Ankica Babic

Ankica Babic
Department of Biomedical Enineering (IMT)

PhD

About

130
Publications
13,936
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
559
Citations

Publications

Publications (130)
Article
Information technology (IT) is used to establish diagnosis and provide treatments for people with cognitive decline. The condition affects many before it becomes clear that more permanent changes, like dementia, could be noticed. Those who search for information are exposed to lots of information and different technologies which they need to make s...
Article
This paper explores the capabilities of a sophisticated deep learning method, named Deep Time Growing Neural Network (DTGNN), and compares its possibilities against a generally well-known method, Convolutional Neural network (CNN). The comparison is performed by using time series of the heart sound signal, so-called Phonocardiography (PCG). The cla...
Article
Health management information systems implemented in low-and middle-income countries (LMICs) have provided availability of HIV-data. As such, dashboards have become increasingly popular as they provide a potentially powerful avenue for deriving insights at glance. This promotes use of data for decision-making by various stakeholders such as Ministr...
Chapter
Full-text available
Electronic Medical Records Systems (EMRs) improve the quality of patient care and reduce medical errors. Nevertheless, their role in health data indicator reporting performance is unclear. We assessed reporting completeness and timeliness of HIV indicator data to the national aggregate reporting system, District Health Information Software 2 (DHIS2...
Chapter
Full-text available
A mobile and web-based prototype was developed to explore utility of heart sound data in the context of patient self-monitoring. There are not many applications available despite measurement equipment that can be purchased. This research aimed at developing an application that could help patients understand and use phonocardiography. The resulting...
Chapter
Full-text available
This paper presents an original method for studying the performance of the supervised Machine Learning (ML) methods, the A-Test method. The method offers the possibility of investigating the structural risk as well as the learning capacity of ML methods in a quantitating manner. A-Test provides a powerful validation method for the learning methods...
Article
Full-text available
Background Electronic medical records systems (EMRs) adoption in healthcare to facilitate work processes have become common in many countries. Although EMRs are associated with quality patient care, patient safety, and cost reduction, their adoption rates are comparatively low. Understanding factors associated with the use of the implemented EMRs a...
Article
Full-text available
Background Health facilities in developing countries are increasingly adopting Electronic Health Records systems (EHRs) to support healthcare processes. However, only limited studies are available that assess the actual use of the EHRs once adopted in these settings. We assessed the state of the 376 KenyaEMR system (national EHRs) implementations i...
Preprint
Full-text available
Background Electronic Medical Records systems (EMRs) adoption in healthcare to facilitate work processes have become common in many countries. Although EMRs are associated with quality patient care, patient safety and cost reduction, their adoption rates are comparatively low. Understanding factors associated with usage of implemented EMRs are crit...
Article
Full-text available
Identifying barriers and facilitators in HIV-indicator reporting contributes to strengthening HIV monitoring and evaluation efforts by acknowledging contributors to success, as well as identifying weaknesses within the system that require improvement. Nonetheless, there is paucity in identifying and comparing barriers and facilitators in HIV-indica...
Article
Full-text available
Background Electronic Health Record Systems (EHRs) are being rolled out nationally in many low- and middle-income countries (LMICs) yet assessing actual system usage remains a challenge. We employed a nominal group technique (NGT) process to systematically develop high-quality indicators for evaluating actual usage of EHRs in LMICs. Methods An ini...
Article
Full-text available
Background The ability to report complete, accurate and timely data by HIV care providers and other entities is a key aspect in monitoring trends in HIV prevention, treatment and care, hence contributing to its eradication. In many low-middle-income-countries (LMICs), aggregate HIV data reporting is done through the District Health Information Soft...
Chapter
In low- and middle-income countries, private and public facilities tend to have highly variable characteristics, which might affect their performance in meeting reporting requirements mandated by ministries of health. There is conflicting evidence on which facility type performs better across various care dimensions, and only few studies exist to e...
Chapter
This paper presents a machine learning method to detect and discriminate between Aortic Stenosis (AS) and Bicuspid Aortic Valve (BAV) based on heart sound analysis. Differentiation between the two heart conditions is clinically important, but complicated if relying merely on the conventional auscultation. A novel form of the Time Growing Neural Net...
Article
Full-text available
Background The District Health Information Software-2 (DHIS2) is widely used by countries for national-level aggregate reporting of health-data. To best leverage DHIS2 data for decision-making, countries need to ensure that data within their systems are of the highest quality. Comprehensive, systematic, and transparent data cleaning approaches form...
