Tuberculosis (TB), caused by Mycobacterium tuberculosis, remains a leading cause of global mortality. While TB detection can be performed through chest X-ray (CXR) analysis, numerous studies have leveraged AI to automate and enhance the diagnostic process. However, existing approaches often focus on partial or incomplete lesion detection, lacking comprehensive multi-class and multi-label solutions for the full range of TB-related anomalies. To address this, we present a hybrid AI model combining vision transformer (ViT) and convolutional neural network (CNN) architectures for efficient multi-class and multi-label classification of 14 TB-related anomalies. Using 133 CXR images from Dr. Cipto Mangunkusumo National Central General Hospital and 214 images from the NIH datasets, we tackled data imbalance with augmentation, class weighting, and focal loss. The model achieved an accuracy of 0.911, a loss of 0.285, and an AUC of 0.510. Given the complexity of handling not only multi-class but also multi-label data with imbalanced and limited samples, the AUC score reflects the challenging nature of the task rather than any shortcoming of the model itself. By classifying the most distinct TB-related labels in a single AI study, this research highlights the potential of AI to enhance both the accuracy and efficiency of detecting TB-related anomalies, offering valuable advancements in combating this global health burden.

Schizophrenia has the main symptom of psychosis which is characterized by speech incoherence due to thought process disturbance. Before schizophrenia, there is a prodromal phase of psychosis in adolescence. Early recognition of this phase is important to prevent the development of symptoms into a severe mental disorder. Machine learning technology can be used to predict thought process disturbance through syntactic and semantic analysis of speech. This study aims to describe the differences in syntactic and semantic analysis in prodromal psychosis and normal adolescents. The research subjects consisted of 70 adolescents aged 14-19 years which were divided into 2 groups. Based on the results of the Prodromal Questionnaire-Brief (PQ-B) Indonesian version, the subjects were split into two groups: prodromal and normal. All participants were voice-recorded during interviews using an open-ended qualitative questionnaire. Syntactic and semantic analysis was carried out on all data which amounted to 1017 phrase segments and classified by machine learning. This is the first study in Indonesia to compare the analysis of syntactic and semantic aspects in prodromal psychosis and normal adolescent populations. There were significant differences in syntactic and semantic analysis between groups of adolescents with prodromal psychosis and normal adolescents at the minimum value of coherence and frequency of use of nouns, personal pronouns, subordinate conjunctions, adjectives, prepositions, and proper nouns.

Background: The artificial intelligence (AI) analysis of chest x-rays can increase the precision of binary COVID-19 diagnosis. However, it is unknown if AI-based chest x-rays can predict who will develop severe COVID-19, especially in low- and middle-income countries. Objective: The study aims to compare the performance of human radiologist Brixia scores versus 2 AI scoring systems in predicting the severity of COVID-19 pneumonia. Methods: We performed a cross-sectional study of 300 patients suspected with and with confirmed COVID-19 infection in Jakarta, Indonesia. A total of 2 AI scores were generated using CAD4COVID x-ray software. Results: The AI probability score had slightly lower discrimination (area under the curve [AUC] 0.787, 95% CI 0.722-0.852). The AI score for the affected lung area (AUC 0.857, 95% CI 0.809-0.905) was almost as good as the human Brixia score (AUC 0.863, 95% CI 0.818-0.908). Conclusions: The AI score for the affected lung area and the human radiologist Brixia score had similar and good discrimination performance in predicting COVID-19 severity. Our study demonstrated that using AI-based diagnostic tools is possible, even in low-resource settings. However, before it is widely adopted in daily practice, more studies with a larger scale and that are prospective in nature are needed to confirm our findings.

