Vinay R Srihari
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Vinay R Srihari has a total of 10 co-authors. Here are the top co-authors by number of shared publications:
- Akash Gajanan Prabhune
ADMIRE, IIHMR Bangalore, Bangalore, India
5 shared publications - Akhila Rayampalli
ADMIRE, IIHMR Bangalore, Bangalore, India
2 shared publications - Mansi Gauniyal
Foundation of Healthcare Technologies Society, Delhi, India
2 shared publications - Neeraj Kumar Sethiya
DIT University
2 shared publications - Adith Vijay
ADMIRE, IIHMR Bangalore, Bangalore, India
1 shared publication Ankur Thakur
ADMIRE Centre for Advancing Digital Health, Institute of Health Management Research, Bangalore (IIHMR-B), Bengaluru, India
1 shared publication
Latest Publications
- Open Access
FootNet: A Multi-View Smartphone Dataset and Four-Model Benchmark for Clinical Foot Segmentation
We present FootNet, a 453-image multi-view smart-phone foot dataset for binary foot segmentation, with expert-annotated masks across six anatomical views (dorsal, medial, and plantar, both left and right). We benchmark four segmentation models under a controlled protocol: U-Net with a MobileNetV2 encoder achieves the best performance (IoU 0.9268, Dice 0.9608, 95% CI [0.9209, 0.9320]); DeepLabV3 with MobileNetV3-Large scores IoU 0.8984 (Dice 0.9449); UNet++ with MobileNetV2 scores IoU 0.8913 (Dice 0.9391); and SAM ViT-B with oracle bounding-box prompt scores IoU 0.9219 on the matched 191-image sub-set. Bonferroni-corrected Wilcoxon signed-rank tests ( k = 6 comparisons) show U-Net significantly outperforms DeepLab ( p < 0.001, r = 0.638) and SAM ViT-B with oracle bounding-box ( p = 0.005, r = 0.202); UNet++ does not significantly differ from DeepLab ( p = 0.062). Connected-component post-processing yields negligible benefit (mean ΔIoU = +0.0003, 12 of 453 images improved). The extended dataset is available upon request.
Open AccessFootNet: A Multi-View Smartphone Dataset and Four-Model Benchmark for Clinical Foot Segmentation
We present FootNet, a 453-image multi-view smart-phone foot dataset for binary foot segmentation, with expert-annotated masks across six anatomical views (dorsal, medial, and plantar, both left and right). We benchmark four segmentation models under a controlled protocol: U-Net with a MobileNetV2 encoder achieves the best performance (IoU 0.9268, Dice 0.9608, 95% CI [0.9209, 0.9320]); DeepLabV3 with MobileNetV3-Large scores IoU 0.8984 (Dice 0.9449); UNet++ with MobileNetV2 scores IoU 0.8913 (Dice 0.9391); and SAM ViT-B with oracle bounding-box prompt scores IoU 0.9219 on the matched 191-image sub-set. Bonferroni-corrected Wilcoxon signed-rank tests ( k = 6 comparisons) show U-Net significantly outperforms DeepLab ( p < 0.001, r = 0.638) and SAM ViT-B with oracle bounding-box ( p = 0.005, r = 0.202); UNet++ does not significantly differ from DeepLab ( p = 0.062). Connected-component post-processing yields negligible benefit (mean ΔIoU = +0.0003, 12 of 453 images improved). The extended dataset is available upon request.