Preprint
Full-text available
Introduction: The ability to report complete, accurate and timely data by HIV care providers and other entities is a key aspect in monitoring trends in HIV prevention, treatment and care, hence contributing to its eradication. In many low-middle-income-countries (LMICs), aggregate HIV data reporting is done through the District Health Information S...
Preprint
Full-text available
Background The ability to report complete, accurate and timely data by HIV care providers and other entities is a key aspect in monitoring trends in HIV prevention, treatment and care, hence contributing to its eradication. In many low-middle-income-countries (LMICs), aggregate HIV data reporting is done through the District Health Information Soft...
Preprint
Full-text available
Background The ability to report complete, accurate and timely data by HIV care providers and other entities is a key aspect in monitoring trends in HIV prevention, treatment and care, hence contributing to its eradication. In many low-middle-income-countries (LMICs), aggregate HIV data reporting is done through the District Health Information Soft...
Preprint
Full-text available
Background The ability to report complete, accurate and timely data by HIV care providers and other entities is a key aspect in monitoring trends in HIV prevention, treatment and care, hence contributing to its eradication. In many low-middle-income-countries (LMICs), aggregate HIV data reporting is done through the District Health Information Soft...
Article
This paper presents experiences of integrating assistive robots in Japanese nursing care through semi-structured interviews and site observations at three nursing homes in Japan during the year 2019. The study looked at experiences with the robots Paro, Pepper, and Qoobo. The goal was to investigate and evaluate the current state of using robots wi...
Article
There is little evidence that implementations of Electronic Medical Record Systems (EMRs) are associated with better reporting completeness and timeliness of HIV routine data to the national aggregate system. We analyzed the reporting completeness and timeliness of HIV reports to Kenya's national aggregate reporting system from District Health Info...
Article
Health management information systems (HMISs) in low- and middle-income countries have been used to collect large amounts of data after years of implementation, especially in support of HIV care services. National-level aggregate reporting data derived from HMISs are essential for informed decision-making. However, the optimal statistical approache...
Article
Full-text available
This paper presents an original machine learning method for extracting diagnostic medical information from heart sound recordings. The method is proposed to be integrated with an intelligent phonocardiography in order to enhance diagnostic value of this technology. The method is tailored to diagnose children with heart septal defects, the pathologi...
Article
Full-text available
This paper presents experiences of integrating assistive robots in Japanese nursing care through semi-structured interviews and site observations at three nursing homes in Japan during the spring of 2019. The study looked at experiences with the robots Paro, Pepper, and Qoobo. The goal was to investigate and evaluate the current state of using robo...
Article
In low- and middle-income countries, private and public facilities tend to have highly variable characteristics, which might affect their performance in meeting reporting requirements mandated by ministries of health. There is conflicting evidence on which facility type performs better across various care dimensions, and only few studies exist to e...
Preprint
Full-text available
Background Electronic Health Record Systems (EHRs) are being rolled out nationally in many low- and middle-income countries (LMICs) yet assessing actual system usage remains a challenge. We employed a nominal group technique (NGT) process to systematically develop high-quality indicators for evaluating actual usage of EHRs in LMICs. Methods An init...
Preprint
Background The District Health Information Software 2 (DHIS2) is widely used by countries for national-level aggregate reporting of health data. To best leverage DHIS2 data for decision-making, countries need to ensure that data within their systems are of the highest quality. Comprehensive, systematic and transparent data cleaning approaches form...
Preprint
Full-text available
Background: The District Health Information Software-2 (DHIS2) is widely used by countries for national-level aggregate reporting of health-data. To best leverage DHIS2 data for decision-making, countries need to ensure that data within their systems are of the highest quality. Comprehensive, systematic, and transparent data cleaning approaches for...
Chapter
Full-text available
This paper presents a novel method for processing heart sound signal for screening forth heart sound (S4). The proposed method is based on time growing neural network with a new scheme, which we call the Backward Time-Growing Neural Network (BTGNN). The BTGNN is trained for detecting S4 in recordings of heart sound signal. In total, 83 children pat...
Chapter
Full-text available
This paper presents a sophisticated machine learning method for screening children with patent ductus arteriosus (PDA) using the phonocardiogram recording as the input signal. The method is based on our original algorithm for finding the discriminative contents of the signal for the healthy children and the diseased ones, which we called Short Time...
