Ejaz Awan - Academia.edu (original) (raw)

Papers by Ejaz Awan

Research paper thumbnail of Machine learning in heart failure

Purpose of review: The aim of this review is to present an up-to-date overview of the application... more Purpose of review: The aim of this review is to present an up-to-date overview of the application of machine learning methods in heart failure including diagnosis, classification, readmissions and medication adherence. Recent findings: Recent studies have shown that the application of machine learning techniques may have the potential to improve heart failure outcomes and management, including cost savings by improving existing diagnostic and treatment support systems. Recently developed deep learning methods are expected to yield even better performance than traditional machine learning techniques in performing complex tasks by learning the intricate patterns hidden in big medical data. Summary: The review summarizes the recent developments in the application of machine and deep learning methods in heart failure management.

Research paper thumbnail of Evaluate the Pattern of Firearm Injuries Based on Gender in Hyderabad, Sindh, Pakistan

Pakistan Journal of Medical and Health Sciences

Aim: To assess the pattern of firearm injuries and different effecting factors based on gender in... more Aim: To assess the pattern of firearm injuries and different effecting factors based on gender in Hyderabad, Sindh, Pakistan. Study Design: Retrospective and descriptive Place and duration of study: Depart. Forensic Medicine & Toxicology, BMC LUMHS Jamshoro 01-01-2017 to 31-12-2019. Methodology: Three hundred and nineteen autopsies based on purposive sampling method were revealed the death due to firearm injuries. The demographic information, pattern of death due to firearm and which part of body involved based on variables. Results: There were 267 males and 52 were females and 95 firearm autopsies were between 31 to 40 years. It was revealed that in 38 autopsies, head was involved, 78 autopsies chest was involved, 76 autopsies abdomen was involved while 267 were from homicidal. Moreover, the cause of death due to firearm in maximum patients was hemorrhage followed by septicemia in 106 autopsies. According to gender wise, 38 autopsies involved head part 30 were male and 8 were femal...

Research paper thumbnail of A Post-Mortem Medicolegal Study of Asphyxial Deaths: An Autopsy Based Study

Pakistan Journal of Medical and Health Sciences

Objective: To assess the medicolegal causes of asphyxial deaths in tertiary care hospital of Hyde... more Objective: To assess the medicolegal causes of asphyxial deaths in tertiary care hospital of Hyderabad, Sindh, Pakistan. Study Design: Descriptive, observational and retrospective Place and Duration of Study: Medicolegal Section of Liaquat University Hospital Hyderabad from 1st January 2015 to 31st December 2019. Methodology: Two hundred and nineteen patients were retrieved and died due to other reasons were excluded from the study while no any patient’s age and gender restrictions. Results: There were 157 males and 62 females. Sixty six patients of asphyxial belonged to age 39-48 years. Among 74 patients of suffocation, 51 patients were males and 23 were females. There are 5 reported reasons of asphyxial deaths. Out of 45 hanging patients, 5 patients belonged to 18-28 years, 8 patients belonged to 29-38 years, 9 patients belonged to 39-48 years, 6 patients belong to 49-58 years and 15 patients belonged to ≥59 59 years. Conclusion: Male is the most vulnerable victim of the violent a...

Research paper thumbnail of Imputation of missing data with class imbalance using conditional generative adversarial networks

Research paper thumbnail of Causes of Death

The Professional Medical Journal

Objectives: The purpose behind this study was to determine the pattern of the causes of death in ... more Objectives: The purpose behind this study was to determine the pattern of the causes of death in adult males - a perspective on autopsy. Study Design: Cross sectional study. Period: 2015 to 2016. Setting: Peoples Medical College Hospital, Nawabshah, Shaheed Benazirabad, Sindh, Pakistan. Material and Methods: 73 male patients, whose autopsy were performed through a convenience non-purposive sampling technique to ascertain the causes of death among dead bodies brought at Peoples Medical College Hospital, Nawabshah, Shaheed Benazirabad, Sindh, Pakistan for the purpose of autopsy. Autopsy was performed with consent taken from the family members and hospital administration. Questionnaire was used to collect the limited relevant data and used SPSS version 17 for data entry and analysis. Results: Mean age of patients whom autopsy were performed was 37.12 years among them minimum age was 10 year and maximum age recorded was 75 years. Among all, 31 (42.46%) cases were from rural area while 4...

