Completeness of reporting of clinical prediction models developed using supervised machine learning: a systematic review

AI Quality Standards in Health Care: Rapid Umbrella Review

BACKGROUND

In recent years, there has been an upwelling of artificial intelligence (AI) studies in the health care literature. During this period, there has been an increasing number of proposed standards to evaluate the quality of health care AI studies.

OBJECTIVE

This rapid umbrella review examines the use of AI quality standards in a sample of health care AI systematic review articles published over a 36-month period.

METHODS

We used a modified version of the Joanna Briggs Institute umbrella review method. Our rapid approach was informed by the practical guide by Tricco and colleagues for conducting rapid reviews. Our search was focused on the MEDLINE database supplemented with Google Scholar. The inclusion criteria were English-language systematic reviews regardless of review type, with mention of AI and health in the abstract, published during a 36-month period. For the synthesis, we summarized the AI quality standards used and issues noted in these reviews drawing on a set of published health care AI standards, harmonized the terms used, and offered guidance to improve the quality of future health care AI studies.

RESULTS

We selected 33 review articles published between 2020 and 2022 in our synthesis. The reviews covered a wide range of objectives, topics, settings, designs, and results. Over 60 AI approaches across different domains were identified with varying levels of detail spanning different AI life cycle stages, making comparisons difficult. Health care AI quality standards were applied in only 39% (13/33) of the reviews and in 14% (25/178) of the original studies from the reviews examined, mostly to appraise their methodological or reporting quality. Only a handful mentioned the transparency, explainability, trustworthiness, ethics, and privacy aspects. A total of 23 AI quality standard-related issues were identified in the reviews. There was a recognized need to standardize the planning, conduct, and reporting of health care AI studies and address their broader societal, ethical, and regulatory implications.

CONCLUSIONS

Despite the growing number of AI standards to assess the quality of health care AI studies, they are seldom applied in practice. With increasing desire to adopt AI in different health topics, domains, and settings, practitioners and researchers must stay abreast of and adapt to the evolving landscape of health care AI quality standards and apply these standards to improve the quality of their AI studies.

REFORMS: Consensus-based Recommendations for Machine-learning-based Science

Machine learning (ML) methods are proliferating in scientific research. However, the adoption of these methods has been accompanied by failures of validity, reproducibility, and generalizability. These failures can hinder scientific progress, lead to false consensus around invalid claims, and undermine the credibility of ML-based science. ML methods are often applied and fail in similar ways across disciplines. Motivated by this observation, our goal is to provide clear recommendations for conducting and reporting ML-based science. Drawing from an extensive review of past literature, we present the REFORMS checklist (recommendations for machine-learning-based science). It consists of 32 questions and a paired set of guidelines. REFORMS was developed on the basis of a consensus of 19 researchers across computer science, data science, mathematics, social sciences, and biomedical sciences. REFORMS can serve as a resource for researchers when designing and implementing a study, for referees when reviewing papers, and for journals when enforcing standards for transparency and reproducibility.

Prediction model protocols indicate better adherence to recommended guidelines for study conduct and reporting

BACKGROUND AND OBJECTIVE

Protocols are invaluable documents for any research study, especially for prediction model studies. However, the mere existence of a protocol is insufficient if key details are omitted. We reviewed the reporting content and details of the proposed design and methods reported in published protocols for prediction model research.

METHODS

We searched MEDLINE, Embase, and the Web of Science Core Collection for protocols for studies developing or validating a diagnostic or prognostic model using any modeling approach in any clinical area. We screened protocols published between Jan 1, 2022 and June 30, 2022. We used the abstract, introduction, methods, and discussion sections of The Transparent Reporting of a multivariable prediction model of Individual Prognosis Or Diagnosis (TRIPOD) statement to inform data extraction.

RESULTS

We identified 30 protocols, of which 28 were describing plans for model development and six for model validation. All protocols were open access, including a preprint. 15 protocols reported prospectively collecting data. 21 protocols planned to use clustered data, of which one-third planned methods to account for it. A planned sample size was reported for 93% development and 67% validation analyses. 16 protocols reported details of study registration, but all protocols reported a statement on ethics approval. Plans for data sharing were reported in 13 protocols.

