Dola Saha

Dola Saha

Auto-generated profile, based on publicly available information

Dola Saha

Department of Health Information Management, Manipal College of Health Professions Manipal Karnataka 576104 Manipal Academy of Higher Education

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
5 February 2025 in F1000Research
Verified
Journal Article
Open access
PDF file
RRRinsy Rahman
Rinsy Rahman
DSDola Saha
Dola Saha
WDWinniecia Dkhar
Winniecia Dkhar
SMSathyendranath Malli
Sathyendranath Malli
NANeil Barnes Abraham
Neil Barnes Abraham
Background Breast cancer remains a significant global health concern, with over 7.8 million cases reported in the last five years. Early detection and accurate classification are crucial for reducing mortality rates and improving outcomes. Machine learning (ML) has emerged as a transformative tool in medical imaging, enabling more efficient and accurate diagnostic processes. Objective This study aims to develop a machine learning-based predictive model for early detection and classification of breast cancer using the Wisconsin Breast Cancer Diagnostic dataset. Methods The dataset, comprising 569 samples and 32 features derived from fine needle aspirate biopsy images, was pre-processed through data cleaning, normalization using the Robust Scaler, and feature selection. Five supervised ML algorithms—Logistic Regression, Support Vector Classification (SVC) with linear and radial basis function (RBF) kernels, Decision Tree, and Random Forest—were implemented. Models were evaluated using performance metrics, including accuracy, precision, sensitivity, specificity, and F1 scores. Results The SVC-RBF model demonstrated the highest accuracy (98.68%) and balanced performance across other metrics, making it the most effective classifier for distinguishing between benign and malignant tumors. Key features such as texture mean and area (worst) significantly contributed to classification accuracy. Conclusions This study highlights the potential of ML algorithms, particularly SVC-RBF, to revolutionize breast cancer diagnostics through improved accuracy and efficiency. Future research should validate these findings with diverse datasets and explore their integration into clinical workflows to enhance decision-making and patient care.

26 August 2026 in International Journal of Sports Science & Coaching
Verified
Journal Article
Open access
TMTanugatri Majumder
Tanugatri Majumder
DSDola Saha
Dola Saha
DNDionne A Noordhof
Dionne A Noordhof
ØSØyvind Sandbakk
Øyvind Sandbakk
Objective: To explore how elite Indian female badminton athletes and their coaches perceive the menstrual cycle (MC), its influence on training and performance, and the communication dynamics surrounding it, using focus group discussions (FGDs). Methods: Eight elite female athletes and six national-level coaches from three premier Indian badminton academies participated in separate FGDs. Discussions were moderated by an all-female research team, audio-recorded, transcribed verbatim, and thematically analysed using an inductive approach. Results: Five themes emerged: (1) perceived relevance of the MC in elite badminton in India, (2) influence of MC on training and performance, (3) MC-related practices and integration into training planning, (4) communication dynamics around the MC in training settings, and (5) personal reflections through lived experiences. Athletes acknowledged phase-specific changes in physical and emotional states but reported persistent discomfort discussing the MC with male coaches. Coaches demonstrated growing awareness but limited phase-specific understanding and tended to equate the MC with the bleeding phase. Across both groups, “open conversation” emerged as a shared indicator of progress toward destigmatization. Conclusion: Despite increasing awareness, the MC remains under-discussed and under-integrated into training systems within the Indian elite badminton community. Findings underscore the need for structured MC education, trust-based communication strategies, and individualised training modifications. Embedding these within high-performance environments may promote athlete well-being, equitable communication, and sustainable performance.