Research paper thumbnail of Machine learning-based prediction of heart failure readmission or death: implications of choosing the right model and the right metrics

ESC Heart Failure

Aims Machine learning (ML) is widely believed to be able to learn complex hidden interactions fro... more Aims Machine learning (ML) is widely believed to be able to learn complex hidden interactions from the data and has the potential in predicting events such as heart failure (HF) readmission and death. Recent studies have revealed conflicting results likely due to failure to take into account the class imbalance problem commonly seen with medical data. We developed a new ML approach to predict 30 day HF readmission or death and compared the performance of this model with other commonly used prediction models. Methods and results We identified all Western Australian patients aged above 65 years admitted for HF between 2003 and 2008 in the linked Hospital Morbidity Data Collection. Taking into consideration the class imbalance problem, we developed a multi-layer perceptron (MLP)-based approach to predict 30 day HF readmission or death and compared the predictive performances using the performance metrics, that is, area under the receiver operating characteristic curve (AUC), area under the precision-recall curve (AUPRC), sensitivity and specificity with other ML and regression models. Out of the 10 757 patients with HF, 23.6% were readmitted or died within 30 days of hospital discharge. We observed an AUC of 0.55, 0.53, 0.58, and 0.54 while an AUPRC of 0.39, 0.38, 0.46, and 0.38 for weighted random forest, weighted decision trees, logistic regression, and weighted support vector machines models, respectively. The MLP-based approach produced the highest AUC (0.62) and AUPRC (0.46) with 48% sensitivity and 70% specificity. Conclusions We show that for the medical data with class imbalance, the proposed MLP-based approach is superior to other ML and regression techniques for the prediction of 30 day HF readmission or death.

Research paper thumbnail of Machine learning in heart failure

Current Opinion in Cardiology

Purpose of review: The aim of this review is to present an up-to-date overview of the application... more Purpose of review: The aim of this review is to present an up-to-date overview of the application of machine learning methods in heart failure including diagnosis, classification, readmissions and medication adherence. Recent findings: Recent studies have shown that the application of machine learning techniques may have the potential to improve heart failure outcomes and management, including cost savings by improving existing diagnostic and treatment support systems. Recently developed deep learning methods are expected to yield even better performance than traditional machine learning techniques in performing complex tasks by learning the intricate patterns hidden in big medical data. Summary: The review summarizes the recent developments in the application of machine and deep learning methods in heart failure management.

Research paper thumbnail of Study to Assess the Autopsy in Relation with Age and Gender in Tertiary Care Hospital of Hyderabad, Sindh, Pakistan

Pakistan Journal of Medical and Health Sciences

Objective: To assess the autopsy in relation with age and gender in tertiary care hospital of Hyd... more Objective: To assess the autopsy in relation with age and gender in tertiary care hospital of Hyderabad, Sindh, Pakistan. Study Design: Retrospective, observational and non-interventional study Place and Duration of Study: Medicolegal Department of Liaquat University of Medical and Health Sciences Hyderabad from 1st January 2017 to 31st December 2018. Methodology: Three hundred and eighty-one patients were enrolled. Results: According to cause of death, 88 (23.10%) were died due to road traffic accident, firearm injury 73 (19.16%) and asphaxial death 70 (18.37%), assault 65 (17.06%), poisoning 37 (9.71%), electric shock 30 (7.87%) and undetermined 18 (4.72%) respectively. Conclusion: The relatable factors such as age and gender with the suicidal cases in results of autopsy examination which plays the most relevant role in the medical practices even after the advancement of diagnostic technologies. Key words: Assess, Autopsy, Age, Gender, Tertiary care hospital