CONCLUSION

Protocols for prediction model studies are uncommon, and few are made publicly available. Those that are available were reasonably well-reported and often described their methods following current prediction model research recommendations, likely leading to better reporting and methods in the actual study.

Machine learning algorithms to predict outcomes in children and adolescents with COVID-19: A systematic review

BACKGROUND AND OBJECTIVES

We aimed to analyze the study designs, modeling approaches, and performance evaluation metrics in studies using machine learning techniques to develop clinical prediction models for children and adolescents with COVID-19.

METHODS

We searched four databases for articles published between 01/01/2020 and 10/25/2023, describing the development of multivariable prediction models using any machine learning technique for predicting several outcomes in children and adolescents who had COVID-19.

RESULTS

We included ten articles, six (60 % [95 % confidence interval (CI) 0.31 - 0.83]) were predictive diagnostic models and four (40% [95 % CI 0.170.69]) were prognostic models. All models were developed to predict a binary outcome (n= 10/10, 100 % [95 % CI 0.72-1]). The most frequently predicted outcome was disease detection (n=3/10, 30% [95 % CI 0.11-0.60]). The most commonly used machine learning models in the studies were tree-based (n=12/33, 36.3% [95 % CI 0.17-0.47]) and neural networks (n=9/27, 33.2% [95% CI 0.15-0.44]).

CONCLUSION

Our review revealed that attention is required to address problems including small sample sizes, inconsistent reporting practices on data preparation, biases in data sources, lack of reporting metrics such as calibration and discrimination, hyperparameters and other aspects that allow reproducibility by other researchers and might improve the methodology.

Evaluating the clinical utility of an easily applicable prediction model of suicide attempts, newly developed and validated with a general community sample of adults

BACKGROUND

A suicide attempt (SA) is a clinically serious action. Researchers have argued that reducing long-term SA risk may be possible, provided that at-risk individuals are identified and receive adequate treatment. Algorithms may accurately identify at-risk individuals. However, the clinical utility of algorithmically estimated long-term SA risk has never been the predominant focus of any study.

METHODS

The data of this report stem from CoLaus|PsyCoLaus, a prospective longitudinal study of general community adults from Lausanne, Switzerland. Participants (N = 4,097; Mage = 54 years, range: 36-86; 54% female) were assessed up to four times, starting in 2003, approximately every 4-5 years. Long-term individual SA risk was prospectively predicted, using logistic regression. This algorithm's clinical utility was assessed by net benefit (NB). Clinical utility expresses a tool's benefit after having taken this tool's potential harm into account. Net benefit is obtained, first, by weighing the false positives, e.g., 400 individuals, at the risk threshold, e.g., 1%, using its odds (odds of 1% yields 1/(100-1) = 1/99), then by subtracting the result (400*1/99 = 4.04) from the true positives, e.g., 5 individuals (5-4.04), and by dividing the result (0.96) by the sample size, e.g., 800 (0.96/800). All results are based on 100 internal cross-validations. The predictors used in this study were: lifetime SA, any lifetime mental disorder, sex, and age.

RESULTS

SA at any of the three follow-up study assessments was reported by 1.2%. For a range of seven a priori selected threshold probabilities, ranging between 0.5% and 2%, logistic regression showed highest overall NB in 97.4% of all 700 internal cross-validations (100 for each selected threshold probability).

CONCLUSION

Despite the strong class imbalance of the outcome (98.8% no, 1.2% yes) and only four predictors, clinical utility was observed. That is, using the logistic regression model for clinical decision making provided the most true positives, without an increase of false positives, compared to all competing decision strategies. Clinical utility is one among several important prerequisites of implementing an algorithm in routine practice, and may possibly guide a clinicians' treatment decision making to reduce long-term individual SA risk. The novel metric NB may become a standard performance measure, because the a priori invested clinical considerations enable clinicians to interpret the results directly.

The reporting completeness and transparency of systematic reviews of prognostic prediction models for COVID-19 was poor: a methodological overview of systematic reviews

OBJECTIVES

To conduct a methodological overview of reviews to evaluate the reporting completeness and transparency of systematic reviews (SRs) of prognostic prediction models (PPMs) for COVID-19.

STUDY DESIGN AND SETTING

MEDLINE, Scopus, Cochrane Database of Systematic Reviews, and Epistemonikos (epistemonikos.org) were searched for SRs of PPMs for COVID-19 until December 31, 2022. The risk of bias in systematic reviews tool was used to assess the risk of bias. The protocol for this overview was uploaded in the Open Science Framework (https://osf.io/7y94c).

RESULTS

Ten SRs were retrieved; none of them synthesized the results in a meta-analysis. For most of the studies, there was absence of a predefined protocol and missing information on study selection, data collection process, and reporting of primary studies and models included, while only one SR had its data publicly available. In addition, for the majority of the SRs, the overall risk of bias was judged as being high. The overall corrected covered area was 6.3% showing a small amount of overlapping among the SRs.

CONCLUSION

The reporting completeness and transparency of SRs of PPMs for COVID-19 was poor. Guidance is urgently required, with increased awareness and education of minimum reporting standards and quality criteria. Specific focus is needed in predefined protocol, information on study selection and data collection process, and in the reporting of findings to improve the quality of SRs of PPMs for COVID-19.

Artificial intelligence in the risk prediction models of cardiovascular disease and development of an independent validation screening tool: a systematic review

BACKGROUND

A comprehensive overview of artificial intelligence (AI) for cardiovascular disease (CVD) prediction and a screening tool of AI models (AI-Ms) for independent external validation are lacking. This systematic review aims to identify, describe, and appraise AI-Ms of CVD prediction in the general and special populations and develop a new independent validation score (IVS) for AI-Ms replicability evaluation.

METHODS

PubMed, Web of Science, Embase, and IEEE library were searched up to July 2021. Data extraction and analysis were performed for the populations, distribution, predictors, algorithms, etc. The risk of bias was evaluated with the prediction risk of bias assessment tool (PROBAST). Subsequently, we designed IVS for model replicability evaluation with five steps in five items, including transparency of algorithms, performance of models, feasibility of reproduction, risk of reproduction, and clinical implication, respectively. The review is registered in PROSPERO (No. CRD42021271789).

RESULTS

In 20,887 screened references, 79 articles (82.5% in 2017-2021) were included, which contained 114 datasets (67 in Europe and North America, but 0 in Africa). We identified 486 AI-Ms, of which the majority were in development (n = 380), but none of them had undergone independent external validation. A total of 66 idiographic algorithms were found; however, 36.4% were used only once and only 39.4% over three times. A large number of different predictors (range 5-52,000, median 21) and large-span sample size (range 80-3,660,000, median 4466) were observed. All models were at high risk of bias according to PROBAST, primarily due to the incorrect use of statistical methods. IVS analysis confirmed only 10 models as "recommended"; however, 281 and 187 were "not recommended" and "warning," respectively.

CONCLUSION

AI has led the digital revolution in the field of CVD prediction, but is still in the early stage of development as the defects of research design, report, and evaluation systems. The IVS we developed may contribute to independent external validation and the development of this field.

The Reporting Quality of Machine Learning Studies on Pediatric Diabetes Mellitus: Systematic Review

BACKGROUND

Diabetes mellitus (DM) is a major health concern among children with the widespread adoption of advanced technologies. However, concerns are growing about the transparency, replicability, biasedness, and overall validity of artificial intelligence studies in medicine.

OBJECTIVE

We aimed to systematically review the reporting quality of machine learning (ML) studies of pediatric DM using the Minimum Information About Clinical Artificial Intelligence Modelling (MI-CLAIM) checklist, a general reporting guideline for medical artificial intelligence studies.

METHODS

We searched the PubMed and Web of Science databases from 2016 to 2020. Studies were included if the use of ML was reported in children with DM aged 2 to 18 years, including studies on complications, screening studies, and in silico samples. In studies following the ML workflow of training, validation, and testing of results, reporting quality was assessed via MI-CLAIM by consensus judgments of independent reviewer pairs. Positive answers to the 17 binary items regarding sufficient reporting were qualitatively summarized and counted as a proxy measure of reporting quality. The synthesis of results included testing the association of reporting quality with publication and data type, participants (human or in silico), research goals, level of code sharing, and the scientific field of publication (medical or engineering), as well as with expert judgments of clinical impact and reproducibility.

