Babar Sultan Hasan
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Babar Sultan Hasan has a total of 97 co-authors. Here are the top co-authors by number of shared publications:
- Zahra Hoodbhoy
Department of Paediatrics and Child Health, Aga Khan University, Karachi, Pakistan
3 shared publications - Bistra Zheleva
Children’s HeartLink
2 shared publications - Brian A. Boe
Department of Cardiology, Joe DiMaggio Children's Hospital, Hollywood, Florida
2 shared publications Brian P. Quinn
Department of Cardiology, Boston Children's Hospital, Boston, Massachusetts, USA
2 shared publicationsFatima Ali
Division of Cardiothoracic Sciences, Sindh Institute of Urology and Transplantation (SIUT), Karachi, Pakistan
2 shared publicationsIgor Polivenok
Zaitcev V.T. Institute of General and Urgent Surgery and William Novick Global Cardiac Alliance, Kharkiv, Ukraine
2 shared publications
Latest Publications
- Open Access
- 22 July 2025
- Published by AccScience Publishing in Artificial Intelligence in Health
- Vol. 3 (1) , 77
Pediatric patient hospital length of stay prediction: A comparative analysis of Bayesian inference and machine learning approaches
Predicting patient length of stay (LoS) is crucial for optimizing resource allocation and enhancing healthcare efficiency. However, achieving accurate LoS predictions remains a challenging and complex task. This study presents a non-disease-specific predictive model that integrates machine learning (ML) methods and Bayesian inference techniques to accurately predict hospital LoS using static patient admission data. While traditional statistical regression techniques have been widely used for LoS prediction within hospital settings, this research investigates the capabilities of ML and Bayesian inference algorithms in this context. By leveraging Bayesian inference techniques, our model captures complex relationships within the data and quantifies uncertainty, offering a more nuanced understanding of the outcomes. This methodological approach offers a more comprehensive and probabilistically grounded framework for LoS prediction, allowing more informed decision-making in resource allocation and patient management. Among the evaluated models, extreme boosting and support vector machine regressor models demonstrated the highest efficiency, achieving mean squared logarithmic error (MSLE) values of 0.23 and 0.24, respectively. The Bayesian model also showed competitive performance with an MSLE of 0.25. While it did not outperform other models in terms of error metrics, the Bayesian model’s ability to provide additional uncertainty output enhances its utility, offering valuable supplementary information for informed decision-making. This research highlights the potential of ML and Bayesian inference in predicting patient LoS, emphasizing their significance in effective resource allocation and patient care management within the healthcare sector.
- 22 July 2025
- Published by AccScience Publishing in Artificial Intelligence in Health
- Vol. 3 (1) , 77
Open AccessPediatric patient hospital length of stay prediction: A comparative analysis of Bayesian inference and machine learning approaches
Predicting patient length of stay (LoS) is crucial for optimizing resource allocation and enhancing healthcare efficiency. However, achieving accurate LoS predictions remains a challenging and complex task. This study presents a non-disease-specific predictive model that integrates machine learning (ML) methods and Bayesian inference techniques to accurately predict hospital LoS using static patient admission data. While traditional statistical regression techniques have been widely used for LoS prediction within hospital settings, this research investigates the capabilities of ML and Bayesian inference algorithms in this context. By leveraging Bayesian inference techniques, our model captures complex relationships within the data and quantifies uncertainty, offering a more nuanced understanding of the outcomes. This methodological approach offers a more comprehensive and probabilistically grounded framework for LoS prediction, allowing more informed decision-making in resource allocation and patient management. Among the evaluated models, extreme boosting and support vector machine regressor models demonstrated the highest efficiency, achieving mean squared logarithmic error (MSLE) values of 0.23 and 0.24, respectively. The Bayesian model also showed competitive performance with an MSLE of 0.25. While it did not outperform other models in terms of error metrics, the Bayesian model’s ability to provide additional uncertainty output enhances its utility, offering valuable supplementary information for informed decision-making. This research highlights the potential of ML and Bayesian inference in predicting patient LoS, emphasizing their significance in effective resource allocation and patient care management within the healthcare sector.
