Hasil untuk "Diseases of the digestive system. Gastroenterology"

Anand S. Jain, Vani J.A. Konda, Milli Gupta et al.

Chinese Society of Gastroenterology, Chinese Medical Association

ABSTRACT Chronic diarrhea is a common symptom of the digestive system and also a frequent reason for consultation among patients in gastroenterology outpatient clinics. As one of the common etiologies of chronic diarrhea, bile acid diarrhea (BAD) has a relatively high incidence rate. However, due to the current limitations in physicians' awareness, medical standards, and diagnostic methods, BAD is often underdiagnosed or misdiagnosed; therefore, patients often fail to receive timely and appropriate treatment. To further improve clinicians' understanding and management of BAD, the Chinese Society of Gastroenterology, Chinese Medical Association, on the basis of drawing on domestic and international diagnostic and therapeutic experiences as well as guidelines and consensuses, has organized domestic experts to formulate this expert consensus focusing on the pathogenesis, clinical classification, diagnosis, and management of BAD.

Manav C. Parikh, Heather Thiessen Philbrook, David Hu et al.

Lin Chang, Shahnaz Sultan, Anthony Lembo et al.

Kimberly Ho, Daniel Marino

J.M. Ladowski, Mariya L. Samoylova, Jeffrey Ord et al.

Background: Intestinal transplantation (IT) remains the only treatment modality for patients with irreversible intestinal failure who cannot be maintained on chronic parenteral nutrition. Multiple reports have demonstrated an association between donor-specific antibodies (DSA) in IT graft rejection, however these studies have largely been single-center analyses. The goal of this study was to examine the available immunological data from the International Intestinal Transplant Registry (IITR) and evaluate the association with rejection. Materials and methods: Demographic, outcomes, and serologic HLA data from donor/recipient pairs was obtained from the IITR. Outcomes including rejection, graft survival, and patient survival were analyzed based on age, DSA reporting, and molecular HLA mismatch. Eplet mismatch analysis was performed using HLAMatchmaker. Results: Our analysis revealed significant limitations in the granularity of data contained in the IITR. Conclusion: The IITR database is a promising option to perform a multicenter analysis of IT outcomes, but there are limitations in the data to allow a thorough immunologic examination.

Paola Andrea Santamaría Losada, Sergio Enrique Pedroza Sabogal

Antecedentes: la retención prolongada de cuerpos extraños en el esófago es infrecuente y puede retrasar el diagnóstico. La mayoría de los pacientes buscan atención médica en las primeras 72 horas tras la ingesta, evitando complicaciones graves. Presentación del caso: se presenta el caso de un paciente masculino de 46 años con disfagia progresiva de 18 meses. Luego de múltiples estudios diagnósticos, se identificó un cuerpo extraño en el esófago superior, que resultó ser una prótesis dental ingerida 20 meses antes durante un episodio de embriaguez. Dado el compromiso estructural del esófago, se realizó la extracción quirúrgica mediante cervicotomía y esofagotomía. La evolución posoperatoria fue favorable sin complicaciones mayores. Conclusión: este caso resalta la importancia de considerar la retención prolongada de cuerpos extraños en pacientes con disfagia crónica de origen incierto. La anamnesis detallada, el uso adecuado de estudios de imagen y endoscópicos, así como un abordaje quirúrgico oportuno fueron fundamentales para el éxito del tratamiento. La ausencia de complicaciones posoperatorias subraya la relevancia de una detección y manejo adecuados.

Yueheng Jiang, Peng Zhang

Multi-disease diagnosis using multi-modal data like electronic health records and medical imaging is a critical clinical task. Although existing deep learning methods have achieved initial success in this area, a significant gap persists for their real-world application. This gap arises because they often overlook unavoidable practical challenges, such as modality missingness, noise, temporal asynchrony, and evidentiary inconsistency across modalities for different diseases. To overcome these limitations, we propose HGDC-Fuse, a novel framework that constructs a patient-centric multi-modal heterogeneous graph to robustly integrate asynchronous and incomplete multi-modal data. Moreover, we design a heterogeneous graph learning module to aggregate multi-source information, featuring a disease correlation-guided attention layer that resolves the modal inconsistency issue by learning disease-specific modality weights based on disease correlations. On the large-scale MIMIC-IV and MIMIC-CXR datasets, HGDC-Fuse significantly outperforms state-of-the-art methods.

Faika Fairuj Preotee, Shuvashis Sarker, Shamim Rahim Refat et al.