Article
Full-text available
This paper presents a mid-fidelity prototype of a mobile application for self-management of chronic disease Multiple Sclerosis (MS). The study focuses on newly diagnosed young Norwegians with MS and wants to deliver IT solutions for a healthier lifestyle. An analysis of a social media platform, interview with medical staff, a social media focus gro...
Article
Full-text available
A VR-based application was developed to explore the potential of mobile technology and the use of mobile-VR to assist in treatment, rehabilitation, and prevention of neck injuries. A prototype was developed through user-centered design and Google Sprint. The application simulated a typical set of exercises that a patient would get from a physiother...
Article
Full-text available
The very act of using indicators by converting the raw data collected to information for purposes such as monitoring, evaluation, decision-making, and management make indicators essential tools for health care services and health systems. In addition, Health Data Warehouses (HDWs) play an important role in the development, and the use of indicators...
Article
Full-text available
This paper presents a high-fidelity prototype of a mobile game for teaching children fundamental skills in first aid. The study utilizes expert interviews to define learning scope and evaluate the design. The game introduces two situations based on realistic scenarios; a boy who fell on a skateboard, and an elderly man with chest pains. Interactive...
Article
Full-text available
This paper presents a structure of decision support system for pediatric cardiac disease, based on an Internet of Things (IoT) framework. The structure performs the intelligent decision making at its edge processing level, which classifies the heart sound signal, to three classes of cardiac conditions, normal, mild disease, and critical disease. Th...
Article
Full-text available
Six people with Inflammatory Bowel Disease (IBD) were interviewed in a natural setting with the purpose of defining requirements for a new IBD mobile application. The first part of the interview had open disease related questions, and the second part involved evaluating three publically available IBD applications. Results suggest that the most impo...
Chapter
Full-text available
This paper presents a high-fidelity prototype of a mobile application for patient self-management within the field of Multiple Sclerosis (MS). Method. Development included mixed and high-fidelity prototypes which were based on the information needs inquired from the potential user groups and their reflection on publicly available applications. The...
Chapter
Full-text available
This paper presents a literature review of the existing tools for data capture in African rural settings. The objective has been to investigate and understand design approaches, usability, user satisfaction, as well as feasibility of capturing data using mobile device forms. Existing open source solutions are most commonly used in a variety of appl...
Chapter
Full-text available
Mobile Electronic Data Capturing Forms (MEDCFs) are electronic form applications that are primarily used for data capture using mobile devices in the place of paper-based routines. Translating paper-based forms to MEDCFs presents several usability challenges due to the design limitations of using mobile devices. The main objective of this study the...
Chapter
Full-text available
Several form design alternatives were created as a starting point for a usability evaluation in a project dedicated to maternal and child care in the rural Northern Ugandan area. The project is concerned with ensuring that pregnant mothers deliver from the hospitals and that their babies receive the necessary care after delivery, despite the limite...
Chapter
Full-text available
The health sector still lags behind in development of data visualization tools due to the complex nature of health data. Furthermore, due to the volume, velocity and veracity of health data consolidated from various sources, re-presenting them in a way that promotes decision-making while supporting various aspects of human interaction becomes even...
Article
Full-text available
Background New Specific Application Domain (SAD) heuristics or design principles are being developed to guide the design and evaluation of mobile applications in a bid to improve on the usability of these applications. This is because the existing heuristics are rather generic and are often unable to reveal a large number of mobile usability issues...
Preprint
Full-text available
BACKGROUND Mobile data collection systems are often difficult to use, for non-technical or novice users. This can be attributed to the fact that, developers of such tools do not adequately involve end-users in the design and development of product features and functions. This has led to products which seem obvious to the developers in their functio...
Article
Full-text available
Background Mobile data collection systems are often difficult to use for nontechnical or novice users. This can be attributed to the fact that developers of such tools do not adequately involve end users in the design and development of product features and functions, which often creates interaction challenges. Objective The main objective of this...
Conference Paper
Full-text available
This paper presents a mobile software application development for safety reporting of adverse events within the field of arthroplasty. Proposed user interface enables entry of data specific for adverse events of the knee and hip implants. Besides the patient data, the system supports entry of the event, its classification (serious, non-serious), it...
Conference Paper
Full-text available
This paper presents a novel method for detecting cardiac ejection murmurs from other pathological and physiological heart murmurs in children. The proposed method combines a hybrid model and a time growing neural network for an improved detection even in mild condition. Children with aortic stenosis and pulmonary stenosis comprised the patient cate...
