscle and its distal insertion after MILPOH. Methods Six patients (median age 63 years, range 52–69 years, f/m 5/1) who had undergone MILPOH for diaphyseal humeral fractures extending into the proximal metaphysis and head (AO 12B/C(i)) between 08/2017 and 08/2020 were included. Functional testing was performed for the injured and uninjured extremity including strength measurements for 30/60/90° shoulder abduction and flexion at least one year postoperatively. Constant-Murley-Score (CMS) including an age-and gender-adjusted version, were obtained and compared to the uninjured side. Oxford Shoulder Score (OSS) and the Disability of the Arm, Shoulder and Hand (DASH) questionnaire were acquired for the affected extremity. Quality of life was measured using the EQ visual analogue scale (EQ-5D-5 L VAS). MR imaging was performed for both shoulders accordingly at the time of follow-up to assess the integrity of the distal insertion, muscle mass and fatty degeneration of the deltoid muscle. Muscle mass was determined by measuring the area of the deltoid muscle on the axial MR image at the height of the center of the humeral head. Results Median follow-up was 29 months (range 12–48 months). Median difference of abduction strength after MILPOH was + 13% for 30°, 0% for 60° and − 22% for 90°. For flexion, the difference to the uninjured side was measured 5% for 30°, -7% for 60° and − 12% for 90°. Median CMS was 75 (66–82) for the operated extremity compared to 82 (77–90) for the uninjured side. Age- and gender-adapted CMS was calculated 88 (79–99) vs. 96 (89–107). Median OSS was 47 (40–48). DASH was 26 (15–36). EQ-5D-5 L VAS ranged from 81 to 95 with a median of 90. The median difference of the deltoid muscle area on MRI was 2% (-21% to + 53%) compared to the uninjured side. No fatty degeneration of the deltoid muscle was observed. The weaker central part of the distal deltoid insertion was exclusively perforated by the plate, leaving the strong anterior and posterior parts of the insertion intact in all patients. Conclusions MILPOH was associated with good functional and subjective outcome. Minor impairment of abduction strength was observed with increasing abduction angles. The reason for this impairment is unclear since MILPOH did not affect the structural quality of the deltoid muscle and the integrity of the strong anterior and posterior parts of its insertion remained intact. Trial registration 26/05/2023: ISRCTN51786146.
Ritesh Chandra, Sadhana Tiwari, Sonali Agarwal
et al.
Vector-borne diseases (VBDs) are a kind of infection caused through the transmission of vectors generated by the bites of infected parasites, bacteria, and viruses, such as ticks, mosquitoes, triatomine bugs, blackflies, and sandflies. If these diseases are not properly treated within a reasonable time frame, the mortality rate may rise. In this work, we propose a set of ontologies that will help in the diagnosis and treatment of vector-borne diseases. For developing VBD's ontology, electronic health records taken from the Indian Health Records website, text data generated from Indian government medical mobile applications, and doctors' prescribed handwritten notes of patients are used as input. This data is then converted into correct text using Optical Character Recognition (OCR) and a spelling checker after pre-processing. Natural Language Processing (NLP) is applied for entity extraction from text data for making Resource Description Framework (RDF) medical data with the help of the Patient Clinical Data (PCD) ontology. Afterwards, Basic Formal Ontology (BFO), National Vector Borne Disease Control Program (NVBDCP) guidelines, and RDF medical data are used to develop ontologies for VBDs, and Semantic Web Rule Language (SWRL) rules are applied for diagnosis and treatment. The developed ontology helps in the construction of decision support systems (DSS) for the NVBDCP to control these diseases.
Navid Ghaffarzadegan, Aritra Majumdar, Ross Williams
et al.
We discuss the emerging new opportunity for building feedback-rich computational models of social systems using generative artificial intelligence. Referred to as Generative Agent-Based Models (GABMs), such individual-level models utilize large language models such as ChatGPT to represent human decision-making in social settings. We provide a GABM case in which human behavior can be incorporated in simulation models by coupling a mechanistic model of human interactions with a pre-trained large language model. This is achieved by introducing a simple GABM of social norm diffusion in an organization. For educational purposes, the model is intentionally kept simple. We examine a wide range of scenarios and the sensitivity of the results to several changes in the prompt. We hope the article and the model serve as a guide for building useful diffusion models that include realistic human reasoning and decision-making.
Utkarsh Yashwant Tambe, A. Shobanadevi, A. Shanthini
et al.
In this study, a Convolutional Neural Network (CNN) is used to classify potato leaf illnesses using Deep Learning. The suggested approach entails preprocessing the leaf image data, training a CNN model on that data, and assessing the model's success on a test set. The experimental findings show that the CNN model, with an overall accuracy of 99.1%, is highly accurate in identifying two kinds of potato leaf diseases, including Early Blight, Late Blight, and Healthy. The suggested method may offer a trustworthy and effective remedy for identifying potato diseases, which is essential for maintaining food security and minimizing financial losses in agriculture. The model can accurately recognize the various disease types even when there are severe infections present. This work highlights the potential of deep learning methods for categorizing potato diseases, which can help with effective and automated disease management in potato farming.