- Open Access
- 31 January 2026
- Published by The Korean Society of Medical Informatics in Healthcare Informatics Research
- Vol. 32 (1) , 69-76
Development and Validation of a Predictive AI Framework for Diabetic Foot Ulcer Monitoring and Severity Assessment: A Step towards Self-monitoring and Primary Care Integration
Objectives: Diabetic foot ulcer (DFU) is a critical complication of diabetes that can lead to severe outcomes such as infection, amputation, and increased mortality if left untreated. Early detection and continuous monitoring are essential but remain challenging, especially in resource-limited settings such as India. This study developed and validated a deep learning algorithm to classify diabetic foot images into severity grades based on the International Working Group on the Diabetic Foot classification: grade 0 (healthy), grade 1 (mild), grade 2 (moderate), and grade 3 (severe).Methods: A dataset of 407 clinical images was collected from open-source platforms and clinics in South India and expanded to 612 images through data augmentation. The dataset was divided into training (70%), validation (15%), and testing (15%) subsets. Multiple machine learning models were tested, including MobileNet_V2, EfficientNet-b0, DenseNet121, ResNet_50, VGG16, and ViT_b_16.Results: Among the evaluated models, MobileNet_V2 demonstrated the highest validation accuracy (82%) and achieved an F1-score of 79% on the test set. Although the model showed strong training accuracy, minor overfitting was observed, particularly in distinguishing adjacent severity grades. To address this, dropout, batch normalization, and early stopping were employed. Overall, the model generalized well, showing high accuracy in detecting healthy cases and acceptable performance across ulcer severity grades.Conclusions: This study underscores the potential of machine learning-based tools to support frontline healthcare workers and facilitate patient self-monitoring in low-resource environments. Future work will focus on refining the model and integrating it into user-friendly applications.
- 31 January 2026
- Published by The Korean Society of Medical Informatics in Healthcare Informatics Research
- Vol. 32 (1) , 69-76
Open AccessDevelopment and Validation of a Predictive AI Framework for Diabetic Foot Ulcer Monitoring and Severity Assessment: A Step towards Self-monitoring and Primary Care Integration
Objectives: Diabetic foot ulcer (DFU) is a critical complication of diabetes that can lead to severe outcomes such as infection, amputation, and increased mortality if left untreated. Early detection and continuous monitoring are essential but remain challenging, especially in resource-limited settings such as India. This study developed and validated a deep learning algorithm to classify diabetic foot images into severity grades based on the International Working Group on the Diabetic Foot classification: grade 0 (healthy), grade 1 (mild), grade 2 (moderate), and grade 3 (severe).Methods: A dataset of 407 clinical images was collected from open-source platforms and clinics in South India and expanded to 612 images through data augmentation. The dataset was divided into training (70%), validation (15%), and testing (15%) subsets. Multiple machine learning models were tested, including MobileNet_V2, EfficientNet-b0, DenseNet121, ResNet_50, VGG16, and ViT_b_16.Results: Among the evaluated models, MobileNet_V2 demonstrated the highest validation accuracy (82%) and achieved an F1-score of 79% on the test set. Although the model showed strong training accuracy, minor overfitting was observed, particularly in distinguishing adjacent severity grades. To address this, dropout, batch normalization, and early stopping were employed. Overall, the model generalized well, showing high accuracy in detecting healthy cases and acceptable performance across ulcer severity grades.Conclusions: This study underscores the potential of machine learning-based tools to support frontline healthcare workers and facilitate patient self-monitoring in low-resource environments. Future work will focus on refining the model and integrating it into user-friendly applications.
- Open Access
- 18 March 2025
- Published by Springer Nature in BMC Health Services Research
- Vol. 25 (1) , 1-17
A web-based platform for optimizing healthcare resource allocation and workload management using agile methodology and WISN theory
Effective healthcare workforce management is critical for ensuring quality care delivery, particularly in resource-constrained settings. The World Health Organization’s (WHO) Workload Indicators of Staffing Need (WISN) methodology provides an evidence-based framework for optimizing staffing levels. However, manual implementation of the WISN methodology is labour-intensive, error-prone, and time-consuming. To address these challenges, the Platform for Resource Allocation and Optimization for Healthcare Facilities (PRAYOJN) platform was developed as a web-based tool to automate WISN calculations, streamline data analysis, and improve workforce planning. To develop and validate a web-based system that automates the WISN methodology for healthcare workforce planning. The PRAYOJN platform was developed using an agile methodology, structured over five iterative sprints. These sprints incorporated stakeholder feedback to refine system functionalities, ensuring adaptability to real-world healthcare needs. The platform integrates data for principal, supporting, and ancillary tasks to calculate staffing requirements. Key functionalities include automated computation of Available Work Time (AWT), Standard Workload (SW), Category Allowance Factor (CAF), and Individual Allowance Factor (IAF). Alpha testing validated usability and accuracy, while beta testing in a clinical phlebotomy department assessed real-world performance. The platform calculated an ideal staffing requirement of 15.53 Full-Time Equivalent (FTE) for the phlebotomy department, aligning closely with the current staff strength of 15 FTE. Agile development ensured iterative improvements, enhancing user interface (UI) and user experience (UX). Feedback highlighted the platform’s user-friendly design, with dynamic visualizations such as pie charts and bar graphs aiding workload interpretation. Users praised its efficiency, adaptability, and role in reducing calculation complexity. PRAYOJN modernizes and enhances WISN-based workforce planning by automating workload calculations, improving data visualization, and supporting real-time decision-making. Its scalability and intuitive interface position it as a valuable tool for optimizing staffing efficiency across diverse healthcare environments.
- 18 March 2025
- Published by Springer Nature in BMC Health Services Research
- Vol. 25 (1) , 1-17
Open AccessA web-based platform for optimizing healthcare resource allocation and workload management using agile methodology and WISN theory
Effective healthcare workforce management is critical for ensuring quality care delivery, particularly in resource-constrained settings. The World Health Organization’s (WHO) Workload Indicators of Staffing Need (WISN) methodology provides an evidence-based framework for optimizing staffing levels. However, manual implementation of the WISN methodology is labour-intensive, error-prone, and time-consuming. To address these challenges, the Platform for Resource Allocation and Optimization for Healthcare Facilities (PRAYOJN) platform was developed as a web-based tool to automate WISN calculations, streamline data analysis, and improve workforce planning. To develop and validate a web-based system that automates the WISN methodology for healthcare workforce planning. The PRAYOJN platform was developed using an agile methodology, structured over five iterative sprints. These sprints incorporated stakeholder feedback to refine system functionalities, ensuring adaptability to real-world healthcare needs. The platform integrates data for principal, supporting, and ancillary tasks to calculate staffing requirements. Key functionalities include automated computation of Available Work Time (AWT), Standard Workload (SW), Category Allowance Factor (CAF), and Individual Allowance Factor (IAF). Alpha testing validated usability and accuracy, while beta testing in a clinical phlebotomy department assessed real-world performance. The platform calculated an ideal staffing requirement of 15.53 Full-Time Equivalent (FTE) for the phlebotomy department, aligning closely with the current staff strength of 15 FTE. Agile development ensured iterative improvements, enhancing user interface (UI) and user experience (UX). Feedback highlighted the platform’s user-friendly design, with dynamic visualizations such as pie charts and bar graphs aiding workload interpretation. Users praised its efficiency, adaptability, and role in reducing calculation complexity. PRAYOJN modernizes and enhances WISN-based workforce planning by automating workload calculations, improving data visualization, and supporting real-time decision-making. Its scalability and intuitive interface position it as a valuable tool for optimizing staffing efficiency across diverse healthcare environments.
- Open Access
- 1 March 2025
- Published by Institute of Advanced Engineering and Science in International Journal of Public Health Science (IJPHS)
- Vol. 14 (1) , 479-492
Utilising consumer reviews for passive surveillance of foodborne illnesses: insights and challenges from the Indian restaurant
This study explores the feasibility of leveraging consumer reviews for passive surveillance of foodborne illnesses, drawing parallels with pharmacovigilance systems. Utilizing a mixed-methods approach, including a literature review, qualitative interviews with key stakeholders, and quantitative analysis of 56,000 restaurant reviews using a bidirectional encoder representation from transformers (BERT-based) aspect-based sentiment analysis model, the study seeks to understand the potential of social media data in enhancing food safety regulations. Despite the promise shown by the aspect-based analysis in identifying hygiene-related concerns, challenges such as data reliability, language diversity, and the absence of verifiable evidence limit the direct application of consumer reviews for regulatory purposes. Key informants highlighted the need for a tailored surveillance system, considering the Indian restaurant industry’s diversity and scale. The quantitative analysis revealed hygiene concerns in a significant portion of reviews, yet the specificity and verifiability of these complaints remain issues. The study suggests a cautious yet optimistic approach towards integrating social media data into foodborne illness surveillance, emphasizing the enhancement of traditional reporting mechanisms, targeted awareness campaigns, and industry collaboration. The findings advocate for a comprehensive strategy that includes developing a common platform for stakeholder communication and strengthening policy frameworks to support a collaborative surveillance system, particularly in developing contexts like India.
