Hanin Farhana Kamaruzaman

Hanin Farhana Kamaruzaman

Auto-generated profile, based on publicly available information

Hanin Farhana Kamaruzaman

University of Glasgow

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

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

Representative Publications

View All Publications
19 June 2025 in JMIR Medical Informatics
Verified
Journal Article
Open access
NANorah Hamad Alhumaidi
Norah Hamad Alhumaidi
DDDoni Dermawan
Doni Dermawan
HKHanin Farhana Kamaruzaman
Hanin Farhana Kamaruzaman
Nasser AlotaiqNasser Alotaiq
Nasser Alotaiq
Background: Machine learning (ML) and big data analytics are rapidly transforming health care, particularly disease prediction, management, and personalized care. With the increasing availability of real-world data (RWD) from diverse sources, such as electronic health records (EHRs), patient registries, and wearable devices, ML techniques present substantial potential to enhance clinical outcomes. Despite this promise, challenges such as data quality, model transparency, generalizability, and integration into clinical practice persist. Objective: This systematic review aims to examine the use of ML for analyzing RWD in disease prediction and management, identifying the most commonly used ML methods, prevalent disease types, study designs, and the sources of real-world evidence (RWE). It also explores the strengths and limitations of current practices, offering insights for future improvements. Methods: A comprehensive search was conducted following the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) guidelines to identify studies using ML techniques for analyzing RWD in disease prediction and management. The search focused on extracting data regarding the ML algorithms applied; disease categories studied; types of study designs (eg, clinical trials and cohort studies); and the sources of RWE, including EHRs, patient registries, and wearable devices. Studies published between 2014 and 2024 were included to ensure the analysis of the most recent advances in the field. Results: This review identified 57 studies that met the inclusion criteria, with a total sample size of >150,000 patients. The most frequently applied ML methods were random forest (n=24, 42%), logistic regression (n=21, 37%), and support vector machines (n=18, 32%). These methods were predominantly used for predictive modeling across disease areas, including cardiovascular diseases (n=19, 33%), cancer (n=9, 16%), and neurological disorders (n=6, 11%). RWE was primarily sourced from EHRs, patient registries, and wearable devices. A substantial portion of studies (n=38, 67%) focused on improving clinical decision-making, patient stratification, and treatment optimization. Among these studies, 14 (25%) focused on decision-making; 12 (21%) on health care outcomes, such as quality of life, recovery rates, and adverse events; and 11 (19%) on survival prediction, particularly in oncology and chronic diseases. For example, random forest models for cardiovascular disease prediction demonstrated an area under the curve of 0.85 (95% CI 0.81-0.89), while support vector machine models for cancer prognosis achieved an accuracy of 83% (P=.04). Despite the promising outcomes, many (n=34, 60%) studies faced challenges related to data quality, model interpretability, and ensuring generalizability across diverse patient populations. Conclusions: This systematic review highlights the significant potential of ML and big data analytics in health care, especially for improving disease prediction and management. However, to fully realize the benefits of these technologies, future research must focus on addressing the challenges of data quality, enhancing model transparency, and ensuring the broader applicability of ML models across diverse populations and clinical settings.

10 August 2022 in Pathogens and Global Health
Verified
Journal Article
Open access
AFAnna Falkowski
Anna Falkowski
GCGiorgio Ciminata
Giorgio Ciminata
FMFrancesco Manca
Francesco Manca
JBJanet Bouttell
Janet Bouttell
NJNishant Jaiswal
Nishant Jaiswal
EGEleanor Grieve
Eleanor Grieve
Health Technology Assessment (HTA) is a multidisciplinary tool to inform healthcare decision-making. HTA has been implemented in high-income countries (HIC) for several decades but has only recently seen a growing investment in low- and middle-income countries. A scoping review was undertaken to define and compare the role of HTA in least developed and lower middle-income countries (LLMIC). MEDLINE and EMBASE databases were searched from January 2015 to August 2021. A matrix comprising categories on HTA objectives, methods, geographies, and partnerships was used for data extraction and synthesis to present our findings. The review identified 50 relevant articles. The matrix was populated and sub-divided into further categories as appropriate. We highlight topical aspects of HTA, including initiatives to overcome well-documented challenges around data and capacity development, and identify gaps in the research for consideration. Those areas we found to be under-studied or under-utilized included disinvestment, early HTA/implementation, system-level interventions, and cross-sectoral partnerships. We consider broad practical implications for decision-makers and researchers aiming to achieve greater interconnectedness between HTA and health systems and generate recommendations that LLMIC can use for HTA implementation. Whilst HIC may have led the way, LLMIC are increasingly beginning to develop HTA processes to assist in their healthcare decision-making. This review provides a forward-looking model that LLMIC can point to as a reference for their own implementation. We hope this can be seen as timely and useful contributions to optimize the impact of HTA in an era of investment and expansion and to encourage debate and implementation.

