Dataset Information

Unveiling the Black Box of Diagnostic and Clinical Decision Support Systems for Antenatal Care: Realist Evaluation.

ABSTRACT:

Background

Digital innovations have shown promise for improving maternal health service delivery. However, low- and middle-income countries are still at the adoption-utilization stage. Evidence on mobile health has been described as a black box, with gaps in theoretical explanations that account for the ecosystem of health care and their effect on adoption mechanisms. Bliss4Midwives, a modular integrated diagnostic kit to support antenatal care service delivery, was piloted for 1 year in Northern Ghana. Although both users and beneficiaries valued Bliss4Midwives, results from the pilot showed wide variations in usage behavior and duration of use across project sites.

Objective

To strengthen the design and implementation of an improved prototype, the study objectives were two-fold: to identify causal factors underlying the variation in Bliss4Midwives usage behavior and understand how to overcome or leverage these in subsequent implementation cycles.

Methods

Using a multiple case study design, a realist evaluation of Bliss4Midwives was conducted. A total of 3 candidate program theories were developed and empirically tested in 6 health facilities grouped into low and moderate usage clusters. Quantitative and qualitative data were collected and analyzed using realist thinking to build configurations that link intervention, context, actors, and mechanisms to program outcomes, by employing inductive and deductive reasoning. Nonparametric t test was used to compare the perceived usefulness and perceived ease of use of Bliss4Midwives between usage clusters.

Results

We found no statistically significant differences between the 2 usage clusters. Low to moderate adoption of Bliss4Midwives was better explained by fear, enthusiasm, and high expectations for service delivery, especially in the absence of alternatives. Recognition from pregnant women, peers, supervisors, and the program itself was a crucial mechanism for device utilization. Other supportive mechanisms included ownership, empowerment, motivation, and adaptive responses to the device, such as realignment and negotiation. Champion users displayed high adoption-utilization behavior in contexts of participative or authoritative supervision, yet used the device inconsistently. Intervention-related (technical challenges, device rotation, lack of performance feedback, and refresher training), context-related (staff turnover, competing priorities, and workload), and individual factors (low technological self-efficacy, baseline knowledge, and internal motivation) suppressed utilization mechanisms.

Conclusions

This study shed light on optimal conditions necessary for Bliss4Midwives to thrive in a complex social and organizational setting. Beyond usability and viability studies, advocates of innovative technologies for maternal care need to consider how implementation strategies and contextual factors, such as existing collaborations and supervision styles, trigger mechanisms that influence program outcomes. In addition to informing scale-up of the Bliss4Midwives prototype, our results highlight the need for interventions that are guided by research methods that account for complexity.

SUBMITTER: Abejirinde IO

PROVIDER: S-EPMC6320439 | biostudies-literature | 2018 Dec

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Unveiling the Black Box of Diagnostic and Clinical Decision Support Systems for Antenatal Care: Realist Evaluation.

Abejirinde Ibukun-Oluwa Omolade IO Zweekhorst Marjolein M Bardají Azucena A Abugnaba-Abanga Rudolf R Apentibadek Norbert N De Brouwere Vincent V van Roosmalen Jos J Marchal Bruno B

JMIR mHealth and uHealth 20181221 12

<h4>Background</h4>Digital innovations have shown promise for improving maternal health service delivery. However, low- and middle-income countries are still at the adoption-utilization stage. Evidence on mobile health has been described as a black box, with gaps in theoretical explanations that account for the ecosystem of health care and their effect on adoption mechanisms. Bliss4Midwives, a modular integrated diagnostic kit to support antenatal care service delivery, was piloted for 1 year in ...[more]