Leaf diseases are harmful conditions that affect the health, appearance and productivity of plants, leading to significant plant loss and negatively impacting farmers' livelihoods. These diseases cause visible symptoms such as lesions, color changes, and texture variations, making it difficult for farmers to manage plant health, especially in large or remote farms where expert knowledge is limited. The main motivation of this study is to provide an efficient and accessible solution for identifying plant leaf diseases in Bangladesh, where agriculture plays a critical role in food security. The objective of our research is to classify 21 distinct leaf diseases across six plants using deep learning models, improving disease detection accuracy while reducing the need for expert involvement. Deep Learning (DL) techniques, including CNN and Transfer Learning (TL) models like VGG16, VGG19, MobileNetV2, InceptionV3, ResNet50V2 and Xception are used. VGG19 and Xception achieve the highest accuracies, with 98.90% and 98.66% respectively. Additionally, Explainable AI (XAI) techniques such as GradCAM, GradCAM++, LayerCAM, ScoreCAM and FasterScoreCAM are used to enhance transparency by highlighting the regions of the models focused on during disease classification. This transparency ensures that farmers can understand the model's predictions and take necessary action. This approach not only improves disease management but also supports farmers in making informed decisions, leading to better plant protection and increased agricultural productivity.

Fahud Ahmmed, Md. Zaheer Raihan, Kamnur Nahar et al.

Skin diseases can arise from infections, allergies, genetic factors, autoimmune disorders, hormonal imbalances, or environmental triggers such as sun damage and pollution. Some skin diseases, such as Actinic Keratosis and Psoriasis, can be fatal if not treated in time. Early identification is crucial, but the diagnostic methods for these conditions are often expensive and not widely accessible. In this study, we propose a novel and efficient method for diagnosing skin diseases using deep learning techniques. This approach employs a modified VGG16 Convolutional Neural Network (CNN) model. The model includes several convolutional layers and utilizes ImageNet weights with modified top layers. The top layer is updated with fully connected layers and a final softmax activation layer to classify skin diseases. The dataset used, titled "Skin Disease Dataset," is publicly available. While the VGG16 architecture does not include data augmentation by default, preprocessing techniques such as rotation, shifting, and zooming were applied to augment the data prior to model training. The proposed methodology achieved 90.67% accuracy using the modified VGG16 model, demonstrating its reliability in classifying skin diseases. The promising results highlight the potential of this approach for real-world applications.

Takashi Nishibayashi, Seiji Kanazawa, Kumpei Yamada

Symptom Checkers (SCs) provide medical information tailored to user symptoms. A critical challenge in SC development is preventing unexpected performance degradation for individual diseases, especially rare diseases, when updating algorithms. This risk stems from the lack of practical pre-deployment evaluation methods. For rare diseases, obtaining sufficient evaluation data from user feedback is difficult. To evaluate the impact of algorithm updates on the diagnostic performance for individual rare diseases before deployment, this study proposes and validates a novel Synthetic Vignette Simulation Approach. This approach aims to enable this essential evaluation efficiently and at a low cost. To estimate the impact of algorithm updates, we generated synthetic vignettes from disease-phenotype annotations in the Human Phenotype Ontology (HPO), a publicly available knowledge base for rare diseases curated by experts. Using these vignettes, we simulated SC interviews to predict changes in diagnostic performance. The effectiveness of this approach was validated retrospectively by comparing the predicted changes with actual performance metrics using the R-squared ($R^2$) coefficient. Our experiment, covering eight past algorithm updates for rare diseases, showed that the proposed method accurately predicted performance changes for diseases with phenotype frequency information in HPO (n=5). For these updates, we found a strong correlation for both Recall@8 change ($R^2$ = 0.83,$p$ = 0.031) and Precision@8 change ($R^2$ = 0.78,$p$ = 0.047). Our proposed method enables the pre-deployment evaluation of SC algorithm changes for individual rare diseases. This evaluation is based on a publicly available medical knowledge database created by experts, ensuring transparency and explainability for stakeholders. Additionally, SC developers can efficiently improve diagnostic performance at a low cost.

Adam Tisch, Siddharth Madapoosi, Stephen Blough et al.

Saixin Li, Zheng Wang, Zheng Li et al.

