The past several decades have seen a shift in patient care towards digitalisation, which has ushe... more The past several decades have seen a shift in patient care towards digitalisation, which has ushered in a new era of health care delivery and improved sustainability and resilience of health systems, with positive impacts on both internal and external stakeholders. This study’s aim was to understand the role of digital virtual consultations in improving internal and external stakeholders’ health, as well as wellbeing among hospital doctors. A qualitative research approach was used with semi-structured online interviews administered to hospital doctors. The interviews showed that the doctors viewed digital virtual consultations as supplementary to in-person consultations, and as tools to reduce obstacles related to distance and time. If the necessary infrastructure and technology were in place, doctors would be willing to use these options. Implementing these technologies would improve the medical profession’s flexibility on the one hand; but it might affect doctors’ work–life balanc...
The problem of hospital patients’ delayed discharge or ‘bed blocking’ has long been a challenge f... more The problem of hospital patients’ delayed discharge or ‘bed blocking’ has long been a challenge for healthcare managers and policymakers. It negatively affects the hospital performance metrics and has other severe consequences for the healthcare system, such as affecting patients’ health. In our previous work, we proposed the phase-type survival tree (PHTST)-based analysis to cluster patients into clinically meaningful patient groups and an extension of this approach to examine the relationship between the length of stay in hospitals and the destination on discharge. This paper describes how PHTST-based clustering can be used for modelling delayed discharge and its effects in a stroke care unit, especially the extra beds required, additional cost, and bed blocking. The PHTST length of stay distribution of each group of patients (each PHTST node) is modelled separately as a finite state continuous-time Markov chain using Coxian-phase-type distributions. Delayed discharge patients wai...
BackgroundQuality of health service delivery data remains sub-optimal in many Low and middle-inco... more BackgroundQuality of health service delivery data remains sub-optimal in many Low and middle-income countries (LMICs) despite over a decade of progress in digitization and Health Management Information Systems (HMIS) improvements. Identifying everyone residing in a country utilizing universal civil registration and/or national unique identification number systems especially for vulnerable patients seeking care within the care continuum is an essential part of pursuing universal health coverage (UHC). Many different strategies or candidate digital technologies exist for uniquely identifying and tracking patients within a health system, and the different strategies also have their advantages and trade-offs. The recent approval of Decentralized identifier (DID) core specification by World Wide Web Consortium (W3C) heralds the search for consensus on standard interoperable DID methods.ObjectiveThis paper aims to: (1) assess how candidate Patient Identification Systems fit the digital Pa...
Background Referral linkages are crucial for efficient functioning of primary health care (PHC) s... more Background Referral linkages are crucial for efficient functioning of primary health care (PHC) systems. Fast Healthcare Interoperability Resource (FHIR) is an open global standard that facilitates structuring of health information for coordinated exchange among stakeholders. Objective The objective of this study is to design FHIR profiles and present methodology and the profiled FHIR resource for Maternal and Child Health referral use cases in Ebonyi state, Nigeria—a typical low- and middle-income country (LMIC) setting. Methods Practicing doctors, midwives, and nurses were purposefully sampled and surveyed. Different referral forms were reviewed. The union of data sets from surveys and forms was aggregated and mapped to base patient FHIR resource elements, and extensions were created for data sets not in the core FHIR specification. This study also introduced FHIR and its relation to the World Health Organization’s (WHO’s) International Classification of Diseases. Results We found...
2017 International Conference on Computing Networking and Informatics (ICCNI), 2017
This paper investigates the application of spectral graph decomposition method in improving the d... more This paper investigates the application of spectral graph decomposition method in improving the discriminative quality of spectral components of the common spatial pattern for seizure classification. The aim is to improve the variance between the normal and abnormal EEG patterns in feature extraction process. The affinity matrix of the graph spectral decomposition that derive the Laplacian matrix encodes the dataset of the CSP covariance matrix as a correlation instead of Euclidean (or Minkowski) distance on Gaussian kernel function. The feature vector containing pattern of abnormality is sorted in order of the magnitude of their simple statistical mean values. The results obtained show that the CSP-Spectral Graph Decompsotion approach seems to provide a better discriminative features than CSP feature extraction process.
BACKGROUND The government and partners have invested heavily in the health information system (HI... more BACKGROUND The government and partners have invested heavily in the health information system (HIS) for service delivery, surveillance, reporting, and monitoring. Sierra Leone’s government launched its first digital health strategy in 2018. In 2019, a broader national innovation and digital strategy was launched. The health pillar direction will use big data and artificial intelligence (AI) to improve health care in general and maternal and child health in particular. Understanding the number, distribution, and interoperability of digital health solutions is crucial for successful implementation strategies. OBJECTIVE This paper presents the state of digital health solutions in Sierra Leone and how these solutions currently interoperate. This study further presents opportunities for big data and AI applications. METHODS All the district health management teams, all digital health implementing organizations, and a stratified sample of 72 (out of 1284) health facilities were purposeful...