PMID: 30578177

Similar Datasets

Project description:State-of-the-art machine learning (ML) artificial intelligence methods are increasingly leveraged in clinical predictive modeling to provide clinical decision support systems to physicians. Modern ML approaches such as artificial neural networks (ANNs) and tree boosting often perform better than more traditional methods like logistic regression. On the other hand, these modern methods yield a limited understanding of the resulting predictions. However, in the medical domain, understanding of applied models is essential, in particular, when informing clinical decision support. Thus, in recent years, interpretability methods for modern ML methods have emerged to potentially allow explainable predictions paired with high performance. To our knowledge, we present in this work the first explainability comparison of two modern ML methods, tree boosting and multilayer perceptrons (MLPs), to traditional logistic regression methods using a stroke outcome prediction paradigm. Here, we used clinical features to predict a dichotomized 90 days post-stroke modified Rankin Scale (mRS) score. For interpretability, we evaluated clinical features' importance with regard to predictions using deep Taylor decomposition for MLP, Shapley values for tree boosting and model coefficients for logistic regression. With regard to performance as measured by Area under the Curve (AUC) values on the test dataset, all models performed comparably: Logistic regression AUCs were 0.83, 0.83, 0.81 for three different regularization schemes; tree boosting AUC was 0.81; MLP AUC was 0.83. Importantly, the interpretability analysis demonstrated consistent results across models by rating age and stroke severity consecutively amongst the most important predictive features. For less important features, some differences were observed between the methods. Our analysis suggests that modern machine learning methods can provide explainability which is compatible with domain knowledge interpretation and traditional method rankings. Future work should focus on replication of these findings in other datasets and further testing of different explainability methods.

Project description:BACKGROUND:Quality antenatal care (ANC) is recognised as an opportunity for screening and early identification of pregnancy-related complications. In rural Ghana, challenges with access to diagnostic services demotivate women from ANC attendance and referral compliance, leading to absent or late identification and management of high-risk women. In 2016, an integrated diagnostic and clinical decision support system tagged 'Bliss4Midwives' (B4M), was piloted in Northern Ghana. The device facilitated non-invasive screening of pre-eclampsia, gestational diabetes and anaemia at the point-of-care. This study aimed to explore the experiences of pregnant women with B4M, and its influence on service utilisation ("pull effect") and woman-provider relationships ("woman engagement"). METHODS:Through an embedded study design, qualitative methods including individual semi-structured interviews and non-participant observation were employed. Interviews were conducted with 20 pregnant women and 10 health workers, supplemented by ANC observations in intervention facilities. Secondary data on ANC registrations over a one-year period were extracted from health facility records to support findings on the perceived influence of B4M on service utilisation. RESULTS:Women's first impressions of the device were mostly emotive (excitement, fear), but sometimes neutral. Although it is inconclusive whether B4M increased ANC registration, pregnant women generally valued the availability of diagnostic services at the point-of-care. Additionally, by fostering some level of engagement, the intervention made women feel listened to and cared for. Process outcomes of the B4M encounter also showed that it was perceived as improving the skills and knowledge of the health worker, which facilitated trust in diagnostic recommendations and was therefore believed to motivate referral compliance. CONCLUSIONS:This study suggests that mHealth diagnostic and decision support devices enhance woman engagement and trust in health workers skills. There is need for further inquiry into how these interventions influence maternal health service utilization and women's expectations of pregnancy care.

Project description:Underuse and overuse of diagnostic tests have important implications for health outcomes and costs. Decision support technology purports to optimize the use of diagnostic tests in clinical practice. The objective of this review was to assess whether computerized clinical decision support systems (CCDSSs) are effective at improving ordering of tests for diagnosis, monitoring of disease, or monitoring of treatment. The outcome of interest was effect on the diagnostic test-ordering behavior of practitioners.We conducted a decision-maker-researcher partnership systematic review. We searched MEDLINE, EMBASE, Ovid's EBM Reviews database, Inspec, and reference lists for eligible articles published up to January 2010. We included randomized controlled trials comparing the use of CCDSSs to usual practice or non-CCDSS controls in clinical care settings. Trials were eligible if at least one component of the CCDSS gave suggestions for ordering or performing a diagnostic procedure. We considered studies 'positive' if they showed a statistically significant improvement in at least 50% of test ordering outcomes.Thirty-five studies were identified, with significantly higher methodological quality in those published after the year 2000 (p = 0.002). Thirty-three trials reported evaluable data on diagnostic test ordering, and 55% (18/33) of CCDSSs improved testing behavior overall, including 83% (5/6) for diagnosis, 63% (5/8) for treatment monitoring, 35% (6/17) for disease monitoring, and 100% (3/3) for other purposes. Four of the systems explicitly attempted to reduce test ordering rates and all succeeded. Factors of particular interest to decision makers include costs, user satisfaction, and impact on workflow but were rarely investigated or reported.Some CCDSSs can modify practitioner test-ordering behavior. To better inform development and implementation efforts, studies should describe in more detail potentially important factors such as system design, user interface, local context, implementation strategy, and evaluate impact on user satisfaction and workflow, costs, and unintended consequences.