Abstract Background T-tube cholangiography and choledochoscopy are commonly used techniques for detecting residual bile duct stones after biliary surgery. However, the utility of routine cholangiography before T-tube removal needs further investigation. This study aims to evaluate the diagnostic efficacy of various methods for detecting residual calculi following biliary surgery. Methods We retrospectively analyzed the clinical data of 287 adult patients who underwent common bile duct exploration with T-tube drainage, followed by T-tube cholangiography and choledochoscopy, at the Department of General Surgery, Xuanwu Hospital, Capital Medical University, between 2017 and 2022. Exclusion criteria were patients with bile duct tumors, incomplete medical records or loss to follow-up, and patients with contraindications to T-tube or choledochoscopy. McNemanr test and Kappa test were used to compare the results and consistency between choledochoscopy and T-tube cholangiography. All patients underwent both cholangiography and choledochoscopy six to eight weeks after laparoscopic cholecystectomy combined with common bile duct exploration and T-tube drainage. The results of T-tube cholangiography and choledochoscopy for each patient were recorded, analyzed, and compared. Results Among the 287 patients, T-tube cholangiography detected residual stones in 38 cases, which were confirmed by choledochoscopy in 29 cases. Conversely, of the 249 patients without evidence of residual stones on T-tube angiography, 11 patient was later found to have retained stones through choledochoscopy. There was no significant difference between the results of T-tube cholangiography and choledochoscopy (P = 0.82), indicating a high level of agreement between the two methods (Kappa value: 0.70) (95% CI, 0.65–0.76). Conclusion There is no significant difference in the diagnostic accuracy between T-tube cholangiography and choledochoscopy for detecting residual bile duct stones after surgery (P = 0.82). The two methods demonstrated a high level of consistency (Kappa value: 0.70) (95% CI, 0.65–0.76). The choice of diagnostic method for postoperative residual bile duct stones should be based on the specific condition of the patient.

Yingjing Xu, Xueyan Cai, Zihong Zhou et al.

Hypomimia is a non-motor symptom of Parkinson's disease that manifests as delayed facial movements and expressions, along with challenges in articulation and emotion. Currently, subjective evaluation by neurologists is the primary method for hypomimia detection, and conventional rehabilitation approaches heavily rely on verbal prompts from rehabilitation physicians. There remains a deficiency in accessible, user-friendly and scientifically rigorous assistive tools for hypomimia treatments. To investigate this, we developed HypomimaCoach, an Action Unit (AU)-based digital therapy system for hypomimia detection and rehabilitation in Parkinson's disease. The HypomimaCoach system was designed to facilitate engagement through the incorporation of both relaxed and controlled rehabilitation exercises, while also stimulating initiative through the integration of digital therapies that incorporated traditional face training methods. We extract action unit(AU) features and their relationship for hypomimia detection. In order to facilitate rehabilitation, a series of training programmes have been devised based on the Action Units (AUs) and patients are provided with real-time feedback through an additional AU recognition model, which guides them through their training routines. A pilot study was conducted with seven participants in China, all of whom exhibited symptoms of Parkinson's disease hypomimia. The results of the pilot study demonstrated a positive impact on participants' self-efficacy, with favourable feedback received. Furthermore, physician evaluations validated the system's applicability in a therapeutic setting for patients with Parkinson's disease, as well as its potential value in clinical applications.

Darlyn Buenaño Vera, Byron Oviedo, Washington Chiriboga Casanova et al.

The early identification of diseases in cocoa pods is an important task to guarantee the production of high-quality cocoa. The use of artificial intelligence techniques such as machine learning, computer vision and deep learning are promising solutions to help identify and classify diseases in cocoa pods. In this paper we introduce the development and evaluation of a deep learning computational model applied to the identification of diseases in cocoa pods, focusing on "monilia" and "black pod" diseases. An exhaustive review of state-of-the-art of computational models was carried out, based on scientific articles related to the identification of plant diseases using computer vision and deep learning techniques. As a result of the search, EfficientDet-Lite4, an efficient and lightweight model for object detection, was selected. A dataset, including images of both healthy and diseased cocoa pods, has been utilized to train the model to detect and pinpoint disease manifestations with considerable accuracy. Significant enhancements in the model training and evaluation demonstrate the capability of recognizing and classifying diseases through image analysis. Furthermore, the functionalities of the model were integrated into an Android native mobile with an user-friendly interface, allowing to younger or inexperienced farmers a fast and accuracy identification of health status of cocoa pods

Branko Mitic, Philipp Seeböck, Jennifer Straub et al.

