Transparent Reporting Research Articles

Do socially responsible firms demonstrate a preference for using classification shifting to manage earnings?

Prior research finds socially responsible firms are less likely to engage in earnings management, suggesting that socially responsible firms seek to provide more transparent financial reports (Hong and Anderson 2011; Kim, Park, and Wier 2012; Hwang, Choi, Choi, and Lee 2022). We investigate whether managers of CSR firms demonstrate a preference for classification shifting when making trade-off decisions among earnings management methods. First, our results support prior studies that find the overall extent of earnings management is lower for CSR firms. However, this study focuses on the use of classification shifting relative to other forms of earnings management. We find a robust positive relation between CSR performance and the relative use of classification shifting. Our results suggest that while CSR firms engage in lower levels of earnings management they demonstrate a preference to choose classification shifting when engaging in earnings management. These findings are consistent with managers perceiving classification shifting as a less unethical tool relative to accruals earnings management or real activities manipulation. Subsequent analyses reveal that our results are most pronounced for firms with lower external monitoring where managers have the most freedom to make trade-off decisions among earnings management methods based on ethical considerations. Overall, by demonstrating a preference for classification shifting relative to other earnings management tools our study furthers our understanding of the role of ethical considerations in earnings management decisions.

AI predictive models and advancements in microdissection testicular sperm extraction for non-obstructive azoospermia: a systematic scoping review

Abstract STUDY QUESTION How accurately can artificial intelligence (AI) models predict sperm retrieval in non-obstructive azoospermia (NOA) patients undergoing micro-testicular sperm extraction (m-TESE) surgery? SUMMARY ANSWER AI predictive models hold significant promise in predicting successful sperm retrieval in NOA patients undergoing m-TESE, although limitations regarding variability of study designs, small sample sizes and a lack of validation studies restrict the overall generalizability of studies in this area. WHAT IS KNOWN ALREADY Previous studies have explored various predictors of successful sperm retrieval in m-TESE, including clinical and hormonal factors. However, no consistent predictive model has yet been established. STUDY DESIGN, SIZE, DURATION A comprehensive literature search was conducted following PRISMA-ScR guidelines, covering PubMed and Scopus databases from 2013 to May 15th, 2024. Relevant English-language studies were identified using Medical Subject Headings (MeSH) terms. We also used PubMed’s “similar articles” and “cited by” features for thorough bibliographic screening to ensure comprehensive coverage of relevant literature. PARTICIPANTS/MATERIALS, SETTING, METHODS The review included studies on patients with NOA where AI-based models were used for predicting m-TESE outcomes, by incorporating clinical data, hormonal levels, histopathological evaluations and genetic parameters. Various machine learning and deep learning techniques, including logistic regression, were employed. The Prediction Model Risk of Bias Assessment Tool (PROBAST) evaluated the bias in the studies, and their quality was assessed using the Transparent Reporting of a Multivariable Prediction Model for Individual Prognosis or Diagnosis (TRIPOD) guidelines, ensuring robust reporting standards and methodological rigour. MAIN RESULTS AND THE ROLE OF CHANCE Out of 427 screened articles, 45 met the inclusion criteria, with most using logistic regression and machine learning to predict m-TESE outcomes. AI-based models demonstrated strong potential by integrating clinical, hormonal and biological factors. However, limitations of the studies included small sample sizes, legal barriers and challenges in generalizability and validation. While some studies featured larger, multi-centre designs, many were constrained by sample size. Most studies had a low risk of bias in participant selection and outcome determination, and two-thirds were rated as low risk for predictor assessment, but the analysis methods varied. LIMITATIONS, REASONS FOR CAUTION The limitations of this review include the heterogeneity of the included research, potential publication bias and reliance on only two databases (PUBMED and SCOPUS), which may limit the scope of findings. Additionally, the absence of a meta-analysis prevents quantitative assessment of the consistency of models. Despite this, the review offers valuable insights into AI predictive models for m-TESE in NOA. WIDER IMPLICATIONS OF THE FINDINGS The review highlights the potential of advanced AI techniques in predicting successful sperm retrieval for NOA patients undergoing m-TESE. By integrating clinical, hormonal, histopathological and genetic factors, AI models can enhance decision-making and improve patient outcomes, reducing the number of unsuccessful procedures. However, to further enhance the precision and reliability of AI predictions in reproductive medicine, future studies should address current limitations by incorporating larger sample sizes and conducting prospective validation trials. This continued research and development is crucial for strengthening the applicability of AI models and ensuring broader clinical adoption. STUDY FUNDING/COMPETING INTEREST(S) The authors would like to acknowledge Mashhad University of Medical Sciences, Mashhad, Iran, for financial support (Grant ID : 4020802). The authors declare no competing interests. REGISTRATION NUMBER N/A

