DESIGN: Qualitative study by means of semistructured interviews with women and key informants, using social-ecological model as a conceptual framework.
SETTING: Interviews were conducted in Kota Bharu district, Kelantan, a northeast state in Peninsular Malaysia.
PARTICIPANTS: Eighteen women of reproductive age (18 to 44 years old) that experienced their first marriage below the age of 18, as well as five key informants, consisting of a government officer, a community leader, an officer from religious department and two mothers. The women were recruited from a reproductive health clinic. The key informants who had specialised knowledge related to child marriage were selectively chosen.
RESULTS: Three themes emerged that aligned with the social-ecological model: immaturity in decision-making, family poverty and religious and cultural norms.
CONCLUSIONS: The findings imply that sex education and awareness-building activities regarding the consequences of child marriage must be implemented to eradicate child marriage in Malaysia. Such implementation must be coordinated as a team-based approach involving experts in such fields as law, religion, psychology, social-welfare and public health. In order to increase the awareness of child marriage consequences, the target for awareness must extend not only to the adolescent girls and their families, but also to the community and society at large by clearly communicating the negative consequences of and addressing the drivers for child marriage.
METHOD: For designing and modeling the DSPN severity grading systems for MNSI, 19 years of data from Epidemiology of Diabetes Interventions and Complications (EDIC) clinical trials were used. Different Machine learning-based feature ranking techniques were investigated to identify the important MNSI features associated with DSPN diagnosis. A multivariable logistic regression-based nomogram was generated and validated for DSPN severity grading using the best performing top-ranked MNSI features.
RESULTS: Top-10 ranked features from MNSI features: Appearance of Feet (R), Ankle Reflexes (R), Vibration perception (L), Vibration perception (R), Appearance of Feet (L), 10-gm filament (L), Ankle Reflexes (L), 10-gm filament (R), Bed Cover Touch, and Ulceration (R) were identified as important features for identifying DSPN by Multi-Tree Extreme Gradient Boost model. The nomogram-based prediction model exhibited an accuracy of 97.95% and 98.84% for the EDIC test set and an independent test set, respectively. A DSPN severity score technique was generated for MNSI from the DSPN severity prediction model. DSPN patients were stratified into four severity levels: absent, mild, moderate, and severe using the cut-off values of 17.6, 19.1, 20.5 for the DSPN probability less than 50%, 75%-90%, and above 90%, respectively.
CONCLUSIONS: The findings of this work provide a machine learning-based MNSI severity grading system which has the potential to be used as a secondary decision support system by health professionals in clinical applications and large clinical trials to identify high-risk DSPN patients.
METHODS: Methods used included policy analysis of legal, policy and regulatory framework documents, and in-depth interviews with key informants from governmental and non-governmental organisations in two States of Malaysia.
RESULTS: The findings show that women's NGOs and health professionals were instrumental in the formulation and scaling-up of the OSCC policy. However, the subsequent breakdown of the NGO-health coalition negatively impacted on the long-term implementation of the policy, which lacked financial resources and clear policy guidance from the Ministry of Health.
CONCLUSION: The findings confirm that a clearly-defined partnership between NGOs and health staff can be very powerful for influencing the legal and policy environment in which health care services for intimate partner violence are developed. It is critical to gain high level support from the Ministry of Health in order to institutionalise the violence-response across the entire health care system. Without clear operational details and resources policy implementation cannot be fully ensured and taken to scale.