- Open Access
- 21 March 2025
- Published by Elsevier in JACC: Advances
- Vol. 4 (4) , 101649
Comparative Congenital Cardiac Catheterization Registry Analysis From the United States and Low- and Middle-Income Countries
- 21 March 2025
- Published by Elsevier in JACC: Advances
- Vol. 4 (4) , 101649
Open AccessComparative Congenital Cardiac Catheterization Registry Analysis From the United States and Low- and Middle-Income Countries
- Open Access
- 5 December 2024
- Published by BMJ in BMJ Global Health
- Vol. 9 (12) , e016088
Prediction of low birth weight from fetal ultrasound and clinical characteristics: a comparative study between a low- and middle-income and a high-income country
Introduction: Adverse perinatal outcomes (APO) pose a significant global challenge, particularly in low- and middle-income countries (LMICs). This study aims to analyse two cohorts of high-risk pregnant women for APO to comprehend risk factors and improve prediction accuracy. Methods: We considered an LMIC and a high-income country (HIC) population to derive XGBoost classifiers to predict low birth weight (LBW) from a comprehensive set of maternal and fetal characteristics including socio-demographic, past and current pregnancy information, fetal biometry and fetoplacental Doppler measurements. Data were sourced from the FeDoC (Fetal Doppler Collaborative) study (Pakistan, LMIC) and theIMPACT (Improving Mothers for a Better PrenAtal Care Trial) study (Spain, HIC), and included 520 and 746 pregnancies assessed from 28 weeks gestation, respectively. The models were trained on varying subsets of the mentioned characteristics to evaluate their contribution in predicting LBW cases. For external validation, and to highlight potential differential risk factors for LBW, we investigated the generalisation of these models across cohorts. Models’ performance was evaluated through the area under the curve (AUC), and their interpretability was assessed using SHapley Additive exPlanations. Results: In FeDoC, Doppler variables demonstrated the highest value at predicting LBW compared with biometry and maternal clinical data (AUCDoppler, 0.67; AUCClinical, 0.65; AUCBiometry, 0.63), and its combination with maternal clinical data yielded the best prediction (AUCClinical+Doppler, 0.71). In IMPACT, fetal biometry emerged as the most predictive set (AUCBiometry, 0.75; AUCDoppler, 0.70; AUCClinical, 0.69) and its combination with Doppler and maternal clinical data achieved the highest accuracy (AUCClinical+Biometry+Doppler, 0.81). External validation consistently indicated that biometry combined with Doppler data yielded the best prediction. Conclusions: Our findings provide new insights into the predictive role of different clinical and ultrasound descriptors in two populations at high risk for APO, highlighting that different approaches are required for different populations. However, Doppler data improves prediction capabilities in both settings, underscoring the value of standardising ultrasound data acquisition, as practiced in HIC, to enhance LBW prediction in LMIC. This alignment contributes to bridging the health equity gap.
