Articles

Multiclass Diabetes Classification using Multimodal Artificial Intelligence

/in /by

Diabetes mellitus is a prevalent metabolic disorder globally. Its primary etiologies encompass socioeconomic determinants, behavioral risk factors, and underlying comorbidities. Numerous epidemiological studies have investigated various diabetes phenotypes, impacting both sexes across the entire age spectrum. This study utilizes a dataset containing clinical profiles of 1,000 subjects assessed on multiple biometric and sociodemographic variables. The objective is to classify diabetes into type 1, type 2, and prediabetes using an array of deep learning and machine learning algorithms. Currently, artificial intelligence-driven diagnostic methods represent a state-of-the-art approach for disease stratification. This research evaluates the performance of six classification algorithms for determining glycemic status: random forest (RF), support vector machine (SVM), extreme gradient boosting (XGBoost), convolutional neural network (CNN), recurrent neural network (RNN), and long short-term memory (LSTM) network. Results demonstrate that the XGBoost classifier attained the highest predictive accuracy of 91% with a training duration of 20 seconds, surpassing the other models. These findings underscore the potential of advanced computational algorithms for precise diabetes phenotyping and risk assessment, offering significant implications for disease management and public health interventions.

Pulmonary Hernia Following Blunt Chest Trauma

/in /by

Defined as a protrusion of the lung parenchyma through the chest wall, traumatic lung hernias constitute a rarely described condition occurring more from penetrating rather than blunt trauma. We report the case of a 17-year-old patient with no prior medical history who was admitted to the emergency department following a motorcycle accident with a protruding thoracic mass. Clinical examination found a soft, reducible bulge on the left anterior 4th intercostal space. A CT scan of the chest demonstrated rib fractures with no lung or muscle laceration. Surgical correction of the defect allowed total disappearance of the bulge, as well as significant pain management, and postoperative recovery was satisfactory. Post-traumatic intercostal lung herniation is a poorly described, challenging entity for which minimally invasive surgical correction of the chest wall defect and reduction of the hernia should be considered whenever feasible.

Comparison of Microscopic Accuracy, Rapid Diagnostic Test (RDT), Polymerase Chain Reaction (PCR), and Loop-Mediated Isothermal Amplification (LAMP) in Malaria Diagnosis: A Literature Review

/in /by

Malaria is an infectious disease that remains a global public health problem, especially in tropical and subtropical countries such as Indonesia. This disease is caused by the Plasmodium parasite, which is transmitted through the bite of infected female Anopheles mosquitoes. According to the 2024 World Malaria Report, there were approximately 249 million cases of malaria and 597,000 deaths worldwide, with Indonesia accounting for approximately 1.8 million cases or 46% of the total cases in Southeast Asia. This condition shows that malaria is still a major challenge in the national health system, especially in endemic areas such as Papua, Nusa Tenggara, and parts of Kalimantan. Rapid and accurate diagnosis of malaria is crucial in reducing morbidity and mortality rates. Peripheral blood microscopy is still considered the gold standard because it can identify Plasmodium species and assess the degree of parasitemia, but its sensitivity decreases in infections with low parasite density. Advances in diagnostic methods have led to the development of Rapid Diagnostic Tests (RDTs), which detect specific parasite antigens and provide rapid results, although the results can be affected by HRP2 gene mutations and reagent storage conditions. Furthermore, molecular methods such as Polymerase Chain Reaction (PCR) offer the highest sensitivity with the ability to detect up to 0.25–5 parasites/µL, but require advanced laboratory facilities. The latest innovation, Loop-Mediated Isothermal Amplification (LAMP), can amplify parasite DNA at a constant temperature of 60–65°C without a thermal cycler, with sensitivity and specificity reaching 95–99%. Therefore, this literature review highlights that a combination of conventional and molecular methods is essential to improve diagnostic accuracy and support malaria elimination efforts in Indonesia.

A Review of AI-powered Diagnosis of Rare Diseases

/in /by

The diagnosis of rare diseases presents significant challenges due to their low prevalence, complex symptomatology, and the scarcity of specialized knowledge. However, advancements in Artificial Intelligence (AI) offer promising solutions to these challenges. This review explores the current state of AI-powered diagnostic tools for rare diseases, focusing on the methodologies, algorithms, and platforms utilized in this emerging field. We examine how AI technologies, such as machine learning, deep learning, and natural language processing, are being integrated into clinical practice to enhance diagnostic accuracy and speed. The research also provides the examples that highlight the successes and limitations of AI in this domain, providing insights into how AI can be harnessed to improve patient outcomes in rare disease diagnosis and management.

The Function of Apparent Diffusion Coefficient and Diffusion-Weighted Imaging in Distinguishing between Different Types of Brain Tumors

/in /by

Introduction: The second most common cause of mortality globally is tumors, and early detection is crucial for improving outcomes. Brain tumors, characterized by abnormal cell growth in the brain, can be either benign or malignant. Although conventional MRI techniques are routinely used for diagnosis, they often lack the sensitivity needed for tumor grading and characterization. By determining the apparent diffusion coefficient (ADC) value for each tumor and contrasting these results with the final histology result, this study seeks to evaluate the function of Diffusion Weighted Imaging (DWI) in differentiating between common brain tumors in patients.

