BACKGROUND AND OBJECTIVES

One of the effects of the COVID-19 pandemic on medical education is an increased awareness and use of social media (SocMed) to facilitate learning. However, literature on the use of SocMed in medical education has focused primarily on educator-led teaching activities. Our study aimed to describe SocMed initiatives that were student-led, particularly for information dissemination and peer collaborative learning, and to elicit perceptions of medical students towards such activities.

An online survey on SocMed usage in medical education was sent to all first- and second-year medical students at the University of the Philippines Manila College of Medicine from October to December 2021. The questionnaire collected data on demographics, SocMed habits and preferences, and perceived advantages and disadvantages of SocMed. Descriptive statistics were calculated while the free-text responses were grouped into prominent themes and summarized.

We received a total of 258 responses (71%) out of 361 eligible participants. Overall, 74% found SocMed platforms to be very and extremely helpful; 88% recommended its continued use. The most popular SocMed platforms for different tasks were as follows: Discord for independent study groups and for conducting peer tutoring sessions; Facebook Messenger for reading reminders; Telegram for reading announcements related to academics and administrative requirements, and for accessing material provided by classmates and professors.

The high uptake of SocMed among medical students may be attributed to its accessibility and costefficiency. The use of a particular SocMed platform was dependent on the students’ needs and the platform's features. Students tended to use multiple SocMed platforms that complemented one another. SocMed also had disadvantages, such as the potential to distract from academic work and to become a source of fatigue. Educators must engage with students to understand how SocMed platforms can be integrated into medical education, whether in the physical or virtual learning environment.

BACKGROUND AND OBJECTIVES

The Philippines faces challenges in the screening of tuberculosis (TB), one of them being the shortage in the health workforce who are skilled and allowed to screen TB. Deep learning neural networks (DLNNs) have shown potential in the TB screening process utilizing chest radiographs (CXRs). However, local studies on AIbased TB screening are limited. This study evaluated qXR3.0 technology's diagnostic performance for TB screening in Filipino adults aged 15 and older. Specifically, we evaluated the specificity and sensitivity of qXR3.0 compared to radiologists' impressions and determined whether it meets the World Health Organization (WHO) standards.

A prospective cohort design was used to perform a study on comparing screening and diagnostic accuracies of qXR3.0 and two radiologist gradings in accordance with the Standards for Reporting Diagnostic Accuracy (STARD). Subjects from two clinics in Metro Manila which had qXR 3.0 seeking consultation at the time of study were invited to participate to have CXRs and sputum collected. Radiologists' and qXR3.0 readings and impressions were compared with respect to the reference standard Xpert MTB/RiF assay. Diagnostic accuracy measures were calculated.

With 82 participants, qXR3.0 demonstrated 100% sensitivity and 72.7% specificity with respect to the reference standard. There was a strong agreement between qXR3.0 and radiologists' readings as exhibited by the 0.7895 (between qXR 3.0 and CXRs read by at least one radiologist), 0.9362 (qXR 3.0 and CXRs read by both radiologists), and 0.9403 (qXR 3.0 and CXRs read as not suggestive of TB by at least one radiologist) concordance indices.

qXR3.0 demonstrated high sensitivity to identify presence of TB among patients, and meets the WHO standard of at least 70% specificity for detecting true TB infection. This shows an immense potential for the tool to supplement the shortage of radiologists for TB screening in the country. Future research directions may consider larger sample sizes to confirm these findings and explore the economic value of mainstream adoption of qXR 3.0 for TB screening.