Fast detection of emerging diseases is important for containing their spread and treating patients effectively. Local anomalies are relevant, but often novel diseases involve familiar disease patterns in new spatial distributions. Therefore, established local anomaly detection approaches may fail to identify them as new. Here, we present a novel approach to detect the emergence of new disease phenotypes exhibiting distinct patterns of the spatial distribution of lesions. We first identify anomalies in lung CT data, and then compare their distribution in a continually acquired new patient cohorts with historic patient population observed over a long prior period. We evaluate how accumulated evidence collected in the stream of patients is able to detect the onset of an emerging disease. In a gram-matrix based representation derived from the intermediate layers of a three-dimensional convolutional neural network, newly emerging clusters indicate emerging diseases.

Eric D. Shah, Emily V. Wechsler

Emily K. Sims, Susan M. Geyer, S. Alice Long et al.

Abed Khalaileh, Ashraf Imam, Alaa Jammal et al.

Background and Aims:. We retrospectively assessed the clinical Pfizer’s mRNA SARS-CoV-2 BNT162b2 vaccination outcomes and the serologic impact on liver transplant (LT) recipients. Patients and Methods:. One hundred and sixty-seven LT cases followed between March 1, 2020 and September 25, 2021, and were stratified into two groups: (1) 37 LT recipients after SARS-CoV-2 infection before vaccine era and (2) 130 LT recipients vaccinated with 2 doses without earlier SARS-CoV-2 exposure. Serum SARS-CoV-2 spike immunoglobulins (anti-S) were assessed 7 days following vaccination (Liaison assay). Results:. In addition to the 37 nonvaccinated cases (22.2% of total group) who experienced SARS-CoV-2 infection (34 symptomatic and 3 asymptomatic), another 8 vaccinated symptomatic recipients (4.8%) were infected (5 from the third and three from the fourth waves). Three of the 45 infected cases died (6.7%) before the vaccine program. Vaccinated group: of the 130 LT vaccinated recipients, 8 (6.2%) got infected postvaccination (added to the infected group) and were defined as clinical vaccine failure; 38 (29.2%) were serological vaccine failure (total failure 35.4%), and 64.6% cases were serological vaccine responders (anti-S≥19 AU/mL). Longer post-LT interval and lower consumption of immunosuppressants (steroids, FK506, and mycophenolate mofetil) correlated with favorable SARS-CoV-2 vaccine response. Mammalian target of rapamycin inhibitors improved vaccine outcomes associated with lower FK506 dosages and serum levels. Patients with anti-S levels <100 AU/mL risked losing serologic response or being infected with SARS-CoV-2. A booster dose achieved an effective serologic response in a third of failures and most responders, securing better and possibly longer protection. Conclusion:. Pfizer’s BNT162b2 vaccine seems to lessen SARS-CoV-2 morbidity and mortality of LT recipients even with weak serological immunogenicity. Switching mycophenolate mofetil to mammalian target of rapamycin inhibitors might be effective before boosters in vaccine failure cases. A booster vaccine should be considered for nonresponders and low-responders after the second dose.

Nancy N Baxter, Jill Tinmouth, Diego Llovet et al.

Background and aims Non-pharmacological interventions to improve patient-reported outcomes of colonoscopy may be effective at mitigating negative experiences and perceptions of the procedure, but research to characterise the extent and features of studies of these interventions is limited.Methods We conducted a scoping review searching multiple databases for peer-reviewed publications of randomised controlled trials conducted in adults investigating a non-pharmacological intervention to improve patient-reported outcomes of colonoscopy. Study characteristics were tabulated and summarised narratively and graphically.Results We screened 5939 citations and 962 full texts, and included 245 publications from 39 countries published between 1992 and 2022. Of these, 80.8% were full publications and 19.2% were abstracts. Of the 41.9% of studies reporting funding sources, 11.4% were unfunded. The most common interventions were carbon dioxide and/or water insufflation methods (33.9%), complementary and alternative medicines (eg, acupuncture) (20.0%), and colonoscope technology (eg, magnetic scope guide) (21.6%). Pain was as an outcome across 82.0% of studies. Studies most often used a patient-reported outcome examining patient experience during the procedure (60.0%), but 42.9% of studies included an outcome without specifying the time that the patient experienced the outcome. Most intraprocedural patient-reported outcomes were measured retrospectively rather than contemporaneously, although studies varied in terms of when outcomes were assessed.Conclusion Research on non-pharmacological interventions to improve patient-reported outcomes of colonoscopy is unevenly distributed across types of intervention and features high variation in study design and reporting, in particular around outcomes. Future research efforts into non-pharmacological interventions to improve patient-reported outcomes of colonoscopy should be directed at underinvestigated interventions and developing consensus-based guidelines for study design, with particular attention to how and when outcomes are experienced and measured.PROSPERO registration number 42020173906.