Article
Full-text available
This paper presents a prototype of a mobile application for patient self-management within the field of Multiple Sclerosis (MS). Five study subjects provided information needs by suggesting functionalities and evaluating three existing MS applications. Prominent functionalities were to collect data about symptoms, physical activities, mood and goal...
Article
Full-text available
This paper presents user evaluation of a high-fidelity prototype of a mobile application for patient self-management within the field of Multiple Sclerosis (MS). The application named msHelse consists of four modules: Diary module, Summary module, Stress management module, and a Todo-list. Four study subjects were interviewed in semi-structured int...
Article
This paper presents a method for exploring structural risk of any artificial intelligence-based method in bioinformatics, the A-Test method. This method provides a way to not only quantitate the structural risk associated with a classification method, but provides a graphical representation to compare the learning capacity of different classificati...
Article
Patient specific forecasting tools are an area of active research and very much seen as a necessary tool for future improvements in healthcare. In order to succeed with decision making tools, fine-grained data are required to build models relevant and valid at an individual level. Location and assemble of data to build such tools is not trivial. Ev...
Article
Data informed decision-making (DIDM) plays a fundamental role in the fight against HIV and AIDS in Low-and-Middle-Income Countries (LMICs). Despite the scale-up of HIV care services, supported by health information systems (HIS), cases of under-utilization of data in decision-making are still being reported at different levels of the health system....
Article
Full-text available
Electronic Medical Records (EMR) systems show promise for facilitating health care improvement in quality patient care, patient safety and cost reduction. Nevertheless, their adoption requires careful planning and execution for successful implementation and optimal benefits. The main objective of this review was to identify, analyse and categorize...
Article
Full-text available
Data collectors collect health data using Mobile Electronic Data Collection Forms (MEDCFs) particularly in hard to reach areas. However, the usability and user acceptance of these forms by the data collectors are seldom considered, and yet these have an implication on the quality of the data collected and on the health decisions thereof. In this st...
Article
Full-text available
This paper presents a mobile software application development for e-learning based on the adverse events data within the field of arthroplasty. The application aims at providing a learning platform for physicians, patients, and medical students. Design of user interface aims to meet requirements of several user groups concerned with the adverse eve...
Article
This paper proposes a decision support system for screening pediatric cardiac disease in primary healthcare centres relying on the heart sound time series analysis. The proposed system employs our processing method which is based on the hidden Markov model for extracting appropriate information from the time series. The binary output resulting from...
Article
Full-text available
In this project, a mHealth tool for smart-phones has been developed using Design Science methodology, where the goal has been to promote an active lifestyle. This was undertaken by implementing social and physical activity stimulating features within the application MoveFit. Users can opt to utilize just a feature or two or engage in social activit...
Article
Full-text available
YouTube as an online video-sharing service in the context of Web 2.0 goes beyond the bounds of pure fun, for which the platform was primarily established. Nowadays, commonly to other social media, it serves also educational, informational and last but not least, marketing purposes. The importance of video sharing is supported by several predictions...
Article
Full-text available
This paper presents results of a study on the applicability of the intelligent phonocardiography in discriminating between Ventricular Spetal Defect (VSD) and regurgitation of the atrioventricular valves. An original machine learning method, based on the Time Growing Neural Network (TGNN), is employed for classifying the phonocardiographic recordin...
Article
Full-text available
Mobile Electronic Data Collection Tools (MEDCTs) are created by form developers to collect data. Usability being one of the top quality attributes is of great concern to developers of any interactive applications. However, little is known about the form developers' understanding of usability, how they measure usability and their limitations in desi...
Article
Full-text available
Pharmacovigilance is an important part of the patient safety and it has a great appeal to physicians. It is concerned with the safety of medical devices and treatments in the light of understanding the risks and dangers based on the already reported safety issues. Internet resources such as the Manufacturer And User Facility Device Experience (MAUD...
Article
Full-text available
This paper presents a safety reporting smartphone application which is expected to reduce the occurrence of postoperative adverse events after total hip arthroplasty (THA). A user-centered design approach was utilized to facilitate optimal user experience. Two main implemented functionalities capture patient pain levels and well-being, the two dime...
