Health Referral Enterprise Architecture Design in Indonesia

An adaptive data-driven architecture for mental health care applications

Background

In the current era of rapid technological innovation, our lives are becoming more closely intertwined with digital systems. Consequently, every human action generates a valuable repository of digital data. In this context, data-driven architectures are pivotal for organizing, manipulating, and presenting data to facilitate positive computing through ensemble machine learning models. Moreover, the COVID-19 pandemic underscored a substantial need for a flexible mental health care architecture. This architecture, inclusive of machine learning predictive models, has the potential to benefit a larger population by identifying individuals at a heightened risk of developing various mental disorders.

Objective

Therefore, this research aims to create a flexible mental health care architecture that leverages data-driven methodologies and ensemble machine learning models. The objective is to proficiently structure, process, and present data for positive computing. The adaptive data-driven architecture facilitates customized interventions for diverse mental disorders, fostering positive computing. Consequently, improved mental health care outcomes and enhanced accessibility for individuals with varied mental health conditions are anticipated.

Method

Following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines, the researchers conducted a systematic literature review in databases indexed in Web of Science to identify the existing strengths and limitations of software architecture relevant to our adaptive design. The systematic review was registered in PROSPERO (CRD42023444661). Additionally, a mapping process was employed to derive essential paradigms serving as the foundation for the research architectural design. To validate the architecture based on its features, professional experts utilized a Likert scale.

Results

Through the review, the authors identified six fundamental paradigms crucial for designing architecture. Leveraging these paradigms, the authors crafted an adaptive data-driven architecture, subsequently validated by professional experts. The validation resulted in a mean score exceeding four for each evaluated feature, confirming the architecture's effectiveness. To further assess the architecture's practical application, a prototype architecture for predicting pandemic anxiety was developed.

The Implementation of Diagnostic Assessment in Breast Lump Cases: A Cross-Sectional Study in Sragen, Indonesia

Introduction Triple assessment, consisting of clinical breast examination, breast imaging, and fine-needle aspiration biopsy (FNAB), is the gold standard for breast lump diagnosis to avoid diagnostic errors. However, current diagnostic practices for breast lump cases in Indonesia are widely variable and evidence for triple assessment implementation is lacking. We aimed to explore the implementation of diagnostic assessments in breast lump cases, its influencing factors, and its association with diagnostic error. Methods This cross-sectional study consecutively recruited 364 females with breast lumps who underwent surgery in Soehadi Prijonegoro Public Hospital, Sragen, Indonesia. Data were retrospectively collected from patient's medical records. Diagnostic assessments were classified as single assessment with clinical breast examination, double assessment with clinical breast examination and breast ultrasonography (USG) or fine-needle aspiration biopsy (FNAB), and triple assessment. Diagnostic error was defined as a discrepancy between pre- and post-surgery diagnosis or repeated surgery without neoadjuvant chemotherapy. Factors associated with diagnostic assessment implementation, diagnostic error, and repeated surgery were analyzed using the chi-square test. Results The choice of diagnostic assessment was influenced by patients' age and health insurance (p<0.001). Triple assessment was only implemented in 21 (5.8%) breast lump cases. It was more frequently applied in patients ≥40 years (57.1%) and patients with contributory health insurance (76.2%). Diagnostic errors were observed in 84 cases (23.1%) and 47 patients out of them (47%) experienced repeated surgery. The implementation of diagnostic assessments was not associated with diagnostic error (p=0.257) but was significantly associated with repeated surgery in breast cancer (p<0.001). Repeated surgery rates were significantly lowered in cases receiving double assessment with FNAB (p<0.001). Conclusions The implementation of triple assessment in the local setting was very low. The choice of diagnostic assessment was influenced by patients' age and health insurance. Further, double assessment applying clinical breast examination and FNAB significantly decreased repeated surgery rates and thus may serve as an alternative to triple assessment in the limited resource setting.

A New eHealth Investment Appraisal Framework for Africa: Validation

(1) Background: Decisions to use eHealth are complex and involve addressing a large opportunity cost. Sound choices are essential. Weighing up investment options is challenging in resource-constrained settings where there are frequently insufficient economics data and expertise to conduct adequate appraisals. To address this, a new eHealth Investment Appraisal Framework (eHIAF) for Africa has been designed and developed. The aim of this paper was to validate the new framework to consider whether it is fit for purpose and to refine it as needed. (2) Methods: An online survey of purposively selected eHealth experts was used to conduct a desktop validation of the proposed eHIAF for Africa. The survey covered the framework development process, structure, content, completeness, and utility. Expert opinions were charted, and a reflective and iterative process used to assess the tool and extract recommendations for refinement. (3) Results: Eleven eHealth experts who completed the survey had experience in African countries and elsewhere. The majority agreed with the eHIAF for Africa development approach and output. They provided valuable suggestions for minor refinements and felt that with these amendments, the eHIAF for Africa would be 'fit for purpose'. (4) Conclusions: The eHIAF for Africa is considered appropriate for use by policy- and decision-makers working in resource-constrained settings who face the task of selecting optimal eHealth investments. It has the potential for applicability beyond Africa and the framework should now be tested in African countries.

Barriers in Health Information Systems and Technologies to Support Maternal and Neonatal Referrals at Primary Health Centers

Objectives

This study explored health workers’ perceptions and experiences regarding the maternal and neonatal referral system, focusing on barriers of health information systems and technologies (IS/IT) at primary health centers (PHCs) in South Tangerang, Indonesia.

Methods

This qualitative study was conducted using semi-structured interviews, which were conducted at the South Tangerang District Health Office and three PHCs. Interviews were conducted with nine participants responsible for maternal and neonatal referrals in their organizations. The data were analyzed using qualitative content analysis.

Results

In South Tangerang, the Primary Health Care Information System (SIMPUS) is used to register patients and record data on medical treatment. To facilitate referrals, the PHCs currently use the Integrated Referral Information System (SISRUTE), P-Care, and the Integrated Emergency Management System (SPGDT). The following four IS/IT barriers to support maternal and neonatal referrals were found: technology, human resources, organizational support, and the referral process and implementation.

Conclusions

The barriers in technology, human resources, and organizational support cause problems in the maternal and neonatal referral process and in the implementation of referrals. Barriers to referrals can influence patients’ ability to receive appropriate care in a timely fashion and lead to inefficiency in maternal and neonatal referrals. This study contributes knowledge about IS/IT implementation in maternal and neonatal referral systems and provides recommendations to health regulators and application developers for the implementation of IS/IT in Indonesia.

Designing a health referral mobile application for high-mobility end users in Indonesia

OBJECTIVE

The purpose of this study was to design a suitable mobile application for high mobility medical staff to support the health referral system of Indonesian universal health coverage.

METHODS

Design science research (DSR) approach were conducted with two iterations. The first iteration was conducted by designing a high-fidelity mockup and evaluating the design using the System Usability Scale (SUS) framework to evaluate the overall usability of the system (n = 48). The second iteration was conducted by designing a running prototype and evaluating the design using the Post-Study System Usability Questionnaire (PSSUQ) framework to evaluate the system's usefulness, information quality, and interface quality (n = 31). For designing the user interface, the eight golden rules guided the process.

RESULTS

The results found that the design for the first iteration was good and the second iteration's design was satisfactory to the respondents. The information quality aspects underwent several changes such as the implementation of local language as the users deemed it to be important to help them easily understand and use the system and eventually support their mobility at the health facility.