- 5 December 2024
- Published by BMJ in BMJ Global Health
- Vol. 9 (12) , e016088
Open AccessPrediction of low birth weight from fetal ultrasound and clinical characteristics: a comparative study between a low- and middle-income and a high-income country
Introduction: Adverse perinatal outcomes (APO) pose a significant global challenge, particularly in low- and middle-income countries (LMICs). This study aims to analyse two cohorts of high-risk pregnant women for APO to comprehend risk factors and improve prediction accuracy. Methods: We considered an LMIC and a high-income country (HIC) population to derive XGBoost classifiers to predict low birth weight (LBW) from a comprehensive set of maternal and fetal characteristics including socio-demographic, past and current pregnancy information, fetal biometry and fetoplacental Doppler measurements. Data were sourced from the FeDoC (Fetal Doppler Collaborative) study (Pakistan, LMIC) and theIMPACT (Improving Mothers for a Better PrenAtal Care Trial) study (Spain, HIC), and included 520 and 746 pregnancies assessed from 28 weeks gestation, respectively. The models were trained on varying subsets of the mentioned characteristics to evaluate their contribution in predicting LBW cases. For external validation, and to highlight potential differential risk factors for LBW, we investigated the generalisation of these models across cohorts. Models’ performance was evaluated through the area under the curve (AUC), and their interpretability was assessed using SHapley Additive exPlanations. Results: In FeDoC, Doppler variables demonstrated the highest value at predicting LBW compared with biometry and maternal clinical data (AUCDoppler, 0.67; AUCClinical, 0.65; AUCBiometry, 0.63), and its combination with maternal clinical data yielded the best prediction (AUCClinical+Doppler, 0.71). In IMPACT, fetal biometry emerged as the most predictive set (AUCBiometry, 0.75; AUCDoppler, 0.70; AUCClinical, 0.69) and its combination with Doppler and maternal clinical data achieved the highest accuracy (AUCClinical+Biometry+Doppler, 0.81). External validation consistently indicated that biometry combined with Doppler data yielded the best prediction. Conclusions: Our findings provide new insights into the predictive role of different clinical and ultrasound descriptors in two populations at high risk for APO, highlighting that different approaches are required for different populations. However, Doppler data improves prediction capabilities in both settings, underscoring the value of standardising ultrasound data acquisition, as practiced in HIC, to enhance LBW prediction in LMIC. This alignment contributes to bridging the health equity gap.
- 20 December 2023
- Published by Springer Nature in Pediatric Cardiology
- Vol. 46 (1) , 27-38
Enhancing Quality of Congenital Heart Care Within Resource-Limited Settings
Over 90% of the world’s children with congenital heart disease (CHD) are born in the resources poor settings of low- to middle-income countries (LMICs). The shortfall in human and material resources and dysfunctional health systems leads to poor quality of care (QoC) which contributes substantially to suboptimal outcomes of patients with CHD in LMICs. Notwithstanding these challenges, it is possible to develop a quality improvement (QI) framework that can have a significant impact on outcomes and prevent a number of deaths. In this review, we examine the common barriers to implementing effective QI processes in LMICs. Using examples of successful QI initiatives in LMIC, we propose a broad framework that focuses on simple, yet effective measures involving cohesive efforts of all key participants guided and nurtured by a leadership that strongly values QoC.
- 20 December 2023
- Published by Springer Nature in Pediatric Cardiology
- Vol. 46 (1) , 27-38
Enhancing Quality of Congenital Heart Care Within Resource-Limited Settings
Over 90% of the world’s children with congenital heart disease (CHD) are born in the resources poor settings of low- to middle-income countries (LMICs). The shortfall in human and material resources and dysfunctional health systems leads to poor quality of care (QoC) which contributes substantially to suboptimal outcomes of patients with CHD in LMICs. Notwithstanding these challenges, it is possible to develop a quality improvement (QI) framework that can have a significant impact on outcomes and prevent a number of deaths. In this review, we examine the common barriers to implementing effective QI processes in LMICs. Using examples of successful QI initiatives in LMIC, we propose a broad framework that focuses on simple, yet effective measures involving cohesive efforts of all key participants guided and nurtured by a leadership that strongly values QoC.