Background Teenage pregnancy remains high with low contraceptive prevalence among adolescents (ag... more Background Teenage pregnancy remains high with low contraceptive prevalence among adolescents (aged 15-19 years) in Sierra Leone. Stakeholders leverage multiple strategies to address the challenge. Mobile technology is pervasive and presents an opportunity to reach young people with critical sexual reproductive health and family planning messages. Objective The objectives of this research study are to understand how mobile health (mHealth) is used for family planning, understand phone use habits among young people in Sierra Leone, and recommend strategies for mobile-enabled dissemination of family planning information at scale. Methods This formative research study was conducted using a systematic literature review and focus group discussions (FGDs). The literature survey assessed similar but existing interventions through a systematic search of 6 scholarly databases. Cross-sections of young people of both sexes and their support groups were engaged in 9 FGDs in an urban and a rural...
Brain imaging with data mining is rising in significance as it enables the provision of prognoses... more Brain imaging with data mining is rising in significance as it enables the provision of prognoses, treatments and a better comprehension of brain functioning. Data mining considers how it might utilize the data to uncover fresh knowledge and thereby improving decision-making processes. Though data mining is a mighty knowledge detecting method, there are limits in the way that it may be employed: it is application dependent. This chapter deals with the early detection of dementia disease with data mining techniques. Once the presence of the disease is detected, further diagnosis can be done so that the health of elderly people can be improved. Dementia is the loss of cognitive efficiency and disorder beyond natural aging that inhibits social and occupational performance. Typical clinical practice reveals that dementia’s cognitive and functional losses lead to variations in behavior, but this is not a primary criterion as it lacks diagnostic specificity. Magnetic Resonance Imaging (MRI) detects dementia disease early before irreversible damage. Features are extracted from the segmented images using both Wavelet Packet Tree (WPT) and First-Order Histogram (FOH) method. Features are normalized and fused using the product rule fusion technique after computing Median Absolute Deviation (MAD) between two features. Classification accuracy is measured using both K-Nearest Neighbor (KNN) and Naive Bayesian Classifier. Performance measures classification accuracy, average precision, average recall, and F Measure are evaluated. The overall classification accuracy achieved using the proposed feature fusion technique is 93.87%. The early detection of Alzheimer’s helps caregivers in taking care of the patients. Once the abnormality is identified, the patient’s condition is monitored using the wireless medium with the Internet of Things (IoT). It helps in creating a working environment for a patient at home by reducing health expenses and reduces burdens on health care professionals.
Background The energy-constrained heterogeneous nodes are the most challenging wireless sensor ne... more Background The energy-constrained heterogeneous nodes are the most challenging wireless sensor networks (WSNs) for developing energy-aware clustering schemes. Although various clustering approaches are proven to minimise energy consumption and delay and extend the network lifetime by selecting optimum cluster heads (CHs), it is still a crucial challenge. Methods This article proposes a genetic algorithm-based energy-aware multi-hop clustering (GA-EMC) scheme for heterogeneous WSNs (HWSNs). In HWSNs, all the nodes have varying initial energy and typically have an energy consumption restriction. A genetic algorithm determines the optimal CHs and their positions in the network. The fitness of chromosomes is calculated in terms of distance, optimal CHs, and the node's residual energy. Multi-hop communication improves energy efficiency in HWSNs. The areas near the sink are deployed with more supernodes far away from the sink to solve the hot spot problem in WSNs near the sink node. R...
Current research on cloud computing often focuses on the technology itself and the benefits that ... more Current research on cloud computing often focuses on the technology itself and the benefits that one company can use and choose from cloud services. Most of the research has focused on mainstream enterprises and limited regard to Central Banks’ (CBs’) Cloud Computing Adoption (CCA). CBs are continually exploring opportunities to enhance IT efficacy while minimizing expenditures and ensuring data protection and network security. This paper investigates the factors affecting the CBs’ CCA by surveying 40 CBs representing approximately 25% of total CBs worldwide. The main participants were senior IT managers who are responsible for any IT decisions in CBs. The findings are also significant for other organizations or businesses where data privacy is crucial. The study results indicate that CBs are still reluctant to migrate to the public cloud. Influential factors preventing CCA are data protection, privacy, and risks.
