Fortis Healthcare

Background: Cardiovascular disease (CVD) remains the leading cause of death and disability worldwide. Among its subtypes, coronary artery disease (CAD) is the most common and often develops silently, without noticeable symptoms. CAD-related murmurs typically fall below the human hearing threshold, limiting the effectiveness of traditional stethoscope-based auscultation. Currently, the gold standard for CAD diagnosis is coronary angiography, an invasive and expensive procedure usually reserved for symptomatic patients. This highlights the global need for a non-invasive, cost-effective pre-screening tool for asymptomatic CAD detection. Objectives: This study investigates the effectiveness of a wearable vest equipped with multiple digital stethoscopes to detect CAD. By applying signal processing and machine learning to multichannel phonocardiogram (PCG) data, we aim to evaluate the accuracy of CAD detection. We further assess the impact of incorporating patient metadata to enhance model performance. Methods: Data were collected from 40 CAD patients and 40 non-CAD individuals using a wearable vest with seven embedded PCG sensors. Subjects performed 10 s breath-hold recordings in a clinical setting. Linear-frequency cepstral coefficients were extracted from the PCG signals and classified using a support vector machine. Metadata, including body mass index, blood pressure, type 2 diabetes, and hypertension, were integrated to assess performance gains. Results: A combination of four channels achieved an accuracy of 80.44%, a 7% improvement over the best single-channel result. Incorporating metadata increased accuracy to 82.08%. Conclusions: The wearable vest demonstrated promising clinical potential, exceeding a 75% sensitivity-specificity average, and may support accessible, automated CAD screening in future validated settings.

e16231 Background: Gallbladder carcinomas (GBC) are the predominant biliary tract malignancies with marked geographic variation and a female-biased, middle-aged patient population. Most patients present with advanced disease, and adjuvant chemotherapy offers limited survival benefit. Mutation profiling can reveal actionable alterations and immunogenomic contexts to guide precision therapeutics and potential trial design. Methods: This study analyzed 115 FFPE-tumor samples from patients undergoing treatment for GBC across multiple hospitals in India, who had opted to undergo molecular genetic testing for somatic variants with 4baseCare’s comprehensive gene panels. Results: The cohort was predominantly female (70.3%), particularly 50 and older (73.07%), and largely derived (85.5%) from high-incidence regions of India. Nearly all patients (98.5%) presented with stage IV disease; adenocarcinoma was the most predominant histological type (61%) Among the IHC markers tested, CK7 and CK19 were frequently positive in evaluated samples, while CK20 and PD-L1 were largely negative. Recurrent genomic alterations included ERBB2 (10.7%), BRCA2 (6.8%), SMAD4 (6.8%), CDKN2A (3.9%), and MDM2 (3.9%), with copy-number amplifications involving ERBB2 and MDM2. Most commonly affected pathways were cell-cycle regulation (37%), RTK signaling (16%), PI3K/AKT/mTOR signaling (11%), DNA damage repair (7%), and chromatin remodeling/DNA methylation (6%). TMB was predominantly low, with only 4.8% demonstrating high TMB. 93.1% samples in a subset were microsatellite marker stable. Overall, 4.76% of samples harbored alterations potentially targetable with FDA-approved therapies. Conclusions: The data reveal a predominance of mutations in RTK/cell-cycle–DNA damage pathways indicating that GBC patients may benefit from targeted therapy. Although actionable targets were identified in a minority of cases, CGP delineates clinically relevant subsets that may benefit from targeted agents, pathway-directed therapies, or immunotherapy where biomarkers align. Routine integration of CGP in advanced GBC may refine treatment selection, improve trial stratification, and support biomarker-driven precision oncology approaches in this high-incidence population.

Coronary artery disease (CAD) remains one of the leading causes of mortality worldwide. Phonocardiogram (PCG) signals offer a non-invasive, affordable, and accessible means for early detection of CAD. However, the diverse acoustic manifestations of the disease across different auscultation sites make accurate diagnosis using a single-channel stethoscope challenging. Moreover, the scarcity of large annotated datasets further limits the development of robust diagnostic models. This work presents a multichannel CAD detection framework using transfer learning that leverages both early/late fusion from multiple auscultation sites. A lightweight pretrained deep learning model is designed to address data scarcity and enable computationally efficient deployment. We explore early and late fusion strategies to extract the channel-wise collective information in detecting CAD. The proposed system achieves a 9.46

Objectives In vitro fertilisation (IVF) cycles employ different ovarian stimulation protocols to promote follicle development and boost the number of embryos. Anticipating ovarian response is crucial for maximising treatment effectiveness and minimising complications from under- or over-stimulation. Age, anti-Müllerian hormone (AMH), and antral follicle count (AFC) are well-known assessors of ovarian response, which makes them established predictors of ovarian response. The Ovarian Response Prediction Index (ORPI) combines these factors to provide a more tailored approach to stimulation protocols, potentially enhancing IVF success rates. Material and Methods It was a retrospective cohort study that included 302 patients undergoing IVF/ICSI cycles between March 2021 and March 2023. Patients aged < 39 years, with a body mass index (BMI) of 20–30 kg/m², regular menstrual cycles, and no history of ovarian surgery or severe endometriosis were included. AMH levels were measured using chemiluminescent immunoassay, and AFC was assessed by transvaginal ultrasound. ORPI was calculated as (AMH × AFC)/age. Outcomes included total retrieved oocytes, metaphase II (MII) oocytes, and clinical pregnancy rates. Results Strong positive correlations were found between ORPI and both total oocytes (r = 0.714, p < 0.0001) and MII oocytes (r = 0.746, p < 0.0001). Univariate logistic regression indicated that age, AMH, AFC, and ORPI were significant predictors of obtaining ≥ 4 oocytes and MII oocytes (p < 0.05). Receiver operating characteristic curve analysis demonstrated that ORPI has excellent discriminative ability for predicting ≥4 oocytes (AUC = 0.907), ≥4 MII oocytes (AUC = 0.937), and clinical pregnancy (AUC = 0.822), with optimal cutoff values established. Conclusion ORPI, which combines age, AMH, and AFC, strongly predicts ovarian response and clinical pregnancy in IVF/ICSI cycles. It can help formulate personalised ovarian stimulation protocols, potentially enhancing patient counselling and treatment outcomes.

Data on pediatric/adolescent von Hippel-Lindau (VHL) disease is sparse, and surveillance/management recommendations rely on expert opinions/extrapolations from adults. We aimed to characterize the childhood/adolescent VHL disease phenotype, compare it with adults, and identify genotype-phenotype correlations. Retrospective review of children/adolescents (≤ 19 years) and adults with VHL disease from a single endocrine center (2000–2024). Only neoplasms diagnosed until age 19 years were included in the childhood/adolescent group and compared with the last follow-up of adults. Twenty-six children/adolescents (median age:15.5 years) were identified. By age 19 years, 81