- Open Access
- 2 November 2023
- Published by BMJ in BMJ Paediatrics Open
- Vol. 7 (1) , e002134
Can machine learning methods be used for identification of at-risk neonates in low-resource settings? A prospective cohort study
Introduction Timely identification of at-risk neonates (ARNs) in the community is essential to reduce mortality in low-resource settings. Tools such as American Academy of Pediatrics pulse oximetry (POx) and WHO Young Infants Clinical Signs (WHOS) have high specificity but low sensitivity to identify ARNs. Our aim was assessing the value of POx and WHOS independently, in combination and with machine learning (ML) from clinical features, to detect ARNs in a low/middle-income country. Methods This prospective cohort study was conducted in a periurban community in Pakistan. Eligible live births were screened using WHOS and POx along with clinical information regarding pregnancy and delivery. The enrolled neonates were followed for 4 weeks of life to assess the vital status. The predictive value to identify ARNs, of POx, WHOS and an ML model using maternal and neonatal clinical features, was assessed. Results Of 1336 neonates, 68 (5%) had adverse outcomes, that is, sepsis (n=40, 59%), critical congenital heart disease (n=2, 3%), severe persistent pulmonary hypertension (n=1), hospitalisation (n=8, 12%) and death (n=17, 25%) assessed at 4 weeks of life. Specificity of POx and WHOS to independently identify ARNs was 99%, with sensitivity of 19% and 63%,respectively. Combining both improved sensitivity to 70%, keeping specificity at 98%. An ML model using clinical variables had 44% specificity and 76% sensitivity. A staged assessment, where WHOS, POx and ML are sequentially used for triage, increased sensitivity to 85%, keeping specificity 75%. Using ML (when WHOS and POx negative) for community follow-up detected the majority of ARNs. Conclusion Classic screening, combined with ML, can help maximise identifying ARNs and could be embedded in low-resource clinical settings, thereby improving outcome. Sequential use of classic assessment and clinical ML identifies the most ARNs in the community, still optimising follow-up clinical care.
- 2 November 2023
- Published by BMJ in BMJ Paediatrics Open
- Vol. 7 (1) , e002134
Open AccessCan machine learning methods be used for identification of at-risk neonates in low-resource settings? A prospective cohort study
Introduction Timely identification of at-risk neonates (ARNs) in the community is essential to reduce mortality in low-resource settings. Tools such as American Academy of Pediatrics pulse oximetry (POx) and WHO Young Infants Clinical Signs (WHOS) have high specificity but low sensitivity to identify ARNs. Our aim was assessing the value of POx and WHOS independently, in combination and with machine learning (ML) from clinical features, to detect ARNs in a low/middle-income country. Methods This prospective cohort study was conducted in a periurban community in Pakistan. Eligible live births were screened using WHOS and POx along with clinical information regarding pregnancy and delivery. The enrolled neonates were followed for 4 weeks of life to assess the vital status. The predictive value to identify ARNs, of POx, WHOS and an ML model using maternal and neonatal clinical features, was assessed. Results Of 1336 neonates, 68 (5%) had adverse outcomes, that is, sepsis (n=40, 59%), critical congenital heart disease (n=2, 3%), severe persistent pulmonary hypertension (n=1), hospitalisation (n=8, 12%) and death (n=17, 25%) assessed at 4 weeks of life. Specificity of POx and WHOS to independently identify ARNs was 99%, with sensitivity of 19% and 63%,respectively. Combining both improved sensitivity to 70%, keeping specificity at 98%. An ML model using clinical variables had 44% specificity and 76% sensitivity. A staged assessment, where WHOS, POx and ML are sequentially used for triage, increased sensitivity to 85%, keeping specificity 75%. Using ML (when WHOS and POx negative) for community follow-up detected the majority of ARNs. Conclusion Classic screening, combined with ML, can help maximise identifying ARNs and could be embedded in low-resource clinical settings, thereby improving outcome. Sequential use of classic assessment and clinical ML identifies the most ARNs in the community, still optimising follow-up clinical care.