The past several decades have seen a shift in patient care towards digitalisation, which has ushe... more The past several decades have seen a shift in patient care towards digitalisation, which has ushered in a new era of health care delivery and improved sustainability and resilience of health systems, with positive impacts on both internal and external stakeholders. This study’s aim was to understand the role of digital virtual consultations in improving internal and external stakeholders’ health, as well as wellbeing among hospital doctors. A qualitative research approach was used with semi-structured online interviews administered to hospital doctors. The interviews showed that the doctors viewed digital virtual consultations as supplementary to in-person consultations, and as tools to reduce obstacles related to distance and time. If the necessary infrastructure and technology were in place, doctors would be willing to use these options. Implementing these technologies would improve the medical profession’s flexibility on the one hand; but it might affect doctors’ work–life balanc...
The problem of hospital patients’ delayed discharge or ‘bed blocking’ has long been a challenge f... more The problem of hospital patients’ delayed discharge or ‘bed blocking’ has long been a challenge for healthcare managers and policymakers. It negatively affects the hospital performance metrics and has other severe consequences for the healthcare system, such as affecting patients’ health. In our previous work, we proposed the phase-type survival tree (PHTST)-based analysis to cluster patients into clinically meaningful patient groups and an extension of this approach to examine the relationship between the length of stay in hospitals and the destination on discharge. This paper describes how PHTST-based clustering can be used for modelling delayed discharge and its effects in a stroke care unit, especially the extra beds required, additional cost, and bed blocking. The PHTST length of stay distribution of each group of patients (each PHTST node) is modelled separately as a finite state continuous-time Markov chain using Coxian-phase-type distributions. Delayed discharge patients wai...
BackgroundQuality of health service delivery data remains sub-optimal in many Low and middle-inco... more BackgroundQuality of health service delivery data remains sub-optimal in many Low and middle-income countries (LMICs) despite over a decade of progress in digitization and Health Management Information Systems (HMIS) improvements. Identifying everyone residing in a country utilizing universal civil registration and/or national unique identification number systems especially for vulnerable patients seeking care within the care continuum is an essential part of pursuing universal health coverage (UHC). Many different strategies or candidate digital technologies exist for uniquely identifying and tracking patients within a health system, and the different strategies also have their advantages and trade-offs. The recent approval of Decentralized identifier (DID) core specification by World Wide Web Consortium (W3C) heralds the search for consensus on standard interoperable DID methods.ObjectiveThis paper aims to: (1) assess how candidate Patient Identification Systems fit the digital Pa...
Background Referral linkages are crucial for efficient functioning of primary health care (PHC) s... more Background Referral linkages are crucial for efficient functioning of primary health care (PHC) systems. Fast Healthcare Interoperability Resource (FHIR) is an open global standard that facilitates structuring of health information for coordinated exchange among stakeholders. Objective The objective of this study is to design FHIR profiles and present methodology and the profiled FHIR resource for Maternal and Child Health referral use cases in Ebonyi state, Nigeria—a typical low- and middle-income country (LMIC) setting. Methods Practicing doctors, midwives, and nurses were purposefully sampled and surveyed. Different referral forms were reviewed. The union of data sets from surveys and forms was aggregated and mapped to base patient FHIR resource elements, and extensions were created for data sets not in the core FHIR specification. This study also introduced FHIR and its relation to the World Health Organization’s (WHO’s) International Classification of Diseases. Results We found...
2017 International Conference on Computing Networking and Informatics (ICCNI), 2017
This paper investigates the application of spectral graph decomposition method in improving the d... more This paper investigates the application of spectral graph decomposition method in improving the discriminative quality of spectral components of the common spatial pattern for seizure classification. The aim is to improve the variance between the normal and abnormal EEG patterns in feature extraction process. The affinity matrix of the graph spectral decomposition that derive the Laplacian matrix encodes the dataset of the CSP covariance matrix as a correlation instead of Euclidean (or Minkowski) distance on Gaussian kernel function. The feature vector containing pattern of abnormality is sorted in order of the magnitude of their simple statistical mean values. The results obtained show that the CSP-Spectral Graph Decompsotion approach seems to provide a better discriminative features than CSP feature extraction process.
BACKGROUND The government and partners have invested heavily in the health information system (HI... more BACKGROUND The government and partners have invested heavily in the health information system (HIS) for service delivery, surveillance, reporting, and monitoring. Sierra Leone’s government launched its first digital health strategy in 2018. In 2019, a broader national innovation and digital strategy was launched. The health pillar direction will use big data and artificial intelligence (AI) to improve health care in general and maternal and child health in particular. Understanding the number, distribution, and interoperability of digital health solutions is crucial for successful implementation strategies. OBJECTIVE This paper presents the state of digital health solutions in Sierra Leone and how these solutions currently interoperate. This study further presents opportunities for big data and AI applications. METHODS All the district health management teams, all digital health implementing organizations, and a stratified sample of 72 (out of 1284) health facilities were purposeful...