INTRODUCTION: Elevated troponin, while essential for diagnosing myocardial infarction, can also be present in non-myocardial infarction conditions. The myocardial-ischaemic-injury-index (MI3) algorithm is a machine learning algorithm that considers age, sex and cardiac troponin I (TnI) results to risk-stratify patients for type 1 myocardial infarction. METHOD: Patients aged ≥25 years who presented to the emergency department (ED) of Singapore General Hospital with symptoms suggestive of acute coronary syndrome with no diagnostic 12-lead electrocardiogram (ECG) changes were included. Participants had serial ECGs and high-sensitivity troponin assays performed at 0, 2 and 7 hours. The primary outcome was the adjudicated diagnosis of type 1 myocardial infarction at 30 days. We compared the performance of MI3 in predicting the primary outcome with the European Society of Cardiology (ESC) 0/2-hour algorithm as well as the 99th percentile upper reference limit (URL) for TnI. RESULTS: There were 1351 patients included (66.7% male, mean age 56 years), 902 (66.8%) of whom had only 0-hour troponin results and 449 (33.2%) with serial (both 0 and 2-hour) troponin results available. MI3 ruled out type 1 myocardial infarction with a higher sensitivity (98.9, 95% confidence interval [CI] 93.4-99.9%) and similar negative predictive value (NPV) 99.8% (95% CI 98.6-100%) as compared to the ESC strategy. The 99th percentile cut-off strategy had the lowest sensitivity, specificity, positive predictive value and NPV. CONCLUSION The MI3 algorithm was accurate in risk stratifying ED patients for myocardial infarction. The 99th percentile URL cut-off was the least accurate in ruling in and out myocardial infarction compared to the other strategies.
Humans ; Male ; Female ; Emergency Service, Hospital ; Middle Aged ; Electrocardiography ; Machine Learning ; Singapore ; Chest Pain/blood* ; Troponin I/blood* ; Myocardial Infarction/blood* ; Risk Assessment/methods* ; Aged ; Algorithms ; Acute Coronary Syndrome/blood* ; Adult ; Sensitivity and Specificity

Research on IgG4-related disease (IgG4-RD), an autoimmune condition recognized to be a unique disease entity only two decades ago, has processed from describing patients' symptoms and signs to summarizing its critical pathological features, and further to investigating key pathogenic mechanisms. Challenges in gaining a better understanding of the disease, however, stem from its relative rarity-potentially attributed to underrecognition-and the absence of ideal experimental animal models. Recently, with the development of various high-throughput techniques, "omics" studies at different levels (particularly the single-cell omics) have shown promise in providing detailed molecular features of IgG4-RD. While, the application of omics approaches in IgG4-RD is still at an early stage. In this paper, we review the current progress of omics research in IgG4-RD and discuss the value of machine learning methods in analyzing the data with high dimensionality.
Humans ; Immunoglobulin G4-Related Disease/metabolism* ; Immunoglobulin G/metabolism* ; Machine Learning ; Animals ; Proteomics/methods*

BACKGROUND: Postoperative pulmonary complications (PPCs) are major adverse events in neurosurgical patients. This study aimed to develop and validate machine learning models predicting PPCs after neurosurgery. METHODS: PPCs were defined according to the European Perioperative Clinical Outcome standards as occurring within 7 postoperative days. Data of cases meeting inclusion/exclusion criteria were extracted from the anesthesia information management system to create three datasets: The development (data of Huashan Hospital, Fudan University from 2018 to 2020), temporal validation (data of Huashan Hospital, Fudan University in 2021) and external validation (data of other three hospitals in 2023) datasets. Machine learning models of six algorithms were trained using either 35 retrievable and plausible features or the 11 features selected by Lasso regression. Temporal validation was conducted for all models and the 11-feature models were also externally validated. Independent risk factors were identified and feature importance in top models was analyzed. RESULTS: PPCs occurred in 712 of 7533 (9.5%), 258 of 2824 (9.1%), and 207 of 2300 (9.0%) patients in the development, temporal validation and external validation datasets, respectively. During cross-validation training, all models except Bayes demonstrated good discrimination with an area under the receiver operating characteristic curve (AUC) of 0.840. In temporal validation of full-feature models, deep neural network (DNN) performed the best with an AUC of 0.835 (95% confidence interval [CI]: 0.805-0.858) and a Brier score of 0.069, followed by Logistic regression (LR), random forest and XGBoost. The 11-feature models performed comparable to full-feature models with very close but statistically significantly lower AUCs, with the top models of DNN and LR in temporal and external validations. An 11-feature nomogram was drawn based on the LR algorithm and it outperformed the minimally modified Assess respiratory RIsk in Surgical patients in CATalonia (ARISCAT) and Laparoscopic Surgery Video Educational Guidelines (LAS VEGAS) scores with a higher AUC (LR: 0.824, ARISCAT: 0.672, LAS: 0.663). Independent risk factors based on multivariate LR mostly overlapped with Lasso-selected features, but lacked consistency with the important features using the Shapley additive explanation (SHAP) method of the LR model. CONCLUSIONS: The developed models, especially the DNN model and the nomogram, had good discrimination and calibration, and could be used for predicting PPCs in neurosurgical patients. The establishment of machine learning models and the ascertainment of risk factors might assist clinical decision support for improving surgical outcomes. TRIAL REGISTRATION ChiCTR 2100047474; https://www.chictr.org.cn/showproj.html?proj=128279 .
Adult ; Aged ; Female ; Humans ; Male ; Middle Aged ; Algorithms ; Lung Diseases/etiology* ; Machine Learning ; Neurosurgical Procedures/adverse effects* ; Postoperative Complications/diagnosis* ; Risk Factors ; ROC Curve