Project description:ImportanceAn increasing number of machine learning (ML)-based clinical decision support systems (CDSSs) are described in the medical literature, but this research focuses almost entirely on comparing CDSS directly with clinicians (human vs computer). Little is known about the outcomes of these systems when used as adjuncts to human decision-making (human vs human with computer).ObjectivesTo conduct a systematic review to investigate the association between the interactive use of ML-based diagnostic CDSSs and clinician performance and to examine the extent of the CDSSs' human factors evaluation.Evidence reviewA search of MEDLINE, Embase, PsycINFO, and grey literature was conducted for the period between January 1, 2010, and May 31, 2019. Peer-reviewed studies published in English comparing human clinician performance with and without interactive use of an ML-based diagnostic CDSSs were included. All metrics used to assess human performance were considered as outcomes. The risk of bias was assessed using Quality Assessment of Diagnostic Accuracy Studies (QUADAS-2) and Risk of Bias in Non-Randomised Studies-Intervention (ROBINS-I). Narrative summaries were produced for the main outcomes. Given the heterogeneity of medical conditions, outcomes of interest, and evaluation metrics, no meta-analysis was performed.FindingsA total of 8112 studies were initially retrieved and 5154 abstracts were screened; of these, 37 studies met the inclusion criteria. The median number of participating clinicians was 4 (interquartile range, 3-8). Of the 107 results that reported statistical significance, 54 (50%) were increased by the use of CDSSs, 4 (4%) were decreased, and 49 (46%) showed no change or an unclear change. In the subgroup of studies carried out in representative clinical settings, no association between the use of ML-based diagnostic CDSSs and improved clinician performance could be observed. Interobserver agreement was the commonly reported outcome whose change was the most strongly associated with CDSS use. Four studies (11%) reported on user feedback, and, in all but 1 case, clinicians decided to override at least some of the algorithms' recommendations. Twenty-eight studies (76%) were rated as having a high risk of bias in at least 1 of the 4 QUADAS-2 core domains, and 6 studies (16%) were considered to be at serious or critical risk of bias using ROBINS-I.Conclusions and relevanceThis systematic review found only sparse evidence that the use of ML-based CDSSs is associated with improved clinician diagnostic performance. Most studies had a low number of participants, were at high or unclear risk of bias, and showed little or no consideration for human factors. Caution should be exercised when estimating the current potential of ML to improve human diagnostic performance, and more comprehensive evaluation should be conducted before deploying ML-based CDSSs in clinical settings. The results highlight the importance of considering supported human decisions as end points rather than merely the stand-alone CDSSs outputs.

Project description:BackgroundClinical decision support systems are designed to utilize medical data, knowledge, and analysis engines and to generate patient-specific assessments or recommendations to health professionals in order to assist decision making. Artificial intelligence-enabled clinical decision support systems aid the decision-making process through an intelligent component. Well-defined evaluation methods are essential to ensure the seamless integration and contribution of these systems to clinical practice.ObjectiveThe purpose of this study was to develop and validate a measurement instrument and test the interrelationships of evaluation variables for an artificial intelligence-enabled clinical decision support system evaluation framework.MethodsAn artificial intelligence-enabled clinical decision support system evaluation framework consisting of 6 variables was developed. A Delphi process was conducted to develop the measurement instrument items. Cognitive interviews and pretesting were performed to refine the questions. Web-based survey response data were analyzed to remove irrelevant questions from the measurement instrument, to test dimensional structure, and to assess reliability and validity. The interrelationships of relevant variables were tested and verified using path analysis, and a 28-item measurement instrument was developed. Measurement instrument survey responses were collected from 156 respondents.ResultsThe Cronbach α of the measurement instrument was 0.963, and its content validity was 0.943. Values of average variance extracted ranged from 0.582 to 0.756, and values of the heterotrait-monotrait ratio ranged from 0.376 to 0.896. The final model had a good fit (χ262=36.984; P=.08; comparative fit index 0.991; goodness-of-fit index 0.957; root mean square error of approximation 0.052; standardized root mean square residual 0.028). Variables in the final model accounted for 89% of the variance in the user acceptance dimension.ConclusionsUser acceptance is the central dimension of artificial intelligence-enabled clinical decision support system success. Acceptance was directly influenced by perceived ease of use, information quality, service quality, and perceived benefit. Acceptance was also indirectly influenced by system quality and information quality through perceived ease of use. User acceptance and perceived benefit were interrelated.