Methods: A retrospective analysis was conducted involving thirty-four patients who underwent MRI examinations, including conventional and DWI, at a diagnostic radiology department between January 2022 and December 2024. The study employed a 1.5-T magnetic resonance scanner, with DWI analyzed using calculated ADC values. Data on demographics, MRI characteristics, and histopathological findings were collected and analyzed using SPSS Version 27.

Results: Whole-lesion ADC center values ranged 0.470–2.854 × 10−3 mm2/s higher values in dysembryoplastic neuroepithelial tumor and lower in abscess, AS for ADC border values ranged 0.770–1.672 × 10−3 mm2/s higher values in pilocytic astrocytoma and lower in malignant meningioma. These results demonstrated the value of ADC in brain lesion differential diagnosis.

Conclusion: DWI and ADC are excellent supplementary imaging modalities because they are quick, simple, non-invasive, and require no contrast injection. It might be able to distinguish between various brain lesions, facilitating prompt diagnosis and care.

Gastroenteritis: A Comprehensive Review

/in /by

Gastroenteritis, commonly referred to as stomach flu, is an acute inflammation of the gastrointestinal tract, marked by symptoms including diarrhea, vomiting, abdominal cramps, and fever. This review article provides a comprehensive overview of gastroenteritis, addressing its etiology, epidemiology, pathophysiology, diagnosis, management, and prevention strategies. The condition is caused by a variety of infectious agents such as viruses (noroviruses, rotaviruses), bacteria (Campylobacter, Salmonella), and parasites (Giardia lamblia), with transmission typically occurring through contaminated food, water, or person-to-person contact. Globally, gastroenteritis remains a significant public health issue, with high morbidity and mortality rates, particularly in children under five in developing countries. Diagnosis often relies on clinical evaluation and laboratory tests, while management focuses on rehydration therapy and symptomatic relief. Preventive measures include personal hygiene, food safety practices, environmental sanitation, and vaccination, with rotavirus vaccines significantly reducing severe cases in children. Emerging trends in gastroenteritis research aim at developing rapid diagnostic tools, novel therapeutic approaches, and new vaccines, highlighting the importance of a multidisciplinary approach to mitigate the global impact of this disease.

Potential Biomarkers for Diagnosis and Prognosis of Acute Myeloid Leukemia

/in /by

For many years, cancer has affected the global population from an economic, social and political point of view and, in most cases, it is a malignant tumor with serious consequences for patients. The objective of this study is to answer the potential biomarkers for the diagnosis and prognosis of acute myeloid leukemia. Therefore, this is an exploratory, descriptive bibliographic study with a qualitative approach. The data were collected from a bibliometric survey carried out during a study of scientific production on the proposed topic from 2013 to 2023. After searching for articles, 210 articles were found on the PubMed platform, and no results were found for the key suggested by word in other databases. Among the 210 articles, 28 articles were selected for review. In this way, we seek to analyze which biomarkers have been addressed in the last 10 years in the scientific literature, thus aiming to demonstrate possible targets for new research. We divide our research into genes that are promising biomarkers for diagnosis and/or prognosis and the role of miRNAs as biomarkers.

The Effectiveness of MRI Techniques in Evaluating Multiple Sclerosis Patients

/in /by

: Background and objective: Multiple sclerosis (MS) is the most common neurodegenerative disease characterized by multiple focal areas of demyelination called plaques or lesions. The main aim of the study is to evaluate patients with multiple sclerosis disease using MRI technology   and to emphasis the effectiveness of this technology in diagnosis of the disease.

Methods:  This study was conducted in order to better recognition and understanding of MS disorder using radiologic MRI techniques and the main problem is the increase prevalence among public population   . The database registry was limited to hospitalized  patients whom diagnosed with  multiple sclerosis  using MRI techniques  and the population of the study was 80 participants  their age elder than 16 years old  in period from April  to  November  2020 .Normal condition or other neurological disorders were excluded.

Results: The most important results obtained in this study is that it is possible to diagnose Multiple sclerosis patients in an accurate manner using magnetic resonance imaging technology.  The outcome of variable detected prevalence of 80 samples 52.5% of them were male, and 47.5% were female and the big distribution group was 53% aged between 30-39 years. The obtained data also showed that the most affected brain region was periventricular matter with 30%, followed by the frontal lobe with 27.5%. clinical etiology big distribution data were achieved for vision Problems with percentage of   22.5 % followed by Dizziness & vertigo sensation with percentage of 18.7% The MRI techniques showed two appearance of MS lesions and plaques, the most distribution achieved for foci appearance with percentage of 75% and patchy appearance with 25% present.

Conclusion: Although for many years there was awareness of the morbidity and mortality associated with Multiple sclerosis however real progress only comes with the ability to early diagnosis using MRI technology.