Artificial intelligence (AI), particularly deep learning, has demonstrated remarkable performance in medical imaging across a variety of modalities, including X-ray, computed tomography (CT), magnetic resonance imaging (MRI), ultrasound, positron emission tomography (PET), and pathological imaging. However, most existing state-of-the-art AI techniques are task-specific and focus on a limited range of imaging modalities. Compared to these task-specific models, emerging foundation models represent a significant milestone in AI development. These models can learn generalized representations of medical images and apply them to downstream tasks through zero-shot or few-shot fine-tuning. Foundation models have the potential to address the comprehensive and multifactorial challenges encountered in clinical practice. This article reviews the clinical applications of both task-specific and foundation models, highlighting their differences, complementarities, and clinical relevance. We also examine their future research directions and potential challenges. Unlike the replacement relationship seen between deep learning and traditional machine learning, task-specific and foundation models are complementary, despite inherent differences. While foundation models primarily focus on segmentation and classification, task-specific models are integrated into nearly all medical image analyses. However, with further advancements, foundation models could be applied to other clinical scenarios. In conclusion, all indications suggest that task-specific and foundation models, especially the latter, have the potential to drive breakthroughs in medical imaging, from image processing to clinical workflows.
Humans ; Artificial Intelligence ; Deep Learning ; Diagnostic Imaging/methods* ; Magnetic Resonance Imaging ; Tomography, X-Ray Computed ; Positron-Emission Tomography

BACKGROUND: Over 20 million colonoscopies are performed in China annually. An automatic clinical decision support system (CDSS) with accurate semantic recognition of colonoscopy reports and guideline-based is helpful to relieve the increasing medical burden and standardize the healthcare. In this study, the CDSS was built under a hierarchical-label interpretable classification framework, trained by a state-of-the-art transformer-based model, and validated in a multi-center style. METHODS: We conducted stratified sampling on a previously established dataset containing 302,965 electronic colonoscopy reports with pathology, identified 2041 patients' records representative of overall features, and randomly divided into the training and testing sets (7:3). A total of five main labels and 22 sublabels were applied to annotate each record on a network platform, and the data were trained respectively by three pre-training models on Chinese corpus website, including bidirectional encoder representations from transformers (BERT)-base-Chinese (BC), the BERT-wwm-ext-Chinese (BWEC), and ernie-3.0-base-zh (E3BZ). The performance of trained models was subsequently compared with a randomly initialized model, and the preferred model was selected. Model fine-tuning was applied to further enhance the capacity. The system was validated in five other hospitals with 3177 consecutive colonoscopy cases. RESULTS: The E3BZ pre-trained model exhibited the best performance, with a 90.18% accuracy and a 69.14% Macro-F1 score overall. The model achieved 100% accuracy in identifying cancer cases and 99.16% for normal cases. In external validation, the model exhibited favorable consistency and good performance among five hospitals. CONCLUSIONS The novel CDSS possesses high-level semantic recognition of colonoscopy reports, provides appropriate recommendations, and holds the potential to be a powerful tool for physicians and patients. The hierarchical multi-label strategy and pre-training method should be amendable to manage more medical text in the future.
Humans ; Colonoscopy/methods* ; Deep Learning ; Decision Support Systems, Clinical ; Female ; Male