20 July 2022 in International Journal of Technology Assessment in Health Care
Verified
Journal Article
Closed access
PDF file
HKHanin Farhana Kamaruzaman
Hanin Farhana Kamaruzaman
EGEleanor Grieve
Eleanor Grieve
OWOlivia Wu
Olivia Wu
Objectives: Disinvestment from low value health technologies is growing globally. Diverse evidence gathering and assessment methods were used to implement disinvestment initiatives, however, less than half of the empirical studies report reduced use of the low-value services. This scoping review aimed to synthesize the information from available reviews on the concepts and purposes of disinvestment in healthcare, the approaches and methods used, the role of stakeholders and facilitators and barriers in its implementation. Methods: This scoping review was guided by the Joanna Briggs Institute Manual for Evidence Synthesis and PRISMA statement for scoping review. Published reviews on disinvestment were identified from scientific databases including health technology assessment (HTA) Web sites using the terms “disinvestment,” “health technology reassessment,” and “healthcare.” The data obtained was synthesized narratively to identify similarities and differences across the approaches based on the prespecified categories. Results: Seventeen reviews were included with thirty-four initiatives identified across sixteen countries at various levels of implementation and responsible agencies for the activities. Two most used methods to facilitate disinvestment decisions are Programme Budgeting and Marginal Analysis (PBMA) and HTA. Stakeholder involvement is the most important aspect to be addressed, as it acts as both facilitator and barrier in disinvestment initiatives implementation. Conclusions: Disinvestment programs have been implemented at multilevel, involving multistakeholders and using multiple methods such as PBMA and HTA. However, there is a lack of clarity on the additional dimensions of technical analysis related to these tools. Further research could focus on technology optimization in healthcare as part of overall health technology management.

1 May 2020 in Value in Health Regional Issues
Verified
Journal Article
Closed access
KRKu Nurhasni Ku Abd Rahim
Ku Nurhasni Ku Abd Rahim
HKHanin Farhana Kamaruzaman
Hanin Farhana Kamaruzaman
MDMaznah Dahlui
Maznah Dahlui
SPSharifa Ezat Wan Puteh
Sharifa Ezat Wan Puteh

22 March 2021 in International Journal of Technology Assessment in Health Care
Verified
Journal Article
Closed access
PDF file
HKHanin Farhana Kamaruzaman
Hanin Farhana Kamaruzaman
KRKu Nurhasni Ku Abd Rahim
Ku Nurhasni Ku Abd Rahim
IGIzzuna Mudla Mohamed Ghazali
Izzuna Mudla Mohamed Ghazali
MYMohd Aminuddin Mohd Yusof
Mohd Aminuddin Mohd Yusof
Patient and public involvement (PPI) in health technology assessment (HTA) is widely promoted to ensure that all health-related decisions are made after taking into consideration the viewpoints of important stakeholders. In Malaysia, patients or their representatives have been involved in the development of HTA and Clinical Practice Guidelines (CPG) since 2009 and their influences have been growing steadily over the years. This paper aimed to describe the journey, achievements, challenges, and future direction of the PPI throughout all stages of the development and implementation of HTA and CPG in Malaysia. Currently, in Malaysia, patients or their representatives are mainly involved during the initial development of HTA and CPG drafts as well as during the internal and external reviews. Additionally, they are also encouraged to be involved during the implementation of HTA and CPG recommendations. Although their involvement in this aspect has slowly increased over time, challenges remain in the form of limited representativeness of selected patients or carers, uncertainty on the level of patient involvement allowed during the HTA/CPG development processes, and limited health literacy, which affect their ability to contribute meaningfully throughout the processes. Continuous improvement in these processes is important as patients or their representatives play a pivotal role in ensuring transparency, accountability, and credibility throughout the HTA/CPG development and decision-making processes.

5 March 2024 in Journal of the American Heart Association
Verified
Journal Article
Open access
KLKa Keat Lim
Ka Keat Lim
RKRositsa Koleva‐Kolarova
Rositsa Koleva‐Kolarova
HKHanin Farhana Kamaruzaman
Hanin Farhana Kamaruzaman
AKAhmad Amir Kamil
Ahmad Amir Kamil
PCPhil Chowienczyk
Phil Chowienczyk
JFJulia Fox‐Rushby
Julia Fox‐Rushby
Background: Genetic‐guided pharmacotherapy (PGx) is not recommended in clinical guidelines for coronary artery disease (CAD). We aimed to examine the extent and quality of evidence from economic evaluations of PGx in CAD and to identify variables influential in changing conclusions on cost‐effectiveness. Methods and Results: From systematic searches across 6 databases, 2 independent reviewers screened, included, and rated the methodological quality of economic evaluations of PGx testing to guide pharmacotherapy for patients with CAD. Of 35 economic evaluations included, most were model‐based cost‐utility analyses alone, or alongside cost‐effectiveness analyses of PGx testing to stratify patients into antiplatelets (25/35), statins (2/35), pain killers (1/35), or angiotensin‐converting enzyme inhibitors (1/35) to predict CAD risk (8/35) or to determine the coumadin doses (1/35). To stratify patients into antiplatelets (96/151 comparisons with complete findings of PGx versus non‐PGx), PGx was more effective and more costly than non‐PGx clopidogrel (28/43) but less costly than non‐PGx prasugrel (10/15) and less costly and less effective than non‐PGx ticagrelor (22/25). To predict CAD risk (51/151 comparisons), PGx using genetic risk scores was more effective and less costly than clinical risk score (13/17) but more costly than no risk score (16/19) or no treatment (9/9). The remaining comparisons were too few to observe any trend. Mortality risk was the most common variable (47/294) changing conclusions. Conclusions: Economic evaluations to date found PGx to stratify patients with CAD into antiplatelets or to predict CAD risk to be cost‐effective, but findings varied based on the non‐PGx comparators, underscoring the importance of considering local practice in deciding whether to adopt PGx.