Effect of Self-Proning on Respiratory Functions, Pneumonia Severity, and Mortality Risk Among Patients Diagnosed With Community-Acquired Pneumonia: A Nursing-Based Quasi-Experimental Study.

Assessing and monitoring respiratory parameters, such as respiratory rate, oxygen saturation, and lung sounds, is crucial for the management and prognosis of pneumonia patients. Prone positioning has been shown to improve oxygenation in patients with respiratory disorders, including pneumonia, by reducing ventilation/perfusion mismatch. However, there is a lack of evidence supporting the benefits of self-proning in spontaneously breathing pneumonia patients. This study aims to evaluate the effect of self-proning on respiratory functions, pneumonia, and mortality risk among patients diagnosed with community-acquired pneumonia. The study used a pre- and post-test quasi-experimental design with a control group, adhering to the Transparent Reporting of Evaluations with Nonrandomized Designs guidelines. It was conducted in the Medical Respiratory Department inpatient wards at the Respiratory Diseases Hospital in Alexandria, Egypt. The study recruited 128 patients with community-acquired pneumonia, conveniently assigned to an intervention group (n = 64) and a control group (n = 64). Data were collected using socio-demographic and historical data sheets, respiratory parameters assessment sheets, the confusion uremia respiratory rate and blood pressure (CURB-65) severity of pneumonia score, and the Pneumonia Severity Index. Prone positioning significantly positively impacted respiratory parameters in the intervention group compared to the control group. Specifically, the intervention group exhibited improvements in respiratory rate, oxygen saturation, reduced need for supplemental oxygen, and cough (p < .05). Furthermore, the intervention group exhibited fewer changes in findings from chest inspection, palpation, and auscultation. In addition, the severity of pneumonia was reduced in the intervention group compared to the control group, as indicated by lower CURB-65 (p = .014) and pneumonia severity index scores (p = .005). The study demonstrated that self-proning interventions significantly improved respiratory functions and reduced the risk of death among participants with community-acquired pneumonia. These findings suggest that self-proning is a beneficial technique for managing respiratory distress, particularly in non-intubated patients, and can be an effective strategy to improve patient outcomes in clinical settings.

PERANCANGAN SISTEM INFORMASI AKUNTANSI BERBASIS FRAMEWORK CODEIGNITER PADA MASJID AN NUR KABUPATEN SANGGAU

The mosque is a non-profit organization, whose income is based on voluntary donations from the community. The An Nur Mosque's financial management still uses conventional or manual methods. To improve accountable and transparent financial reporting, an accounting information system design was created that uses a website with the codeigniter framework method at the An Nur Mosque in Sanggau Regency, West Kalimantan. This research aims to develop an accounting information system that uses the codeigniter framework, with a focus on making it easier to prepare financial reports for the An Nur Mosque. The research method applied is descriptive qualitative with a waterfall method approach which includes various steps such as needs analysis, design, implementation and testing. The results of this research show that the design of an accounting information system can help non-profit organizations, especially the An Nur Mosque, in preparing more accurate and transparent financial reports.

Is transparency furthering clarity in multilateral climate governance? The case of climate finance

AbstractDeveloping countries’ ambitious climate action hinges on the provision of climate finance from developed countries. Yet, despite decades of debate and contestation over this, substantial controversies continue to persist over whether and how much climate finance is flowing, including whether it is ‘new and additional’ to existing development assistance, whether it targets climate mitigation or adaptation, and whether it is delivered as grants or loans. In this article, we draw on a little-examined source of self-reporting by countries to shed light on these persisting climate finance controversies. Elaborate transparency arrangements have been set up under the United Nations Framework Convention on Climate Change (UNFCCC), whereby countries report on climate finance provided and received. We examine transparency reports submitted by 26 countries from 2014 to 2021 by both developed and developing countries, and international review of these reports, to ascertain the extent to which country self-reporting under the UNFCCC sheds light on the nature of climate finance flows between developed and developing countries. We find that both the reports submitted and the international review of these reports are not furthering clarity around climate finance provided and received. This is because of (a) a persisting lack of multilaterally agreed definitions of key aspects of climate finance provided, and a resulting heterogeneity of definitions used by countries to self-report; and (b) because international review of country self-reporting is subject to politically negotiated limitations. We conclude that clarity remains elusive on climate finance provided and received under the UNFCCC, a situation that seems likely to continue under the Paris Agreement’s enhanced transparency framework, due to be implemented in 2024.

Development and validation of a prediction model for ED using machine learning: according to NHANES 2001–2004

Erectile Dysfunction (ED) is a form of sexual dysfunction in males that imposes significant health and financial burdens globally. Despite its high prevalence, diagnosing ED remains challenging due to the limitations of current diagnostic methods and patients’ reluctance to seek medical help. Currently, some studies have used machine learning techniques for developing ED prediction models, but the performance and interpretability of existing models need to be further improved. This study utilized data from the National Health and Nutrition Examination Survey (NHANES) for the years 2001 to 2004, adhering to the Transparent Reporting of a Multivariable Prediction Model for Individual Prognosis or Diagnosis (TRIPOD) statement. After excluding male respondents who did not meet the study criteria, a total of 3,869 participants were included. Gradient boosting decision tree (GBDT) algorithms (XGBoost, CatBoost, LightGBM) were used to develop the ED prediction model. Data preprocessing, feature selection, model evaluation, and interpretability analysis were performed to ensure the reliability and effectiveness of the model. The model evaluation results revealed that the AUC values are XGBoost: 0.887 ± 0.016; LightGBM: 0.879 ± 0.016; CatBoost: 0.871 ± 0.019. The F1-Scores are XGBoost: 0.695 ± 0.023; LightGBM: 0.681 ± 0.025; CatBoost: 0.681 ± 0.025. The Recall values are XGBoost: 0.789 ± 0.026; LightGBM: 0.739 ± 0.030; CatBoost: 0.711 ± 0.030. These results confirmed that the XGBoost model is the best-performing ED prediction model in this study. Interpretability analysis results of the XGBoost model showed that age, obesity, cardiovascular risk factors, prostate-related diseases, and socioeconomic status are key features for predicting ED, playing a significant role in the ED mechanism. Therefore, we believe the ED prediction model trained in this study has strong predictive performance and high interpretability. This model can help to expand the diagnostic options for ED, improve the diagnosis rate of ED, and assist doctors in early intervention for patients with ED, ultimately improving patient prognosis.

CEO Connectedness and Firm Transparency

ABSTRACTOur research reveals that CEO connections with Audit Committee directors, established through past employment, education, or social organization memberships, significantly impact firm transparency. These connections increase the likelihood of firms issuing less transparent and readable financial reports. Furthermore, these connections are linked to decreased long‐term firm value and increased crash risk. Our findings underscore the crucial role of CEO connectedness in corporate disclosure transparency and firm value. We employed multiple methodologies to address endogeneity concerns. Our results remain robust.

Do’s and Don’ts in Climate Impact Assessment of University Campuses: Towards Responsible, Transparent and Comprehensive Reporting

With the commitment of more and more universities to decrease greenhouse gas emissions, standardizing the modeling is now becoming urgent. To date, published climate-relevant emissions can be based on completely different and incomparable accounting methods, as shown with results between 6 and 2696 t CO2e for the use phase of the same campus. This article aims to identify, compare, and evaluate the different modeling approaches behind this. For this purpose, this article proposes basic attributes of emissions modeling and reporting. Of the three established approaches to emissions accounting, sector logic (territorial carbon accounting) produces the lowest figures. Reporting in accordance with the greenhouse gas protocol, which has become established worldwide, can also shift the responsibility outside the institutional consumer. Life-cycle assessment, instead, essentially includes provision costs triggered by the consumer. The different modeling approaches also overlap with different coverage of emission sources, for which a standard set is being proposed. Such emissions modeling should finally lead to the determination of university-specific climate performances, i.e., the CO2e emissions per capita and per m2 of gross floor area. Infrastructure and procurement expenses must be recorded in addition and converted to an annual average.

Foundation Model Transparency Reports

Foundation models are critical digital technologies with sweeping societal impact that necessitates transparency. To codify how foundation model developers should provide transparency about the development and deployment of their models, we propose Foundation Model Transparency Reports, drawing upon the transparency reporting practices in social media. While external documentation of societal harms prompted social media transparency reports, our objective is to institutionalize transparency reporting for foundation models while the industry is still nascent. To design our reports, we identify 6 design principles given the successes and shortcomings of social media transparency reporting. To further schematize our reports, we draw upon the 100 transparency indicators from the Foundation Model Transparency Index. Given these indicators, we measure the extent to which they overlap with the transparency requirements included in six prominent government policies (e.g. the EU AI Act, the US Executive Order on Safe, Secure, and Trustworthy AI). Well-designed transparency reports could reduce compliance costs, in part due to overlapping regulatory requirements across different jurisdictions. We encourage foundation model developers to regularly publish transparency reports, building upon recommendations from the G7 and the White House.

Machine learning approaches for risk prediction after percutaneous coronary intervention: a systematic review and meta-analysis

Abstract Aims Accurate prediction of clinical outcomes following percutaneous coronary intervention (PCI) is essential for mitigating risk and peri-procedural planning. Traditional risk models have demonstrated a modest predictive value. Machine learning (ML) models offer an alternative risk stratification that may provide improved predictive accuracy. Methods and results This study was reported according to the Preferred Reporting Items for Systematic Reviews and Meta-Analyses, Critical Appraisal and Data Extraction for Systematic Reviews of Prediction Modelling Studies and Transparent Reporting of a multivariable prediction model for Individual Prognosis or Diagnosis guidelines. PubMed, EMBASE, Web of Science, and Cochrane databases were searched until 1 November 2023 for studies comparing ML models with traditional statistical methods for event prediction after PCI. The primary outcome was comparative discrimination measured by C-statistics with 95% confidence intervals (CIs) between ML models and traditional methods in estimating the risk of all-cause mortality, major bleeding, and the composite outcome major adverse cardiovascular events (MACE). Thirty-four models were included across 13 observational studies (4 105 916 patients). For all-cause mortality, the pooled C-statistic for top-performing ML models was 0.89 (95%CI, 0.84–0.91), compared with 0.86 (95% CI, 0.80–0.93) for traditional methods (P = 0.54). For major bleeding, the pooled C-statistic for ML models was 0.80 (95% CI, 0.77–0.84), compared with 0.78 (95% CI, 0.77–0.79) for traditional methods (P = 0.02). For MACE, the C-statistic for ML models was 0.83 (95% CI, 0.75–0.91), compared with 0.71 (95% CI, 0.69–0.74) for traditional methods (P = 0.007). Out of all included models, only one model was externally validated. Calibration was inconsistently reported across all models. Prediction Model Risk of Bias Assessment Tool demonstrated a high risk of bias across all studies. Conclusion Machine learning models marginally outperformed traditional risk scores in the discrimination of MACE and major bleeding following PCI. While integration of ML algorithms into electronic healthcare systems has been hypothesized to improve peri-procedural risk stratification, immediate implementation in the clinical setting remains uncertain. Further research is required to overcome methodological and validation limitations.

Recommended Minimum Elements for Transparent Reporting of Multi-Jurisdiction Algorithm Feasibility Studies

BackgroundResearch and surveillance using routinely collected health data rely on algorithms to ascertain disease cases or health measures. Where algorithm validation studies are not possible due to lack of a reference standard, algorithm feasibility studies can be used to create and assess algorithms for use in more than one population or jurisdiction. Publication of the methods used to conduct feasibility studies is critical for transparency and reproducibility. Existing guidelines applicable to feasibility studies, including the STrengthening the Reporting of OBservational studies in Epidemiology (STROBE) and REporting of studies Conducted using Observational Routinely collected health Data (RECORD) statements, may benefit from additional elements to capture aspects particular to multi-jurisdiction algorithm feasibility studies and ensure full reproducibility. MethodsA subcommittee of members from Health Data Research Network (HDRN) Canada’s Algorithms and Harmonized Data Working Group (AHD-WG) reviewed items within the STROBE and RECORD guidelines and compared these to published feasibility studies. Items not contained within STROBE or RECORD but recommended to ensure transparent reporting of feasibility studies were identified. The AHD-WG reviewed and approved these additional recommended elements. ResultsEleven additional recommended elements were identified: one element for the title and abstract, one in the introduction, five in the methods, and four in the results sections. Elements primarily addressed reporting jurisdictional data variabilities, data harmonization methods, and algorithm implementation. SignificanceImplementation of these recommended elements, alongside the RECORD guidelines, is intended to encourage consistent publication of methods that support reproducibility, as well as increase comparability and international collaborations.

Multivariate time series approaches to extract predictive asthma biomarkers from prospectively patient-collected diary data: a systematic review

ObjectivesLongitudinal data are common in asthma studies, to assess asthma progression in patients and identify predictors of future outcomes, including asthma exacerbations and asthma control. Different methods can quantify temporal...

The Urgency Of Implementing Sharia Accounting In Sharia Financial Institutions In The Indonesian Context: Bibliometric Analysis

Sharia accounting has an important role in a sharia bank to help record financial reports. through recording financial reports will help produce quality, ideal and transparent financial report information. This research aims to determine the mapping of sharia accounting research on Sharia Financial Institutions in Indonesia from 2013 to 2023 and find out the importance of implementing sharia accounting in Sharia Financial Institutions. The approach used is quantitative with bibliometric analysis methods. The data source used is secondary data from the Garuda portal (Garba Reference Digital) and analyzed using VOSviewer software. The research results show that the number of scientific article publications on the application of sharia accounting in sharia financial institutions from 2001 to 2023 was 107 articles divided into 8 clusters and 58 topics.

Using Artificial Intelligence in ESG Assurance

ABSTRACT As environmental, social, and governance (ESG) reporting has become a mainstream channel for companies to communicate their commitment to sustainability issues, the need for reliable and transparent ESG reports is increasing. However, research on ESG assurance is still in its early stages. ESG assurance poses more challenges than traditional financial auditing due to the diverse subjects and types of information in ESG reports. This paper proposes using artificial intelligence (AI) technologies and exogenous data as solutions. It discusses how AI can enhance the efficiency and effectiveness of ESG assurance by assessing vast and extensive data. This paper also explores AI’s application throughout the general ESG assurance process and contributes to the discussion on providing high-quality ESG assurance services. Additionally, it provides practical implications for auditors, regulators, and stakeholders.

Health technology assessment in mental health services.

Mental illnesses have a significant impact on the lives of people not only because of their morbidity but also because of their noticeable impact on economic wellbeing. Out-of-pocket expenditure for mental healthcare services is significant in India and may even lead to impoverishment of the families. The present paper states that Health Technology Assessment (HTA) is necessary for mental healthcare primarily because of its rising cost and competing interests in government decisions and prioritization. HTA does a systematic evaluation of the consequences of using health technology. HTA will provide information to decision makers to develop and implement safer, cost-effective, and efficient policies at the individual and government levels. Appropriate guidance regarding the cost-effectiveness of mental health interventions will help to serve the purpose of providing transparent reports in the context of limited budgets.

The Effect of Nursing Counseling on Treatment Compliance: Acute Coronary Syndrome and Diabetes Mellitus.

The comorbidity of acute coronary syndrome and diabetes affects patient prognoses. Therefore, it is important to manage these diseases simultaneously. In this study, the effect of nursing counseling on treatment compliance was investigated in patients who had received surgical treatment for acute coronary syndrome and had been recently diagnosed with diabetes. A quasi-experimental design with pretest-posttest control group was used. The study sample consisted of 60 patients (intervention group = 30, control group = 30). The data were collected using a patient information form, the Patient Learning Needs Scale, and the Scale for Patient Compliance with Type 2 Diabetes Mellitus Treatment. This study was conducted in compliance with the Transparent Reporting of Evaluations with Nonrandomized Designs checklist. The intervention group earned significantly higher posttest scores on the Patient Learning Needs total scale and subscales than the control group. Moreover, intervention group compliance with treatment was higher than that of the control group. Furthermore, although significant improvements were found in the average posttest body mass index, fasting blood glucose, HbA1c, total cholesterol, triglyceride, and low-density lipoprotein cholesterol values of the control group, the between-group differences in these values were not significant. It is important for nurses to provide counseling services that align with the learning needs of their patients. Also, nursing counseling units should be created and staffed by both specialist nurses and nurse trainers working in healthcare institutions.

The Influence of Human Resource Competencies on The Quality of Financial Statements: Lessons from Indonesia

The increasing demand for good governance has encouraged the government to implement public accountability. One form of accountability in governance is to realize the accountability and transparency of government financial management, through the submission of accountability reports in the form of financial statements. The Navy Headquarters Work Unit is also tasked with preparing accountable and transparent financial reports. Empirical facts show that there are still several problems in realizing the quality of the financial statements (LK) of the Headquarters Satker, especially those caused by the competence of human resources (HR). This study aims to determine the effect of Human Resources competence on the quality of the Headquarters Satker financial statements. The population in this study were personnel serving in the Navy Finance Service (Diskual). The research method used is quantitative with a survey design. The results of this study found that: 1) Human Resource Competence has a positive and significant effect on the quality of Financial Statements. The limitations of this study are put forward as a reference for further research to produce better research. Some of these limitations are the uneven diversity/variation of age, length of service and work experience of respondents (across generations) and data collection carried out at a certain time, so that variations in perception are uneven and cannot be seen continuously.

Gluten-Free Diet Adherence Tools for Individuals with Celiac Disease: A Systematic Review and Meta-Analysis of Tools Compared to Laboratory Tests.

This systematic review aimed to find the tool that best predicts celiac individuals' adherence to a gluten-free diet (GFD). The Transparent Reporting of Multivariable Prediction Models for Individual Prognosis or Diagnosis (TRIPOD-SRMA) guideline was used for the construction and collection of data from eight scientific databases (PubMed, EMBASE, LILACS, Web of Science, LIVIVO, SCOPUS, Google Scholar, and Proquest) on 16 November 2023. The inclusion criteria were studies involving individuals with celiac disease (CD) who were over 18 years old and on a GFD for at least six months, using a questionnaire to predict adherence to a GFD, and comparing it with laboratory tests (serological tests, gluten immunogenic peptide-GIP, or biopsy). Review articles, book chapters, and studies without sufficient data were excluded. The Checklist for Critical Appraisal and Data Extraction for Systematic Reviews of Prediction Modeling Studies (CHARMS) was used for data collection from the selected primary studies, and their risk of bias and quality was assessed using the Prediction Risk of Bias Assessment Tool (PROBAST). The association between the GFD adherence determined by the tool and laboratory test was assessed using the phi contingency coefficient. The studies included in this review used four different tools to evaluate GFD adherence: BIAGI score, Coeliac Dietary Adherence Test (CDAT), self-report questions, and interviews. The comparison method most often used was biopsy (n = 19; 59.3%), followed by serology (n = 14; 43.7%) and gluten immunogenic peptides (GIPs) (n = 4; 12.5%). There were no significant differences between the interview, self-report, and BIAGI tools used to evaluate GFD adherence. These tools were better associated with GFD adherence than the CDAT. Considering their cost, application time, and prediction capacity, the self-report and BIAGI were the preferred tools for evaluating GFD adherence.

Machine-learning-based prediction of disability progression in multiple sclerosis: An observational, international, multi-center study.

Disability progression is a key milestone in the disease evolution of people with multiple sclerosis (PwMS). Prediction models of the probability of disability progression have not yet reached the level of trust needed to be adopted in the clinic. A common benchmark to assess model development in multiple sclerosis is also currently lacking. Data of adult PwMS with a follow-up of at least three years from 146 MS centers, spread over 40 countries and collected by the MSBase consortium was used. With basic inclusion criteria for quality requirements, it represents a total of 15, 240 PwMS. External validation was performed and repeated five times to assess the significance of the results. Transparent Reporting for Individual Prognosis Or Diagnosis (TRIPOD) guidelines were followed. Confirmed disability progression after two years was predicted, with a confirmation window of six months. Only routinely collected variables were used such as the expanded disability status scale, treatment, relapse information, and MS course. To learn the probability of disability progression, state-of-the-art machine learning models were investigated. The discrimination performance of the models is evaluated with the area under the receiver operator curve (ROC-AUC) and under the precision recall curve (AUC-PR), and their calibration via the Brier score and the expected calibration error. All our preprocessing and model code are available at https://gitlab.com/edebrouwer/ms_benchmark, making this task an ideal benchmark for predicting disability progression in MS. Machine learning models achieved a ROC-AUC of 0⋅71 ± 0⋅01, an AUC-PR of 0⋅26 ± 0⋅02, a Brier score of 0⋅1 ± 0⋅01 and an expected calibration error of 0⋅07 ± 0⋅04. The history of disability progression was identified as being more predictive for future disability progression than the treatment or relapses history. Good discrimination and calibration performance on an external validation set is achieved, using only routinely collected variables. This suggests machine-learning models can reliably inform clinicians about the future occurrence of progression and are mature for a clinical impact study.

Machine learning in the prediction of treatment response in rheumatoid arthritis: A systematic review

ObjectiveThis study aimed to investigate the current status and performance of machine learning (ML) approaches in providing reproducible treatment response predictions. MethodsThis systematic review was conducted in accordance with the PRISMA statement and the CHARMS checklist. We searched PubMed, Cochrane Library, Web of Science, Scopus, and EBSCO databases for cohort studies that derived and/or validated ML models focused on predicting rheumatoid arthritis (RA) treatment response. We extracted data and critically appraised studies based on the Transparent Reporting of a Multivariable Prediction Model for Individual Prognosis or Diagnosis (TRIPOD) and Prediction Model Risk of Bias Assessment Tool (PROBAST) guidelines. ResultsFrom 210 unduplicated records identified by the literature search, we retained 29 eligible studies. Of these studies, 10 developed a predictive model and reported a mean adherence to the TRIPOD guidelines of 45.6 % (95 % CI: 38.3–52.8 %). The remaining 19 studies not only developed a predictive model but also validated it externally, with a mean adherence of 42.9 % (95 % CI: 39.1–46.6 %). Most of the articles had an unclear risk of bias (41.4 %), followed by a high risk of bias, which was present in 37.9 %. ConclusionsIn recent years, ML methods have been increasingly used to predict treatment response in RA. Our critical appraisal revealed unclear and high risk of bias in most of the identified models, suggesting that researchers can do more to address the risk of bias and increase transparency, including the use of calibration measures and reporting methods for handling missing data. FundingNone.