BACKGROUND: Gluconeogenesis is a critical metabolic pathway for maintaining glucose homeostasis, and its dysregulation can lead to glycometabolic disorders. This study aimed to identify hub biomarkers of these disorders to provide a theoretical foundation for enhancing diagnosis and treatment. METHODS: Gene expression profiles from liver tissues of three well-characterized gluconeogenesis mouse models were analyzed to identify commonly differentially expressed genes (DEGs). Weighted gene co-expression network analysis (WGCNA), machine learning techniques, and diagnostic tests on transcriptome data from publicly available datasets of type 2 diabetes mellitus (T2DM) patients were employed to assess the clinical relevance of these DEGs. Subsequently, we identified hub biomarkers associated with gluconeogenesis-related glycometabolic disorders, investigated potential correlations with immune cell types, and validated expression using quantitative polymerase chain reaction in the mouse models. RESULTS: Only a few common DEGs were observed in gluconeogenesis-related glycometabolic disorders across different contributing factors. However, these DEGs were consistently associated with cytokine regulation and oxidative stress (OS). Enrichment analysis highlighted significant alterations in terms related to cytokines and OS. Importantly, osteomodulin ( OMD ), apolipoprotein A4 ( APOA4 ), and insulin like growth factor binding protein 6 ( IGFBP6 ) were identified with potential clinical significance in T2DM patients. These genes demonstrated robust diagnostic performance in T2DM cohorts and were positively correlated with resting dendritic cells. CONCLUSIONS Gluconeogenesis-related glycometabolic disorders exhibit considerable heterogeneity, yet changes in cytokine regulation and OS are universally present. OMD , APOA4 , and IGFBP6  may serve as hub biomarkers for gluconeogenesis-related glycometabolic disorders.
Machine Learning ; Humans ; Computational Biology/methods* ; Biomarkers/metabolism* ; Diabetes Mellitus, Type 2/genetics* ; Animals ; Mice ; Gluconeogenesis/physiology* ; Gene Expression Profiling ; Transcriptome/genetics* ; Gene Regulatory Networks/genetics* ; Clinical Relevance

Prostate cancer (PCa) ranks as the second most prevalent malignancy among men worldwide. Early diagnosis, personalized treatment, and prognosis prediction of PCa play a crucial role in improving patients' survival rates. The advancement of artificial intelligence (AI), particularly the utilization of deep learning (DL) algorithms, has brought about substantial progress in assisting the diagnosis, treatment, and prognosis prediction of PCa. The introduction of the foundation model has revolutionized the application of AI in medical treatment and facilitated its integration into clinical practice. This review emphasizes the clinical application of AI in PCa by discussing recent advancements from both pathological and imaging perspectives. Furthermore, it explores the current challenges faced by AI in clinical applications while also considering future developments, aiming to provide a valuable point of reference for the integration of AI and clinical applications.
Humans ; Prostatic Neoplasms/diagnosis* ; Male ; Artificial Intelligence ; Deep Learning ; Prognosis

With the emergence of deep learning techniques based on convolutional neural networks, artificial intelligence (AI) has driven transformative developments in the field of medical image analysis. Recently, large language models (LLMs) such as ChatGPT have also started to achieve distinction in this domain. Increasing research shows the undeniable role of AI in reshaping various aspects of medical image analysis, including processes such as image enhancement, segmentation, detection in image preprocessing, and postprocessing related to medical diagnosis and prognosis in clinical settings. However, despite the significant progress in AI research, studies investigating the recent advances in AI technology in the aforementioned aspects, the changes in research hotspot trajectories, and the performance of studies in addressing key clinical challenges in this field are limited. This article provides an overview of recent advances in AI for medical image analysis and discusses the methodological profiles, advantages, disadvantages, and future trends of AI technologies.
Artificial Intelligence ; Humans ; Image Processing, Computer-Assisted/methods* ; Neural Networks, Computer ; Deep Learning ; Diagnostic Imaging/methods*