Disparities in the quality of healthcare persist globally, with poor-quality care contributing significantly to preventable mortality, particularly in low- and middle-income countries. While digital technologies, including generative artificial intelligence (AI), hold promise for improving clinical decision-making, their global effectiveness and potential to mitigate cross-country variation remain underexplored. We conducted a parallel-group randomized controlled trial across three economically diverse countries—Indonesia, Kenya, and the Netherlands—to evaluate the impact of large language model (LLM) access on physician performance using standardized clinical vignettes. Physicians (N=249) were randomly assigned to either a control group or an intervention group with access to GPT-4o. Results showed that LLM access significantly improved clinical performance, with the largest effect in Kenya (18%, 95% CI: 12.7 to 23.2, p < 0.001), followed by Indonesia (10.7%, 95% CI: 5.7 to 15.7, p < 0.001) and the Netherlands (7.2%, 95% CI: 3.7 to 10.7, p < 0.001). Notably, LLM access reduced cross-country performance disparities, particularly between Kenya and the Netherlands. However, distributional effects varied, with increased score dispersion in Indonesia and reduced variation in Kenya. Higher LLM usage was associated with greater performance gains, though some physicians without access outperformed those with access, suggesting that effective use depends on individual engagement. Our findings demonstrate that LLMs can enhance clinical performance across diverse settings while potentially narrowing global inequalities in care quality. Further research should explore mechanisms of effective LLM integration and long-term impacts on real-world clinical practice.

Diffusion tensor imaging (DTI) metrics provide insights into neural pathways, which can be pivotal in differentiating congenital and acquired hearing loss to support diagnosis, especially for those diagnosed late. In this study, we analyzed DTI parameters and developed machine learning to classify these two patient groups. The study included 29 patients with congenital hearing loss and 6 with acquired hearing loss. DTI scans were performed to obtain metrics, such as fractional anisotropy (FA), axial diffusivity (AD), radial diffusivity (RD), and mean diffusivity (MD). Statistical analyses based on p-values highlighted the cortical auditory system’s prominence in differentiating between groups, with FA and RD emerging as pivotal metrics. Three machine learning models were trained to classify hearing loss types for each of five dataset scenarios. Random forest (RF) trained on a dataset consisting of significant features demonstrated superior performance, achieving a specificity of 87.12% and F1 score of 96.88%. This finding highlights the critical role of DTI metrics in the classification of hearing loss. The experimental results also emphasized the critical role of FA in distinguishing between the two types of hearing loss, underscoring its potential clinical utility. DTI parameters, combined with machine learning, can effectively distinguish between congenital and acquired hearing loss, offering a robust tool for clinical diagnosis and treatment planning. Further research with larger and balanced cohorts is warranted to validate these findings.

Journal of Medical Internet Research - International Scientific Journal for Medical Research, Information and Communication on the Internet #Preprint #PeerReviewMe: Warning: This is a unreviewed preprint. Readers are warned that the document has not been peer-reviewed by expert/patient reviewers or an academic editor, may contain misleading claims, and is likely to undergo changes before final publication, if accepted, or may have been rejected/withdrawn. Readers with interest and expertise are encouraged to sign up as peer-reviewer, if the paper is within an open peer-review period. Please cite this preprint only for review purposes or for grant applications and CVs (if you are the author). Background: The artificial intelligence (AI) analysis of chest x-rays can increase the precision of binary COVID-19 diagnosis. However, it is unknown if AI-based chest x-rays can predict who will develop severe COVID-19, especially in low- and middle-income countries. Objective: The study aims to compare the performance of human radiologist Brixia scores versus 2 AI scoring systems in predicting the severity of COVID-19 pneumonia. Methods: We performed a cross-sectional study of 300 patients suspected with and with confirmed COVID-19 infection in Jakarta, Indonesia. A total of 2 AI scores were generated using CAD4COVID x-ray software. Results: The AI probability score had slightly lower discrimination (area under the curve [AUC] 0.787, 95% CI 0.722-0.852). The AI score for the affected lung area (AUC 0.857, 95% CI 0.809-0.905) was almost as good as the human Brixia score (AUC 0.863, 95% CI 0.818-0.908). Conclusions: The AI score for the affected lung area and the human radiologist Brixia score had similar and good discrimination performance in predicting COVID-19 severity. Our study demonstrated that using AI-based diagnostic tools is possible, even in low-resource settings. However, before it is widely adopted in daily practice, more studies with a larger scale and that are prospective in nature are needed to confirm our findings. Trial Registration: