-
Journal of Computing in Higher Education Mar 2023This article maps considerations of inclusiveness and support for students with disabilities by reviewing articles within the field of learning analytics. The study...
This article maps considerations of inclusiveness and support for students with disabilities by reviewing articles within the field of learning analytics. The study involved a PRISMA-informed systematic review of two popular digital libraries, namely Clarivate's Web of Science, and Elsevier's Scopus for peer-reviewed journal articles and conference proceedings. A final corpus of 26 articles was analysed. Findings show that although the field of learning analytics emerged in 2011, none of the studies identified here covered topics of inclusiveness in education before the year of 2016. Screening also shows that learning analytics provides great potential to promote inclusiveness in terms of reducing discrimination, increasing retention among disadvantaged students, and validating particular learning designs for marginalised groups. Gaps in this potential are also identified. The article aims to provide valuable insight into what is known about learning analytics and inclusiveness and contribute knowledge to this particular nascent area for researchers and institutional stakeholders.
PubMed: 37359042
DOI: 10.1007/s12528-023-09363-4 -
Professional Psychology, Research and... Aug 2022We conducted a systematic review to characterize features and evaluate outcomes of cultural competence trainings delivered to mental health providers. We reviewed 37...
We conducted a systematic review to characterize features and evaluate outcomes of cultural competence trainings delivered to mental health providers. We reviewed 37 training curricula described in 40 articles published between 1984-2019 and extracted information about curricular content (e.g., cultural identities), as well as training features (e.g., duration), methods (e.g., instructional strategies), and outcomes (i.e., attitudes, knowledge, skills). Training participants included graduate students and practicing professionals from a range of disciplines. Few studies (7.1%) employed a randomized-controlled trial design, instead favoring single-group (61.9%) or quasi-experimental (31.0%) designs. Many curricula focused on race/ethnicity (64.9%), followed by sexual orientation (45.9%) and general multicultural identity (43.2%). Few curricula included other cultural categorizations such as religion (16.2%), immigration status (13.5%), or socioeconomic status (13.5%). Most curricula included topics of sociocultural information (89.2%) and identity (78.4%), but fewer included topics such as discrimination and prejudice (54.1%). Lectures (89.2%) and discussions (86.5%) were common instructional strategies, whereas opportunities for application of material were less common (e.g., clinical experience: 16.2%; modeling: 13.5%). Cultural attitudes were the most frequently assessed training outcome (89.2%), followed by knowledge (81.1%) and skills (67.6%). To advance the science and practice of cultural competence trainings, we recommend that future studies include control groups, pre- and post-training assessment, and multiple methods for measuring multiple training outcomes. We also recommend consideration of cultural categories that are less frequently represented, how curricula might develop culturally competent providers beyond any single cultural category, and how best to leverage active learning strategies to maximize the impact of trainings.
PubMed: 37332624
DOI: 10.1037/pro0000469 -
Current Diabetes Reports Sep 2023Despite the crucial role that prediction models play in guiding early risk stratification and timely intervention to prevent type 2 diabetes after gestational diabetes... (Review)
Review
PURPOSE OF REVIEW
Despite the crucial role that prediction models play in guiding early risk stratification and timely intervention to prevent type 2 diabetes after gestational diabetes mellitus (GDM), their use is not widespread in clinical practice. The purpose of this review is to examine the methodological characteristics and quality of existing prognostic models predicting postpartum glucose intolerance following GDM.
RECENT FINDINGS
A systematic review was conducted on relevant risk prediction models, resulting in 15 eligible publications from research groups in various countries. Our review found that traditional statistical models were more common than machine learning models, and only two were assessed to have a low risk of bias. Seven were internally validated, but none were externally validated. Model discrimination and calibration were done in 13 and four studies, respectively. Various predictors were identified, including body mass index, fasting glucose concentration during pregnancy, maternal age, family history of diabetes, biochemical variables, oral glucose tolerance test, use of insulin in pregnancy, postnatal fasting glucose level, genetic risk factors, hemoglobin A1c, and weight. The existing prognostic models for glucose intolerance following GDM have various methodological shortcomings, with only a few models being assessed to have low risk of bias and validated internally. Future research should prioritize the development of robust, high-quality risk prediction models that follow appropriate guidelines, in order to advance this area and improve early risk stratification and intervention for glucose intolerance and type 2 diabetes among women who have had GDM.
Topics: Pregnancy; Female; Humans; Diabetes, Gestational; Glucose Intolerance; Diabetes Mellitus, Type 2; Postpartum Period; Glucose; Blood Glucose
PubMed: 37294513
DOI: 10.1007/s11892-023-01516-0 -
Digital Health 2023Systematic review of length of stay (LOS) prediction models to assess the study methods (including prediction variables), study quality, and performance of predictive... (Review)
Review
OBJECTIVE
Systematic review of length of stay (LOS) prediction models to assess the study methods (including prediction variables), study quality, and performance of predictive models (using area under receiver operating curve (AUROC)) for general surgery populations and total knee arthroplasty (TKA).
METHOD
LOS prediction models published since 2010 were identified in five major research databases. The main outcomes were model performance metrics including AUROC, prediction variables, and level of validation. Risk of bias was assessed using the PROBAST checklist.
RESULTS
Five general surgery studies (15 models) and 10 TKA studies (24 models) were identified. All general surgery and 20 TKA models used statistical approaches; 4 TKA models used machine learning approaches. Risk scores, diagnosis, and procedure types were predominant predictors used. Risk of bias was ranked as moderate in 3/15 and high in 12/15 studies. Discrimination measures were reported in 14/15 and calibration measures in 3/15 studies, with only 4/39 externally validated models (3 general surgery and 1 TKA). Meta-analysis of externally validated models (3 general surgery) suggested the AUROC 95% prediction interval is excellent and ranges between 0.803 and 0.970.
CONCLUSION
This is the first systematic review assessing quality of risk prediction models for prolonged LOS in general surgery and TKA groups. We showed that these risk prediction models were infrequently externally validated with poor study quality, typically related to poor reporting. Both machine learning and statistical modelling methods, plus the meta-analysis, showed acceptable to good predictive performance, which are encouraging. Moving forward, a focus on quality methods and external validation is needed before clinical application.
PubMed: 37284012
DOI: 10.1177/20552076231177497 -
Frontiers in Immunology 2023A high tumor mutation burden (TMB) is known to drive the response to immune checkpoint inhibitors (ICI) and is associated with favorable prognoses. However, because it...
A high tumor mutation burden (TMB) is known to drive the response to immune checkpoint inhibitors (ICI) and is associated with favorable prognoses. However, because it is a one-dimensional numerical representation of non-synonymous genetic alterations, TMB suffers from clinical challenges due to its equal quantification. Since not all mutations elicit the same antitumor rejection, the effect on immunity of neoantigens encoded by different types or locations of somatic mutations may vary. In addition, other typical genomic features, including complex structural variants, are not captured by the conventional TMB metric. Given the diversity of cancer subtypes and the complexity of treatment regimens, this paper proposes that tumor mutations capable of causing various degrees of immunogenicity should be calculated separately. TMB should therefore, be segmented into more exact, higher dimensional feature vectors to exhaustively measure the foreignness of tumors. We systematically reviewed patients' multifaceted efficacy based on a refined TMB metric, investigated the association between multidimensional mutations and integrative immunotherapy outcomes, and developed a convergent categorical decision-making framework, TMBserval (Statistical Explainable machine learning with Regression-based VALidation). TMBserval integrates a multiple-instance learning concept with statistics to create a statistically interpretable model that addresses the broad interdependencies between multidimensional mutation burdens and decision endpoints. TMBserval is a pan-cancer-oriented many-to-many nonlinear regression model with discrimination and calibration power. Simulations and experimental analyses using data from 137 actual patients both demonstrated that our method could discriminate between patient groups in a high-dimensional feature space, thereby rationally expanding the beneficiary population of immunotherapy.
Topics: Humans; Neoplasms; Biomarkers, Tumor; Prognosis; Immunotherapy; Mutation
PubMed: 37234148
DOI: 10.3389/fimmu.2023.1151755 -
Journal of Clinical Epidemiology Jun 2023We evaluated the presence and frequency of spin practices and poor reporting standards in studies that developed and/or validated clinical prediction models using... (Review)
Review
OBJECTIVES
We evaluated the presence and frequency of spin practices and poor reporting standards in studies that developed and/or validated clinical prediction models using supervised machine learning techniques.
STUDY DESIGN AND SETTING
We systematically searched PubMed from 01/2018 to 12/2019 to identify diagnostic and prognostic prediction model studies using supervised machine learning. No restrictions were placed on data source, outcome, or clinical specialty.
RESULTS
We included 152 studies: 38% reported diagnostic models and 62% prognostic models. When reported, discrimination was described without precision estimates in 53/71 abstracts (74.6% [95% CI 63.4-83.3]) and 53/81 main texts (65.4% [95% CI 54.6-74.9]). Of the 21 abstracts that recommended the model to be used in daily practice, 20 (95.2% [95% CI 77.3-99.8]) lacked any external validation of the developed models. Likewise, 74/133 (55.6% [95% CI 47.2-63.8]) studies made recommendations for clinical use in their main text without any external validation. Reporting guidelines were cited in 13/152 (8.6% [95% CI 5.1-14.1]) studies.
CONCLUSION
Spin practices and poor reporting standards are also present in studies on prediction models using machine learning techniques. A tailored framework for the identification of spin will enhance the sound reporting of prediction model studies.
Topics: Humans; Prognosis; Machine Learning
PubMed: 37024020
DOI: 10.1016/j.jclinepi.2023.03.024 -
Journal of Clinical Epidemiology May 2023In biomedical research, spin is the overinterpretation of findings, and it is a growing concern. To date, the presence of spin has not been evaluated in prognostic model... (Review)
Review
OBJECTIVES
In biomedical research, spin is the overinterpretation of findings, and it is a growing concern. To date, the presence of spin has not been evaluated in prognostic model research in oncology, including studies developing and validating models for individualized risk prediction.
STUDY DESIGN AND SETTING
We conducted a systematic review, searching MEDLINE and EMBASE for oncology-related studies that developed and validated a prognostic model using machine learning published between 1st January, 2019, and 5th September, 2019. We used existing spin frameworks and described areas of highly suggestive spin practices.
RESULTS
We included 62 publications (including 152 developed models; 37 validated models). Reporting was inconsistent between methods and the results in 27% of studies due to additional analysis and selective reporting. Thirty-two studies (out of 36 applicable studies) reported comparisons between developed models in their discussion and predominantly used discrimination measures to support their claims (78%). Thirty-five studies (56%) used an overly strong or leading word in their title, abstract, results, discussion, or conclusion.
CONCLUSION
The potential for spin needs to be considered when reading, interpreting, and using studies that developed and validated prognostic models in oncology. Researchers should carefully report their prognostic model research using words that reflect their actual results and strength of evidence.
Topics: Humans; Medical Oncology; Prognosis; Research; Machine Learning
PubMed: 36935090
DOI: 10.1016/j.jclinepi.2023.03.012 -
Human Resources For Health Mar 2023Rural pipeline approach has recently gain prominent recognition in improving the availability of health workers in hard-to-reach areas such as rural and poor regions.... (Review)
Review
INTRODUCTION
Rural pipeline approach has recently gain prominent recognition in improving the availability of health workers in hard-to-reach areas such as rural and poor regions. Understanding implications for its successful implementation is important to guide health policy and decision-makers in Sub-Saharan Africa. This review aims to synthesize the evidence on rural pipeline implementation and impacts in sub-Saharan Africa.
METHODS
We conducted a scoping review using Joanna Briggs Institute guidebook. We searched in PubMed and Google scholar databases and the grey literature. We conducted a thematic analysis to assess the studies. Data were reported following the PRISMA extension for Scoping reviews guidelines.
RESULTS
Of the 443 references identified through database searching, 22 met the inclusion criteria. Rural pipeline pillars that generated impacts included ensuring that more rural students are selected into programmes; developing a curriculum oriented towards rural health and rural exposure during training; curriculum oriented to rural health delivery; and ensuring retention of health workers in rural areas through educational and professional support. These impacts varied from one pillar to another and included: increased in number of rural health practitioners; reduction in communication barriers between healthcare providers and community members; changes in household economic and social circumstances especially for students from poor family; improvement of health services quality; improved health education and promotion within rural communities; and motivation of community members to enrol their children in school. However, implementation of rural pipeline resulted in some unintended impacts such as perceived workload increased by trainee's supervisors; increased job absenteeism among senior health providers; patients' discomfort of being attended by students; perceived poor quality care provided by students which influenced health facilities attendance. Facilitating factors of rural pipeline implementation included: availability of learning infrastructures in rural areas; ensuring students' accommodation and safety; setting no age restriction for students applying for rural medical schools; and appropriate academic capacity-building programmes for medical students. Implementation challenges included poor preparation of rural health training schools' candidates; tuition fees payment; limited access to rural health facilities for students training; inadequate living and working conditions; and perceived discrimination of rural health workers.
CONCLUSION
This review advocates for combined implementation of rural pipeline pillars, taking into account the specificity of country context. Policy and decision-makers in sub-Saharan Africa should extend rural training programmes to involve nurses, midwives and other allied health professionals. Decision-makers in sub-Saharan Africa should also commit more for improving rural living and working environments to facilitate the implementation of rural health workforce development programmes.
Topics: Child; Humans; Health Workforce; Rural Population; Health Services Accessibility; Health Services; Health Personnel
PubMed: 36918864
DOI: 10.1186/s12960-023-00801-z -
European Heart Journal. Quality of Care... Jun 2023Cardiovascular disease (CVD) risk prediction is important for guiding the intensity of therapy in CVD prevention. Whilst current risk prediction algorithms use... (Meta-Analysis)
Meta-Analysis
Machine-learning versus traditional approaches for atherosclerotic cardiovascular risk prognostication in primary prevention cohorts: a systematic review and meta-analysis.
BACKGROUND
Cardiovascular disease (CVD) risk prediction is important for guiding the intensity of therapy in CVD prevention. Whilst current risk prediction algorithms use traditional statistical approaches, machine learning (ML) presents an alternative method that may improve risk prediction accuracy. This systematic review and meta-analysis aimed to investigate whether ML algorithms demonstrate greater performance compared with traditional risk scores in CVD risk prognostication.
METHODS AND RESULTS
MEDLINE, EMBASE, CENTRAL, and SCOPUS Web of Science Core collections were searched for studies comparing ML models to traditional risk scores for CVD risk prediction between the years 2000 and 2021. We included studies that assessed both ML and traditional risk scores in adult (≥18 year old) primary prevention populations. We assessed the risk of bias using the Prediction Model Risk of Bias Assessment Tool (PROBAST) tool. Only studies that provided a measure of discrimination [i.e. C-statistics with 95% confidence intervals (CIs)] were included in the meta-analysis. A total of 16 studies were included in the review and meta-analysis (3302 515 individuals). All study designs were retrospective cohort studies. Out of 16 studies, 3 externally validated their models, and 11 reported calibration metrics. A total of 11 studies demonstrated a high risk of bias. The summary C-statistics (95% CI) of the top-performing ML models and traditional risk scores were 0.773 (95% CI: 0.740-0.806) and 0.759 (95% CI: 0.726-0.792), respectively. The difference in C-statistic was 0.0139 (95% CI: 0.0139-0.140), P < 0.0001.
CONCLUSION
ML models outperformed traditional risk scores in the discrimination of CVD risk prognostication. Integration of ML algorithms into electronic healthcare systems in primary care could improve identification of patients at high risk of subsequent CVD events and hence increase opportunities for CVD prevention. It is uncertain whether they can be implemented in clinical settings. Future implementation research is needed to examine how ML models may be utilized for primary prevention.This review was registered with PROSPERO (CRD42020220811).
Topics: Adult; Humans; Adolescent; Cardiovascular Diseases; Risk Factors; Retrospective Studies; Heart Disease Risk Factors; Machine Learning; Primary Prevention
PubMed: 36869800
DOI: 10.1093/ehjqcco/qcad017 -
Anaesthesia May 2023Estimating pre-operative mortality risk may inform clinical decision-making for peri-operative care. However, pre-operative mortality risk prediction models are rarely... (Review)
Review
Estimating pre-operative mortality risk may inform clinical decision-making for peri-operative care. However, pre-operative mortality risk prediction models are rarely implemented in routine clinical practice. High predictive accuracy and clinical usability are essential for acceptance and clinical implementation. In this systematic review, we identified and appraised prediction models for 30-day postoperative mortality in non-cardiac surgical cohorts. PubMed and Embase were searched up to December 2022 for studies investigating pre-operative prediction models for 30-day mortality. We assessed predictive performance in terms of discrimination and calibration. Risk of bias was evaluated using a tool to assess the risk of bias and applicability of prediction model studies. To further inform potential adoption, we also assessed clinical usability for selected models. In all, 15 studies evaluating 10 prediction models were included. Discrimination ranged from a c-statistic of 0.82 (MySurgeryRisk) to 0.96 (extreme gradient boosting machine learning model). Calibration was reported in only six studies. Model performance was highest for the surgical outcome risk tool (SORT) and its external validations. Clinical usability was highest for the surgical risk pre-operative assessment system. The SORT and risk quantification index also scored high on clinical usability. We found unclear or high risk of bias in the development of all models. The SORT showed the best combination of predictive performance and clinical usability and has been externally validated in several heterogeneous cohorts. To improve clinical uptake, full integration of reliable models with sufficient face validity within the electronic health record is imperative.
Topics: Humans; Clinical Decision-Making; Risk Assessment
PubMed: 36823388
DOI: 10.1111/anae.15988