RESULTS

After screening 1043 records, 28 studies were included. The sample size of the training cohort ranged from 5 to 561. Six studies featured only in silico patients. The reporting quality was low, with great variation among the 21 studies assessed using MI-CLAIM. The number of items with sufficient reporting ranged from 4 to 12 (mean 7.43, SD 2.62). The items on research questions and data characterization were reported adequately most often, whereas items on patient characteristics and model examination were reported adequately least often. The representativeness of the training and test cohorts to real-world settings and the adequacy of model performance evaluation were the most difficult to judge. Reporting quality improved over time (r=0.50; P=.02); it was higher than average in prognostic biomarker and risk factor studies (P=.04) and lower in noninvasive hypoglycemia detection studies (P=.006), higher in studies published in medical versus engineering journals (P=.004), and higher in studies sharing any code of the ML pipeline versus not sharing (P=.003). The association between expert judgments and MI-CLAIM ratings was not significant.

CONCLUSIONS

The reporting quality of ML studies in the pediatric population with DM was generally low. Important details for clinicians, such as patient characteristics; comparison with the state-of-the-art solution; and model examination for valid, unbiased, and robust results, were often the weak points of reporting. To assess their clinical utility, the reporting standards of ML studies must evolve, and algorithms for this challenging population must become more transparent and replicable.

Open science practices need substantial improvement in prognostic model studies in oncology using machine learning

OBJECTIVE

To describe the frequency of open science practices in a contemporary sample of studies developing prognostic models using machine learning methods in the field of oncology.

STUDY DESIGN AND SETTING

We conducted a systematic review, searching the MEDLINE database between December 1, 2022, and December 31, 2022, for studies developing a multivariable prognostic model using machine learning methods (as defined by the authors) in oncology. Two authors independently screened records and extracted open science practices.

RESULTS

We identified 46 publications describing the development of a multivariable prognostic model. The adoption of open science principles was poor. Only one study reported availability of a study protocol, and only one study was registered. Funding statements and conflicts of interest statements were common. Thirty-five studies (76%) provided data sharing statements, with 21 (46%) indicating data were available on request to the authors and seven declaring data sharing was not applicable. Two studies (4%) shared data. Only 12 studies (26%) provided code sharing statements, including 2 (4%) that indicated the code was available on request to the authors. Only 11 studies (24%) provided sufficient information to allow their model to be used in practice. The use of reporting guidelines was rare: eight studies (18%) mentioning using a reporting guideline, with 4 (10%) using the Transparent Reporting of a Multivariable Prediction Model for Individual Prognosis Or Diagnosis statement, 1 (2%) using Minimum Information About Clinical Artificial Intelligence Modeling and Consolidated Standards Of Reporting Trials-Artificial Intelligence, 1 (2%) using Strengthening The Reporting Of Observational Studies In Epidemiology, 1 (2%) using Standards for Reporting Diagnostic Accuracy Studies, and 1 (2%) using Transparent Reporting of Evaluations with Nonrandomized Designs.

CONCLUSION

The adoption of open science principles in oncology studies developing prognostic models using machine learning methods is poor. Guidance and an increased awareness of benefits and best practices of open science are needed for prediction research in oncology.

Machine learning prediction models for diabetic kidney disease: systematic review and meta-analysis

BACKGROUND

Machine learning is increasingly recognized as a viable approach for identifying risk factors associated with diabetic kidney disease (DKD). However, the current state of real-world research lacks a comprehensive systematic analysis of the predictive performance of machine learning (ML) models for DKD.

OBJECTIVES

The objectives of this study were to systematically summarize the predictive capabilities of various ML methods in forecasting the onset and the advancement of DKD, and to provide a basic outline for ML methods in DKD.

METHODS

We have searched mainstream databases, including PubMed, Web of Science, Embase, and MEDLINE databases to obtain the eligible studies. Subsequently, we categorized various ML techniques and analyzed the differences in their performance in predicting DKD.

RESULTS

Logistic regression (LR) was the prevailing ML method, yielding an overall pooled area under the receiver operating characteristic curve (AUROC) of 0.83. On the other hand, the non-LR models also performed well with an overall pooled AUROC of 0.80. Our t-tests showed no statistically significant difference in predicting ability between LR and non-LR models (t = 1.6767, p > 0.05).

CONCLUSION

All ML predicting models yielded relatively satisfied DKD predicting ability with their AUROCs greater than 0.7. However, we found no evidence that non-LR models outperformed the LR model. LR exhibits high performance or accuracy in practice, while it is known for algorithmic simplicity and computational efficiency compared to others. Thus, LR may be considered a cost-effective ML model in practice.

Prediction models using artificial intelligence and longitudinal data from electronic health records: a systematic methodological review

OBJECTIVE

To describe and appraise the use of artificial intelligence (AI) techniques that can cope with longitudinal data from electronic health records (EHRs) to predict health-related outcomes.

METHODS

This review included studies in any language that: EHR was at least one of the data sources, collected longitudinal data, used an AI technique capable of handling longitudinal data, and predicted any health-related outcomes. We searched MEDLINE, Scopus, Web of Science, and IEEE Xplorer from inception to January 3, 2022. Information on the dataset, prediction task, data preprocessing, feature selection, method, validation, performance, and implementation was extracted and summarized using descriptive statistics. Risk of bias and completeness of reporting were assessed using a short form of PROBAST and TRIPOD, respectively.

RESULTS

Eighty-one studies were included. Follow-up time and number of registers per patient varied greatly, and most predicted disease development or next event based on diagnoses and drug treatments. Architectures generally were based on Recurrent Neural Networks-like layers, though in recent years combining different layers or transformers has become more popular. About half of the included studies performed hyperparameter tuning and used attention mechanisms. Most performed a single train-test partition and could not correctly assess the variability of the model's performance. Reporting quality was poor, and a third of the studies were at high risk of bias.

CONCLUSIONS

AI models are increasingly using longitudinal data. However, the heterogeneity in reporting methodology and results, and the lack of public EHR datasets and code sharing, complicate the possibility of replication.

REGISTRATION

PROSPERO database (CRD42022331388).

Artificial intelligence education: An evidence-based medicine approach for consumers, translators, and developers

Current and future healthcare professionals are generally not trained to cope with the proliferation of artificial intelligence (AI) technology in healthcare. To design a curriculum that caters to variable baseline knowledge and skills, clinicians may be conceptualized as "consumers", "translators", or "developers". The changes required of medical education because of AI innovation are linked to those brought about by evidence-based medicine (EBM). We outline a core curriculum for AI education of future consumers, translators, and developers, emphasizing the links between AI and EBM, with suggestions for how teaching may be integrated into existing curricula. We consider the key barriers to implementation of AI in the medical curriculum: time, resources, variable interest, and knowledge retention. By improving AI literacy rates and fostering a translator- and developer-enriched workforce, innovation may be accelerated for the benefit of patients and practitioners.

Machine learning models in clinical practice for the prediction of postoperative complications after major abdominal surgery

Complications after surgery have a major impact on short- and long-term outcomes, and decades of technological advancement have not yet led to the eradication of their risk. The accurate prediction of complications, recently enhanced by the development of machine learning algorithms, has the potential to completely reshape surgical patient management. In this paper, we reflect on multiple issues facing the implementation of machine learning, from the development to the actual implementation of machine learning models in daily clinical practice, providing suggestions on the use of machine learning models for predicting postoperative complications after major abdominal surgery.

An Integrated Multi-Omics and Artificial Intelligence Framework for Advance Plant Phenotyping in Horticulture

This review discusses the transformative potential of integrating multi-omics data and artificial intelligence (AI) in advancing horticultural research, specifically plant phenotyping. The traditional methods of plant phenotyping, while valuable, are limited in their ability to capture the complexity of plant biology. The advent of (meta-)genomics, (meta-)transcriptomics, proteomics, and metabolomics has provided an opportunity for a more comprehensive analysis. AI and machine learning (ML) techniques can effectively handle the complexity and volume of multi-omics data, providing meaningful interpretations and predictions. Reflecting the multidisciplinary nature of this area of research, in this review, readers will find a collection of state-of-the-art solutions that are key to the integration of multi-omics data and AI for phenotyping experiments in horticulture, including experimental design considerations with several technical and non-technical challenges, which are discussed along with potential solutions. The future prospects of this integration include precision horticulture, predictive breeding, improved disease and stress response management, sustainable crop management, and exploration of plant biodiversity. The integration of multi-omics and AI holds immense promise for revolutionizing horticultural research and applications, heralding a new era in plant phenotyping.

A systematic review of clinical health conditions predicted by machine learning diagnostic and prognostic models trained or validated using real-world primary health care data

With the advances in technology and data science, machine learning (ML) is being rapidly adopted by the health care sector. However, there is a lack of literature addressing the health conditions targeted by the ML prediction models within primary health care (PHC) to date. To fill this gap in knowledge, we conducted a systematic review following the PRISMA guidelines to identify health conditions targeted by ML in PHC. We searched the Cochrane Library, Web of Science, PubMed, Elsevier, BioRxiv, Association of Computing Machinery (ACM), and IEEE Xplore databases for studies published from January 1990 to January 2022. We included primary studies addressing ML diagnostic or prognostic predictive models that were supplied completely or partially by real-world PHC data. Studies selection, data extraction, and risk of bias assessment using the prediction model study risk of bias assessment tool were performed by two investigators. Health conditions were categorized according to international classification of diseases (ICD-10). Extracted data were analyzed quantitatively. We identified 106 studies investigating 42 health conditions. These studies included 207 ML prediction models supplied by the PHC data of 24.2 million participants from 19 countries. We found that 92.4% of the studies were retrospective and 77.3% of the studies reported diagnostic predictive ML models. A majority (76.4%) of all the studies were for models' development without conducting external validation. Risk of bias assessment revealed that 90.8% of the studies were of high or unclear risk of bias. The most frequently reported health conditions were diabetes mellitus (19.8%) and Alzheimer's disease (11.3%). Our study provides a summary on the presently available ML prediction models within PHC. We draw the attention of digital health policy makers, ML models developer, and health care professionals for more future interdisciplinary research collaboration in this regard.

Consolidated Reporting Guidelines for Prognostic and Diagnostic Machine Learning Modeling Studies: Development and Validation

BACKGROUND

The reporting of machine learning (ML) prognostic and diagnostic modeling studies is often inadequate, making it difficult to understand and replicate such studies. To address this issue, multiple consensus and expert reporting guidelines for ML studies have been published. However, these guidelines cover different parts of the analytics lifecycle, and individually, none of them provide a complete set of reporting requirements.

OBJECTIVE

We aimed to consolidate the ML reporting guidelines and checklists in the literature to provide reporting items for prognostic and diagnostic ML in in-silico and shadow mode studies.

METHODS

We conducted a literature search that identified 192 unique peer-reviewed English articles that provide guidance and checklists for reporting ML studies. The articles were screened by their title and abstract against a set of 9 inclusion and exclusion criteria. Articles that were filtered through had their quality evaluated by 2 raters using a 9-point checklist constructed from guideline development good practices. The average κ was 0.71 across all quality criteria. The resulting 17 high-quality source papers were defined as having a quality score equal to or higher than the median. The reporting items in these 17 articles were consolidated and screened against a set of 6 inclusion and exclusion criteria. The resulting reporting items were sent to an external group of 11 ML experts for review and updated accordingly. The updated checklist was used to assess the reporting in 6 recent modeling papers in JMIR AI. Feedback from the external review and initial validation efforts was used to improve the reporting items.

RESULTS

In total, 37 reporting items were identified and grouped into 5 categories based on the stage of the ML project: defining the study details, defining and collecting the data, modeling methodology, model evaluation, and explainability. None of the 17 source articles covered all the reporting items. The study details and data description reporting items were the most common in the source literature, with explainability and methodology guidance (ie, data preparation and model training) having the least coverage. For instance, a median of 75% of the data description reporting items appeared in each of the 17 high-quality source guidelines, but only a median of 33% of the data explainability reporting items appeared. The highest-quality source articles tended to have more items on reporting study details. Other categories of reporting items were not related to the source article quality. We converted the reporting items into a checklist to support more complete reporting.