Project description:BackgroundDiagnostic errors pose significant health risks and contribute to patient mortality. With the growing accessibility of electronic health records, machine learning models offer a promising avenue for enhancing diagnosis quality. Current research has primarily focused on a limited set of diseases with ample training data, neglecting diagnostic scenarios with limited data availability.ObjectiveThis study aims to develop an information retrieval (IR)-based framework that accommodates data sparsity to facilitate broader diagnostic decision support.MethodsWe introduced an IR-based diagnostic decision support framework called CliniqIR. It uses clinical text records, the Unified Medical Language System Metathesaurus, and 33 million PubMed abstracts to classify a broad spectrum of diagnoses independent of training data availability. CliniqIR is designed to be compatible with any IR framework. Therefore, we implemented it using both dense and sparse retrieval approaches. We compared CliniqIR's performance to that of pretrained clinical transformer models such as Clinical Bidirectional Encoder Representations from Transformers (ClinicalBERT) in supervised and zero-shot settings. Subsequently, we combined the strength of supervised fine-tuned ClinicalBERT and CliniqIR to build an ensemble framework that delivers state-of-the-art diagnostic predictions.ResultsOn a complex diagnosis data set (DC3) without any training data, CliniqIR models returned the correct diagnosis within their top 3 predictions. On the Medical Information Mart for Intensive Care III data set, CliniqIR models surpassed ClinicalBERT in predicting diagnoses with <5 training samples by an average difference in mean reciprocal rank of 0.10. In a zero-shot setting where models received no disease-specific training, CliniqIR still outperformed the pretrained transformer models with a greater mean reciprocal rank of at least 0.10. Furthermore, in most conditions, our ensemble framework surpassed the performance of its individual components, demonstrating its enhanced ability to make precise diagnostic predictions.ConclusionsOur experiments highlight the importance of IR in leveraging unstructured knowledge resources to identify infrequently encountered diagnoses. In addition, our ensemble framework benefits from combining the complementary strengths of the supervised and retrieval-based models to diagnose a broad spectrum of diseases.

Project description:BackgroundAlthough there is widespread agreement that strong district manager decision-making improves health systems, understanding about how the design and implementation of capacity-strengthening interventions work is limited. The Ghana Health Service has adopted the Leadership Development Programme (LDP) as one intervention to support the development of management and leadership within district teams. This paper seeks to address how and why the LDP 'works' when it is introduced into a district health system in Ghana, and whether or not it supports systems thinking in district teams.MethodsWe undertook a realist evaluation to investigate the outcomes, contexts, and mechanisms of the intervention. Building on two working hypotheses developed from our earlier work, we developed an explanatory case study of one rural district in the Greater Accra Region of Ghana. Data collection included participant observation, document review, and semi-structured interviews with district managers prior to, during, and after the intervention. Working backwards from an in-depth analysis of the context and observed short- and medium-term outcomes, we drew a causal loop diagram to explain interactions between contexts, outcomes, and mechanisms.ResultsThe LDP was a valuable experience for district managers and teams were able to attain short-term outcomes because the novel approach supported teamwork, initiative-building, and improved prioritisation. However, the LDP was not institutionalised in district teams and did not lead to increased systems thinking. This was related to the context of high uncertainty within the district, and hierarchical authority of the system, which triggered the LDP's underlying goal of organisational control.ConclusionsConsideration of organisational context is important when trying to sustain complex interventions, as it seems to influence the gap between short- and medium-term outcomes. More explicit focus on systems thinking principles that enable district managers to better cope with their contexts may strengthen the institutionalisation of the LDP in the future.

Dataset Information

Unveiling the Black Box of Diagnostic and Clinical Decision Support Systems for Antenatal Care: Realist Evaluation.

Background

Objective

Methods

Results

Conclusions

Publications

Unveiling the Black Box of Diagnostic and Clinical Decision Support Systems for Antenatal Care: Realist Evaluation.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets