API module to Potential Prediction of Diabetes Risk through AI-Enhanced Assessment of Pancreatic Density and Visceral Fat on Computed Tomography Scans, Correlating with Glycated Haemoglobin Levels
试验速览
- 阶段
- 不适用
- 状态
- 尚未招募
- 发起方
- 入组人数
- 100
- 试验地点
- 1
- 主要终点
- To predict the risk of diabetes mellitus using AI-driven analysis of pancreatic density and visceral fat from CT scans
研究概览
简要总结
An innovative API module designed to predict the risk of diabetes mellitus through the analysis of pancreatic density and visceral fat area extracted from CT abdomen scans. The module employs advanced artificial intelligence algorithms to assess these parameters, which are crucial indicators of diabetes risk.
Pancreatic density is quantified in Hounsfield Units (HU), while visceral fat area is measured at the level of the umbilicus in square centimeters (cm²) from CT scans. These measurements are then compared to established normal ranges. The correlation between pancreatic density, visceral fat area, and the risk of diabetes mellitus has been extensively studied and validated in medical literature.
The API module utilizes machine learning algorithms trained on large datasets to accurately interpret and analyze CT scan images. By correlating pancreatic density and visceral fat area with known risk factors for diabetes mellitus, the module generates a binary prediction: either a positive indication for diabetes risk ("yes") or a negative indication ("no").
This invention aims to provide healthcare professionals with a reliable and efficient tool for early diabetes risk assessment, enabling timely intervention and personalized patient care. The scalability and accessibility of the API module ensure its seamless integration into existing healthcare systems, facilitating widespread adoption in clinical settings.
By harnessing the power of AI and advanced imaging techniques, this patent application represents a significant advancement in diabetes risk assessment, ultimately contributing to improved patient outcomes and healthcare management.
研究设计
- 研究类型
- Observational
入排标准
- 年龄范围
- 15.00 Year(s) 至 90.00 Year(s)（—）
- 性别
- All
入选标准
- •1.Population Criteria: Individuals with varying degrees of risk for diabetes.
- •Patients who have undergone CT scans for abdominal imaging.
- •Patients with available glycated haemoglobin (HbA1c) levels, including normal, prediabetic, and diabetic ranges.
- •2.Medical History: Patients with medical records indicating a history of diabetes or prediabetes.
- •Patients with no prior history of diabetes to evaluate predictive capabilities.
- •3.CT Scan Data: High-quality CT scan images with clear visualization of pancreatic structures and visceral fat.
- •4.Ethnicity and Demographics: Consideration of diverse ethnic and demographic backgrounds to ensure the generalizability of the predictive model.
排除标准
- •1.Pregnancy: Excluding pregnant individuals to avoid radiation exposure.
- •2.Presence of Other Chronic Diseases: Excluding individuals with chronic diseases (e.g., cancer) that may confound the relationship between pancreatic density, visceral fat, and diabetes risk.
- •3.Recent Major Surgery: Excluding individuals who have undergone recent major surgery, particularly those involving the pancreas or abdominal organs, as this can affect pancreatic density and visceral fat distribution.
- •4.Unreliable CT Scan Quality: Excluding individuals with CT scans of poor quality or artifacts that may compromise accurate assessment of pancreatic density and visceral fat.
- •5.Inability to Provide Relevant Laboratory Data: Excluding individuals who cannot provide laboratory data, which is essential for correlating CT findings with glycated hemoglobin levels and diabetes risk.
结局指标
主要结局
To predict the risk of diabetes mellitus using AI-driven analysis of pancreatic density and visceral fat from CT scans
时间窗: 24 hours
次要结局
- To assess the accuracy & clinical utility of the AI model by correlating the predictions with glycated hemoglobin (HbA1c) levels(1 week)
研究者
Ajina Sam
Saveetha medical college and hospital, Saveetha institute of medical and technical sciences.