Article
Full-text available
In this project the potential of social media has been reviewed in terms how it can promote a healthy lifestyle utilized in an app. A mHealth app for smartphones has been developed using Design Science methodology, where various features from social media have been implemented with the goal of increasing physical activity. The application has been...
Article
Low-Middle-Income-Countries (LMICs) are beginning to adopt national health data warehousing (NHDWs) for making strategic decisions and for improving health outcomes. Given the numerous challenges likely to be faced in establishment of NHDWs by LMICs, it is prudent that evaluations are done in relation to the data warehouses (DWs), in order to ident...
Article
Full-text available
As healthcare organizations strive to improve quality of care and patient safety, it becomes paramount that they identify patients correctly and match records accurately both within and across institutions. Continuous care and population health benefits can be optimized when providers can have a comprehensive view of a patient's health record throu...
Article
Full-text available
Transitioning enterprise operations to the cloud brings a variety of opportunities and challenges. Such step requires a deep and complex understanding of all elements related to the technology as well as defining the manner in which specific cloud challenges can be dealt with. To provide a better understanding of these opportunities and challenges...
Article
Full-text available
This paper presents a study that has developed a mobile software application for assisting diagnosis of learning disabilities in mathematics, called dyscalculia, and measuring correlations between dyscalculia symptoms and magnocellular reasoning. Usually, software aids for dyscalculic individuals are focused on both assisting diagnosis and teaching...
Conference Paper
Full-text available
This study presents a screening algorithm for severe aortic stenosis (AS), based on a processing method for phonocardiographic (PCG) signal. The processing method employs a hybrid model, constituted of a hidden Markov model and support vector machine. The method benefits from a preprocessing phase for an enhanced learning. The performance of the me...
Article
Full-text available
The paper studies different user interfaces developed for visualizing data mined from cancer registries. The motivation behind this research is a need to create more flexible and smart, easy to use interfaces that will assist users in utilizing and exploring clinical information. The design process combined Parallel and Iterative design process mod...
Chapter
Full-text available
Storage, integration and presentation of clinical data is an important aspect of any modern medical research. The Biomaterials research group at the Haukeland University Hospital uses both their own locally generated clinical data and external registry data to examine explanted joint implants. As a solution to this challenge, a system prototype was...
Conference Paper
Full-text available
This study presents an algorithm for screening aortic stenosis, based on heart sound signal processing. It benefits from an artificial intelligent-based (AI-based) model using a multi-layer perceptron neural network. The AI-based model learns disease related murmurs using non-stationary features of the murmurs. Performance of the model is statistic...
Article
Full-text available
This paper proposes a framework for binary classification of the time series with cyclic characteristics. The framework presents an iterative algorithm for learning the cyclic characteristics by introducing the discriminative frequency bands (DFBs) using the discriminant analysis along with k-means clustering method. The DFBs are employed by a hybr...
Article
Full-text available
The main goal is to facilitate information technology to support patients by providing them a digital tool for daily logging of psychiatric symptoms and the integration of a crisis plan. This is presented in a project which places focus on a design of a mobile diary application. Interaction design and evaluation methodologies will be used throughou...
Article
Full-text available
Case Based Reasoning (CBR) methodology provides means of collecting patients cases and retrieving them following the clinical criteria. By studying previously treated patients with similar backgrounds, the physician can get a better base for deciding on treatment for a current patient and be better prepared for complications that might occur during...
Article
Full-text available
Self-reporting of symptoms is widely used and validated in the field of psychiatry, also in the context of bipolar disorder. This paper presents work on a self-reporting system for bipolar patients using a smartphone to gather data from the patient, which is communicated to a server via a secure connection. The data is presented in a web applicatio...
Article
Full-text available
Cancer registries are created, managed and data mined to gain knowledge about long term patient outcomes, effects of medication, clinical factors influencing patients' wellbeing. Equally important is the insight into the cost effectiveness of cancer treatments, and securing data input from different medical centers and enable competent data analysi...
Article
Full-text available
It is assumed that bipolar disorder patients can benefit from monitoring their mood, sleep, medicine intake and behavior which could be both done by patients themselves and in cooperation with health care professionals. This study aims at understanding what is required from a computerized system, as seen from the view of therapists and the patients...
Article
Full-text available
The Cherry project seeks to address the information needs of young cancer patients, their parents, and health care providers. It aims at helping the patients to understand various aspects of their disease and treatment, and allow them to assess and record their disease related quality of life. It uses elements of social media to offer a meeting poi...