- Open Access
- 3 October 2023
- Published by Elsevier in Journal of the Society for Cardiovascular Angiography & Interventions
- Vol. 2 (6) , 101119
Evaluating Procedural Performance: A Composite Outcome for Aortic and Pulmonary Valvuloplasty in Congenital Cardiac Catheterization
- 3 October 2023
- Published by Elsevier in Journal of the Society for Cardiovascular Angiography & Interventions
- Vol. 2 (6) , 101119
Open AccessEvaluating Procedural Performance: A Composite Outcome for Aortic and Pulmonary Valvuloplasty in Congenital Cardiac Catheterization
- Open Access
- 24 May 2023
- Published by Elsevier in JACC: Advances
- Vol. 2 (4) , 100344
Congenital Cardiac Catheterization in Low- and Middle-Income Countries
- 24 May 2023
- Published by Elsevier in JACC: Advances
- Vol. 2 (4) , 100344
Open AccessCongenital Cardiac Catheterization in Low- and Middle-Income Countries
- Top Cited PapersOpen Access
- 4 May 2023
- Published by BMJ in BMJ Global Health
- Vol. 8 (5) , e012049
Recommendations for developing effective and safe paediatric and congenital heart disease services in low-income and middle-income countries: a public health framework
The global burden of paediatric and congenital heart disease (PCHD) is substantial. We propose a novel public health framework with recommendations for developing effective and safe PCHD services in low-income and middle-income countries (LMICs). This framework was created by the Global Initiative for Children’s Surgery Cardiac Surgery working group in collaboration with a group of international rexperts in providing paediatric and congenital cardiac care to patients with CHD and rheumatic heart disease (RHD) in LMICs. Effective and safe PCHD care is inaccessible to many, and there is no consensus on the best approaches to provide meaningful access in resource-limited settings, where it is often needed the most. Considering the high inequity in access to care for CHD and RHD, we aimed to create an actionable framework for health practitioners, policy makers and patients that supports treatment and prevention. It was formulated based on rigorous evaluation of available guidelines and standards of care and builds on a consensus process about the competencies needed at each step of the care continuum. We recommend a tier-based framework for PCHD care integrated within existing health systems. Each level of care is expected to meet minimum benchmarks and ensure high-quality and family centred care. We propose that cardiac surgery capabilities should only be developed at the more advanced levels on hospitals that have an established foundation of cardiology and cardiac surgery services, including screening, diagnostics, inpatient and outpatient care, postoperative care and cardiac catheterisation. This approach requires a quality control system and close collaboration between the different levels of care to facilitate the journey and care of every child with heart disease. This effort was designed to guide readers and leaders in taking action, strengthening capacity, evaluating impact, advancing policy and engaging in partnerships to guide facilities providing PCHD care in LMICs.
- 4 May 2023
- Published by BMJ in BMJ Global Health
- Vol. 8 (5) , e012049
Top Cited PapersOpen AccessRecommendations for developing effective and safe paediatric and congenital heart disease services in low-income and middle-income countries: a public health framework
The global burden of paediatric and congenital heart disease (PCHD) is substantial. We propose a novel public health framework with recommendations for developing effective and safe PCHD services in low-income and middle-income countries (LMICs). This framework was created by the Global Initiative for Children’s Surgery Cardiac Surgery working group in collaboration with a group of international rexperts in providing paediatric and congenital cardiac care to patients with CHD and rheumatic heart disease (RHD) in LMICs. Effective and safe PCHD care is inaccessible to many, and there is no consensus on the best approaches to provide meaningful access in resource-limited settings, where it is often needed the most. Considering the high inequity in access to care for CHD and RHD, we aimed to create an actionable framework for health practitioners, policy makers and patients that supports treatment and prevention. It was formulated based on rigorous evaluation of available guidelines and standards of care and builds on a consensus process about the competencies needed at each step of the care continuum. We recommend a tier-based framework for PCHD care integrated within existing health systems. Each level of care is expected to meet minimum benchmarks and ensure high-quality and family centred care. We propose that cardiac surgery capabilities should only be developed at the more advanced levels on hospitals that have an established foundation of cardiology and cardiac surgery services, including screening, diagnostics, inpatient and outpatient care, postoperative care and cardiac catheterisation. This approach requires a quality control system and close collaboration between the different levels of care to facilitate the journey and care of every child with heart disease. This effort was designed to guide readers and leaders in taking action, strengthening capacity, evaluating impact, advancing policy and engaging in partnerships to guide facilities providing PCHD care in LMICs.