Background Teenage pregnancy remains high with low contraceptive prevalence among adolescents (ag... more Background Teenage pregnancy remains high with low contraceptive prevalence among adolescents (aged 15-19 years) in Sierra Leone. Stakeholders leverage multiple strategies to address the challenge. Mobile technology is pervasive and presents an opportunity to reach young people with critical sexual reproductive health and family planning messages. Objective The objectives of this research study are to understand how mobile health (mHealth) is used for family planning, understand phone use habits among young people in Sierra Leone, and recommend strategies for mobile-enabled dissemination of family planning information at scale. Methods This formative research study was conducted using a systematic literature review and focus group discussions (FGDs). The literature survey assessed similar but existing interventions through a systematic search of 6 scholarly databases. Cross-sections of young people of both sexes and their support groups were engaged in 9 FGDs in an urban and a rural...
Brain imaging with data mining is rising in significance as it enables the provision of prognoses... more Brain imaging with data mining is rising in significance as it enables the provision of prognoses, treatments and a better comprehension of brain functioning. Data mining considers how it might utilize the data to uncover fresh knowledge and thereby improving decision-making processes. Though data mining is a mighty knowledge detecting method, there are limits in the way that it may be employed: it is application dependent. This chapter deals with the early detection of dementia disease with data mining techniques. Once the presence of the disease is detected, further diagnosis can be done so that the health of elderly people can be improved. Dementia is the loss of cognitive efficiency and disorder beyond natural aging that inhibits social and occupational performance. Typical clinical practice reveals that dementia’s cognitive and functional losses lead to variations in behavior, but this is not a primary criterion as it lacks diagnostic specificity. Magnetic Resonance Imaging (MRI) detects dementia disease early before irreversible damage. Features are extracted from the segmented images using both Wavelet Packet Tree (WPT) and First-Order Histogram (FOH) method. Features are normalized and fused using the product rule fusion technique after computing Median Absolute Deviation (MAD) between two features. Classification accuracy is measured using both K-Nearest Neighbor (KNN) and Naive Bayesian Classifier. Performance measures classification accuracy, average precision, average recall, and F Measure are evaluated. The overall classification accuracy achieved using the proposed feature fusion technique is 93.87%. The early detection of Alzheimer’s helps caregivers in taking care of the patients. Once the abnormality is identified, the patient’s condition is monitored using the wireless medium with the Internet of Things (IoT). It helps in creating a working environment for a patient at home by reducing health expenses and reduces burdens on health care professionals.
Background The energy-constrained heterogeneous nodes are the most challenging wireless sensor ne... more Background The energy-constrained heterogeneous nodes are the most challenging wireless sensor networks (WSNs) for developing energy-aware clustering schemes. Although various clustering approaches are proven to minimise energy consumption and delay and extend the network lifetime by selecting optimum cluster heads (CHs), it is still a crucial challenge. Methods This article proposes a genetic algorithm-based energy-aware multi-hop clustering (GA-EMC) scheme for heterogeneous WSNs (HWSNs). In HWSNs, all the nodes have varying initial energy and typically have an energy consumption restriction. A genetic algorithm determines the optimal CHs and their positions in the network. The fitness of chromosomes is calculated in terms of distance, optimal CHs, and the node's residual energy. Multi-hop communication improves energy efficiency in HWSNs. The areas near the sink are deployed with more supernodes far away from the sink to solve the hot spot problem in WSNs near the sink node. R...
Current research on cloud computing often focuses on the technology itself and the benefits that ... more Current research on cloud computing often focuses on the technology itself and the benefits that one company can use and choose from cloud services. Most of the research has focused on mainstream enterprises and limited regard to Central Banks’ (CBs’) Cloud Computing Adoption (CCA). CBs are continually exploring opportunities to enhance IT efficacy while minimizing expenditures and ensuring data protection and network security. This paper investigates the factors affecting the CBs’ CCA by surveying 40 CBs representing approximately 25% of total CBs worldwide. The main participants were senior IT managers who are responsible for any IT decisions in CBs. The findings are also significant for other organizations or businesses where data privacy is crucial. The study results indicate that CBs are still reluctant to migrate to the public cloud. Influential factors preventing CCA are data protection, privacy, and risks.
Uploads
Papers by Lalit Garg