- 1 March 2025
- Published by Institute of Advanced Engineering and Science in International Journal of Public Health Science (IJPHS)
- Vol. 14 (1) , 479-492
Open AccessUtilising consumer reviews for passive surveillance of foodborne illnesses: insights and challenges from the Indian restaurant
This study explores the feasibility of leveraging consumer reviews for passive surveillance of foodborne illnesses, drawing parallels with pharmacovigilance systems. Utilizing a mixed-methods approach, including a literature review, qualitative interviews with key stakeholders, and quantitative analysis of 56,000 restaurant reviews using a bidirectional encoder representation from transformers (BERT-based) aspect-based sentiment analysis model, the study seeks to understand the potential of social media data in enhancing food safety regulations. Despite the promise shown by the aspect-based analysis in identifying hygiene-related concerns, challenges such as data reliability, language diversity, and the absence of verifiable evidence limit the direct application of consumer reviews for regulatory purposes. Key informants highlighted the need for a tailored surveillance system, considering the Indian restaurant industry’s diversity and scale. The quantitative analysis revealed hygiene concerns in a significant portion of reviews, yet the specificity and verifiability of these complaints remain issues. The study suggests a cautious yet optimistic approach towards integrating social media data into foodborne illness surveillance, emphasizing the enhancement of traditional reporting mechanisms, targeted awareness campaigns, and industry collaboration. The findings advocate for a comprehensive strategy that includes developing a common platform for stakeholder communication and strengthening policy frameworks to support a collaborative surveillance system, particularly in developing contexts like India.
- Open Access
- 1 April 2024
- Published by Institute of Advanced Engineering and Science in Indonesian Journal of Electrical Engineering and Computer Science
- Vol. 34 (1) , 602-619
Agile fusion: developing 'Eat at Right Place' sentiment analysis tool
This study presents the development and validation of the "Eat at Right Place Initiative," a sentiment analysis tool for restaurant reviews. Combining a user-centric approach with the Scrum framework, the mHealth agile development and evaluation framework was implemented, deviating from the initially considered Scrum framework. A multidisciplinary team navigated three phases, aligning sprints, goals, and backlogs. Phase 1 focused on product identification through interviews and surveys. Phase 2 involved development and alpha testing using a bidirectional encoder representation from transformers (BERT) rule-based sentiment analysis model. The final phase, beta testing, incorporated user feedback for usability enhancements. Ethical considerations were prioritized, ensuring participant consent and confidentiality. The study culminated in a robust aspect-based sentiment analysis model, effective in capturing nuanced insights from diverse restaurant aspects. Beta testing revealed actionable insights, marking the tool as fit for release. This sentiment analysis tool addresses consumer and owner needs, with iterative development and real-world testing laying the groundwork for future enhancements.
- 1 April 2024
- Published by Institute of Advanced Engineering and Science in Indonesian Journal of Electrical Engineering and Computer Science
- Vol. 34 (1) , 602-619
Open AccessAgile fusion: developing 'Eat at Right Place' sentiment analysis tool
This study presents the development and validation of the "Eat at Right Place Initiative," a sentiment analysis tool for restaurant reviews. Combining a user-centric approach with the Scrum framework, the mHealth agile development and evaluation framework was implemented, deviating from the initially considered Scrum framework. A multidisciplinary team navigated three phases, aligning sprints, goals, and backlogs. Phase 1 focused on product identification through interviews and surveys. Phase 2 involved development and alpha testing using a bidirectional encoder representation from transformers (BERT) rule-based sentiment analysis model. The final phase, beta testing, incorporated user feedback for usability enhancements. Ethical considerations were prioritized, ensuring participant consent and confidentiality. The study culminated in a robust aspect-based sentiment analysis model, effective in capturing nuanced insights from diverse restaurant aspects. Beta testing revealed actionable insights, marking the tool as fit for release. This sentiment analysis tool addresses consumer and owner needs, with iterative development and real-world testing laying the groundwork for future enhancements.