Research paper thumbnail of Machine learning in heart failure

Purpose of review: The aim of this review is to present an up-to-date overview of the application... more Purpose of review: The aim of this review is to present an up-to-date overview of the application of machine learning methods in heart failure including diagnosis, classification, readmissions and medication adherence. Recent findings: Recent studies have shown that the application of machine learning techniques may have the potential to improve heart failure outcomes and management, including cost savings by improving existing diagnostic and treatment support systems. Recently developed deep learning methods are expected to yield even better performance than traditional machine learning techniques in performing complex tasks by learning the intricate patterns hidden in big medical data. Summary: The review summarizes the recent developments in the application of machine and deep learning methods in heart failure management.

Research paper thumbnail of Evaluate the Pattern of Firearm Injuries Based on Gender in Hyderabad, Sindh, Pakistan

Pakistan Journal of Medical and Health Sciences

Aim: To assess the pattern of firearm injuries and different effecting factors based on gender in... more Aim: To assess the pattern of firearm injuries and different effecting factors based on gender in Hyderabad, Sindh, Pakistan. Study Design: Retrospective and descriptive Place and duration of study: Depart. Forensic Medicine & Toxicology, BMC LUMHS Jamshoro 01-01-2017 to 31-12-2019. Methodology: Three hundred and nineteen autopsies based on purposive sampling method were revealed the death due to firearm injuries. The demographic information, pattern of death due to firearm and which part of body involved based on variables. Results: There were 267 males and 52 were females and 95 firearm autopsies were between 31 to 40 years. It was revealed that in 38 autopsies, head was involved, 78 autopsies chest was involved, 76 autopsies abdomen was involved while 267 were from homicidal. Moreover, the cause of death due to firearm in maximum patients was hemorrhage followed by septicemia in 106 autopsies. According to gender wise, 38 autopsies involved head part 30 were male and 8 were femal...

Research paper thumbnail of A Post-Mortem Medicolegal Study of Asphyxial Deaths: An Autopsy Based Study

Pakistan Journal of Medical and Health Sciences

Objective: To assess the medicolegal causes of asphyxial deaths in tertiary care hospital of Hyde... more Objective: To assess the medicolegal causes of asphyxial deaths in tertiary care hospital of Hyderabad, Sindh, Pakistan. Study Design: Descriptive, observational and retrospective Place and Duration of Study: Medicolegal Section of Liaquat University Hospital Hyderabad from 1st January 2015 to 31st December 2019. Methodology: Two hundred and nineteen patients were retrieved and died due to other reasons were excluded from the study while no any patient’s age and gender restrictions. Results: There were 157 males and 62 females. Sixty six patients of asphyxial belonged to age 39-48 years. Among 74 patients of suffocation, 51 patients were males and 23 were females. There are 5 reported reasons of asphyxial deaths. Out of 45 hanging patients, 5 patients belonged to 18-28 years, 8 patients belonged to 29-38 years, 9 patients belonged to 39-48 years, 6 patients belong to 49-58 years and 15 patients belonged to ≥59 59 years. Conclusion: Male is the most vulnerable victim of the violent a...

Research paper thumbnail of Imputation of missing data with class imbalance using conditional generative adversarial networks

Research paper thumbnail of Causes of Death

The Professional Medical Journal

Objectives: The purpose behind this study was to determine the pattern of the causes of death in ... more Objectives: The purpose behind this study was to determine the pattern of the causes of death in adult males - a perspective on autopsy. Study Design: Cross sectional study. Period: 2015 to 2016. Setting: Peoples Medical College Hospital, Nawabshah, Shaheed Benazirabad, Sindh, Pakistan. Material and Methods: 73 male patients, whose autopsy were performed through a convenience non-purposive sampling technique to ascertain the causes of death among dead bodies brought at Peoples Medical College Hospital, Nawabshah, Shaheed Benazirabad, Sindh, Pakistan for the purpose of autopsy. Autopsy was performed with consent taken from the family members and hospital administration. Questionnaire was used to collect the limited relevant data and used SPSS version 17 for data entry and analysis. Results: Mean age of patients whom autopsy were performed was 37.12 years among them minimum age was 10 year and maximum age recorded was 75 years. Among all, 31 (42.46%) cases were from rural area while 4...