23 June 2026 in F1000Research
Verified
Journal Article
Open access
RRRinsy Rahman
Rinsy Rahman
DSDola Saha
Dola Saha
WDWinniecia Dkhar
Winniecia Dkhar
SMSathyendranath Malli
Sathyendranath Malli
NANeil Barnes Abraham
Neil Barnes Abraham
Background Breast cancer remains a significant global health concern, with over 7.8 million cases reported in the last five years. Early detection and accurate classification are crucial for reducing mortality rates and improving outcomes. Machine learning (ML) has emerged as a transformative tool in medical imaging, enabling more efficient and accurate diagnostic processes. Objective This study aims to develop a machine learning-based predictive model for early detection and classification of breast cancer using the Wisconsin Breast Cancer Diagnostic dataset. Methods The dataset, comprising 569 samples and 33 features derived from fine needle aspirate biopsy images, was pre-processed through data cleaning, normalization using the Robust Scaler, and feature selection. Five supervised ML algorithms—Logistic Regression, Support Vector Classification (SVC) with linear and radial basis function (RBF) kernels, Decision Tree, and Random Forest—were implemented. Models were evaluated using performance metrics, including accuracy, precision, sensitivity, specificity, and F1 scores. Results The SVC-RBF model demonstrated the highest accuracy (98.68%) and balanced performance across other metrics, making it the most effective classifier for distinguishing between benign and malignant tumors. Key features such as texture mean and area (worst) significantly contributed to classification accuracy. Conclusions This study highlights the potential of ML algorithms, particularly SVC-RBF, to revolutionize breast cancer diagnostics through improved accuracy and efficiency. Future research should validate these findings with diverse datasets and explore their integration into clinical workflows to enhance decision-making and patient care.

9 May 2026 in F1000Research
Verified
Journal Article
Open access
PDF file
RRRinsy Rahman
Rinsy Rahman
DSDola Saha
Dola Saha
WDWinniecia Dkhar
Winniecia Dkhar
SMSathyendranath Malli
Sathyendranath Malli
NANeil Barnes Abraham
Neil Barnes Abraham
Background Breast cancer remains a significant global health concern, with over 7.8 million cases reported in the last five years. Early detection and accurate classification are crucial for reducing mortality rates and improving outcomes. Machine learning (ML) has emerged as a transformative tool in medical imaging, enabling more efficient and accurate diagnostic processes. Objective This study aims to develop a machine learning-based predictive model for early detection and classification of breast cancer using the Wisconsin Breast Cancer Diagnostic dataset. Methods The dataset, comprising 569 samples and 32 features derived from fine needle aspirate biopsy images, was pre-processed through data cleaning, normalization using the Robust Scaler, and feature selection. Five supervised ML algorithms—Logistic Regression, Support Vector Classification (SVC) with linear and radial basis function (RBF) kernels, Decision Tree, and Random Forest—were implemented. Models were evaluated using performance metrics, including accuracy, precision, sensitivity, specificity, and F1 scores. Results The SVC-RBF model demonstrated the highest accuracy (98.68%) and balanced performance across other metrics, making it the most effective classifier for distinguishing between benign and malignant tumors. Key features such as texture mean and area (worst) significantly contributed to classification accuracy. Conclusions This study highlights the potential of ML algorithms, particularly SVC-RBF, to revolutionize breast cancer diagnostics through improved accuracy and efficiency. Future research should validate these findings with diverse datasets and explore their integration into clinical workflows to enhance decision-making and patient care.

1 May 2020 in Biological Psychiatry
Verified
Journal Article
Closed access
DNDylan Nielson
Dylan Nielson
HKHanna Keren
Hanna Keren
GOGeorgia O'Callaghan
Georgia O'Callaghan
SJSarah M. Jackson
Sarah M. Jackson
DSDipta Saha
Dipta Saha
ASArgyris Stringaris
Argyris Stringaris

1 May 2020 in Biological Psychiatry
Verified
Journal Article
Closed access
CZCharles Zheng
Charles Zheng
DSDipta Saha
Dipta Saha
DNDylan Nielson
Dylan Nielson
HKHanna Keren
Hanna Keren
FPFrancisco Pereira
Francisco Pereira
PSPer Sederberg
Per Sederberg