Explainable AI based automated segmentation and multi-stage classification of gastroesophageal reflux using machine learning techniques.

Presently, close to two million patients globally succumb to gastrointestinal reflux diseases (GERD). Video endoscopy represents cutting-edge technology in medical imaging, facilitating the diagnosis of various gastrointestinal ailments including stomach ulcers, bleeding, and polyps. However, the abundance of images produced by medical video endoscopy necessitates significant time for doctors to analyze them thoroughly, posing a challenge for manual diagnosis. This challenge has spurred research into computer-aided techniques aimed at diagnosing the plethora of generated images swiftly and accurately. The novelty of the proposed methodology lies in the development of a system tailored for the diagnosis of gastrointestinal diseases. The proposed work used an object detection method called Yolov5 for identifying abnormal region of interest and Deep LabV3+ for segmentation of abnormal regions in GERD. Further, the features are extracted from the segmented image and given as an input to the seven different machine learning classifiers and custom deep neural network model for multi-stage classification of GERD. The DeepLabV3+ attains an excellent segmentation accuracy of 95.2% and an F1 score of 93.3%. The custom dense neural network obtained a classification accuracy of 90.5%. Among the seven different machine learning classifiers, support vector machine (SVM) outperformed with classification accuracy of 87% compared to all other class outperformed combination of object detection, deep learning-based segmentation and machine learning classification enables the timely identification and surveillance of problems associated with GERD for healthcare providers.

Clinical profile of 1208 newly diagnosed colorectal cancer patients in Tamil Nadu-A multi-centric survey.

BACKGROUND: An increasing incidence of colorectal cancer (CRC) is being reported in developing countries, including India. Most Indian studies on CRC are retrospective and single-centered. The present study is an attempt to understand the current clinical profile and stage of newly diagnosed CRCs across multiple centers in Tamil Nadu, India. METHODS: A multi-centric observational survey was conducted between September 1, 2021, and August 31, 2022, under the aegis of the Indian Society of Gastroenterology - Tamil Nadu chapter. Patients 18 years of age and older with a recent diagnosis of CRC fulfilling the inclusion criteria were prospectively recruited at the participating centers. Their demographic, clinical, biochemical, endoscopic, histopathologic, radiologic and risk factor details were systematically collected and analyzed. RESULTS: Across 23 centers in Tamil Nadu, 1208 patients were recruited. The male:female ratio was 1.49:1, while mean (SD) age was 57.7 (13.5) years. A majority (81.9%) were Tamils and 78.5% belonged to lower socioeconomic classes. The predominant symptoms were hematochezia (30.2%) and a change in bowel habits (27.5%). The most common locations were the rectum (34.3%) and rectosigmoid (15.1%). Synchronous CRCs were seen in 3.3% and synchronous colorectal polyps in 12.8%. Predisposing factors for CRC were seen in 2%. A past history of any cancer among CRC patients was obtained in 3.1% and a family history of any cancer was found in 7.6%. Patients who were either overweight or obese constituted 46.4% of the study population. At presentation, the predominant stages were stage III (44.7%) and stage IV (20.8%). CONCLUSIONS: A majority of patients with newly diagnosed CRC in Tamil Nadu belonged to the lower socioeconomic classes. About 60% had CRCs located within the reach of the flexible sigmoidoscope. Two-thirds of the patients exceeded stage II disease at presentation. TRIAL REGISTRATION: Not applicable.