Research paper thumbnail of Machine learning-based prediction of heart failure readmission or death: implications of choosing the right model and the right metrics

ESC Heart Failure

Aims Machine learning (ML) is widely believed to be able to learn complex hidden interactions fro... more Aims Machine learning (ML) is widely believed to be able to learn complex hidden interactions from the data and has the potential in predicting events such as heart failure (HF) readmission and death. Recent studies have revealed conflicting results likely due to failure to take into account the class imbalance problem commonly seen with medical data. We developed a new ML approach to predict 30 day HF readmission or death and compared the performance of this model with other commonly used prediction models. Methods and results We identified all Western Australian patients aged above 65 years admitted for HF between 2003 and 2008 in the linked Hospital Morbidity Data Collection. Taking into consideration the class imbalance problem, we developed a multi-layer perceptron (MLP)-based approach to predict 30 day HF readmission or death and compared the predictive performances using the performance metrics, that is, area under the receiver operating characteristic curve (AUC), area under the precision-recall curve (AUPRC), sensitivity and specificity with other ML and regression models. Out of the 10 757 patients with HF, 23.6% were readmitted or died within 30 days of hospital discharge. We observed an AUC of 0.55, 0.53, 0.58, and 0.54 while an AUPRC of 0.39, 0.38, 0.46, and 0.38 for weighted random forest, weighted decision trees, logistic regression, and weighted support vector machines models, respectively. The MLP-based approach produced the highest AUC (0.62) and AUPRC (0.46) with 48% sensitivity and 70% specificity. Conclusions We show that for the medical data with class imbalance, the proposed MLP-based approach is superior to other ML and regression techniques for the prediction of 30 day HF readmission or death.

Research paper thumbnail of Machine learning in heart failure

Current Opinion in Cardiology

Purpose of review: The aim of this review is to present an up-to-date overview of the application... more Purpose of review: The aim of this review is to present an up-to-date overview of the application of machine learning methods in heart failure including diagnosis, classification, readmissions and medication adherence. Recent findings: Recent studies have shown that the application of machine learning techniques may have the potential to improve heart failure outcomes and management, including cost savings by improving existing diagnostic and treatment support systems. Recently developed deep learning methods are expected to yield even better performance than traditional machine learning techniques in performing complex tasks by learning the intricate patterns hidden in big medical data. Summary: The review summarizes the recent developments in the application of machine and deep learning methods in heart failure management.

Research paper thumbnail of Study to Assess the Autopsy in Relation with Age and Gender in Tertiary Care Hospital of Hyderabad, Sindh, Pakistan

Pakistan Journal of Medical and Health Sciences

Objective: To assess the autopsy in relation with age and gender in tertiary care hospital of Hyd... more Objective: To assess the autopsy in relation with age and gender in tertiary care hospital of Hyderabad, Sindh, Pakistan. Study Design: Retrospective, observational and non-interventional study Place and Duration of Study: Medicolegal Department of Liaquat University of Medical and Health Sciences Hyderabad from 1st January 2017 to 31st December 2018. Methodology: Three hundred and eighty-one patients were enrolled. Results: According to cause of death, 88 (23.10%) were died due to road traffic accident, firearm injury 73 (19.16%) and asphaxial death 70 (18.37%), assault 65 (17.06%), poisoning 37 (9.71%), electric shock 30 (7.87%) and undetermined 18 (4.72%) respectively. Conclusion: The relatable factors such as age and gender with the suicidal cases in results of autopsy examination which plays the most relevant role in the medical practices even after the advancement of diagnostic technologies. Key words: Assess, Autopsy, Age, Gender, Tertiary care hospital