CONCLUSIONS

Our findings supported the need for a set of consolidated reporting items, given that existing high-quality guidelines and checklists do not individually provide complete coverage. The consolidated set of reporting items is expected to improve the quality and reproducibility of ML modeling studies.

Dementia prediction in the general population using clinically accessible variables: a proof-of-concept study using machine learning. The AGES-Reykjavik study

BACKGROUND

Early identification of dementia is crucial for prompt intervention for high-risk individuals in the general population. External validation studies on prognostic models for dementia have highlighted the need for updated models. The use of machine learning in dementia prediction is in its infancy and may improve predictive performance. The current study aimed to explore the difference in performance of machine learning algorithms compared to traditional statistical techniques, such as logistic and Cox regression, for prediction of all-cause dementia. Our secondary aim was to assess the feasibility of only using clinically accessible predictors rather than MRI predictors.

METHODS

Data are from 4,793 participants in the population-based AGES-Reykjavik Study without dementia or mild cognitive impairment at baseline (mean age: 76 years, % female: 59%). Cognitive, biometric, and MRI assessments (total: 59 variables) were collected at baseline, with follow-up of incident dementia diagnoses for a maximum of 12 years. Machine learning algorithms included elastic net regression, random forest, support vector machine, and elastic net Cox regression. Traditional statistical methods for comparison were logistic and Cox regression. Model 1 was fit using all variables and model 2 was after feature selection using the Boruta package. A third model explored performance when leaving out neuroimaging markers (clinically accessible model). Ten-fold cross-validation, repeated ten times, was implemented during training. Upsampling was used to account for imbalanced data. Tuning parameters were optimized for recalibration automatically using the caret package in R.

RESULTS

19% of participants developed all-cause dementia. Machine learning algorithms were comparable in performance to logistic regression in all three models. However, a slight added performance was observed in the elastic net Cox regression in the third model (c = 0.78, 95% CI: 0.78-0.78) compared to the traditional Cox regression (c = 0.75, 95% CI: 0.74-0.77).

CONCLUSIONS

Supervised machine learning only showed added benefit when using survival techniques. Removing MRI markers did not significantly worsen our model's performance. Further, we presented the use of a nomogram using machine learning methods, showing transportability for the use of machine learning models in clinical practice. External validation is needed to assess the use of this model in other populations. Identifying high-risk individuals will amplify prevention efforts and selection for clinical trials.

Sample size requirements are not being considered in studies developing prediction models for binary outcomes: a systematic review

BACKGROUND

Having an appropriate sample size is important when developing a clinical prediction model. We aimed to review how sample size is considered in studies developing a prediction model for a binary outcome.

METHODS

We searched PubMed for studies published between 01/07/2020 and 30/07/2020 and reviewed the sample size calculations used to develop the prediction models. Using the available information, we calculated the minimum sample size that would be needed to estimate overall risk and minimise overfitting in each study and summarised the difference between the calculated and used sample size.

RESULTS

A total of 119 studies were included, of which nine studies provided sample size justification (8%). The recommended minimum sample size could be calculated for 94 studies: 73% (95% CI: 63-82%) used sample sizes lower than required to estimate overall risk and minimise overfitting including 26% studies that used sample sizes lower than required to estimate overall risk only. A similar number of studies did not meet the ≥ 10EPV criteria (75%, 95% CI: 66-84%). The median deficit of the number of events used to develop a model was 75 [IQR: 234 lower to 7 higher]) which reduced to 63 if the total available data (before any data splitting) was used [IQR:225 lower to 7 higher]. Studies that met the minimum required sample size had a median c-statistic of 0.84 (IQR:0.80 to 0.9) and studies where the minimum sample size was not met had a median c-statistic of 0.83 (IQR: 0.75 to 0.9). Studies that met the ≥ 10 EPP criteria had a median c-statistic of 0.80 (IQR: 0.73 to 0.84).

CONCLUSIONS

Prediction models are often developed with no sample size calculation, as a consequence many are too small to precisely estimate the overall risk. We encourage researchers to justify, perform and report sample size calculations when developing a prediction model.

Predicting the recurrence risk of renal cell carcinoma after nephrectomy: potential role of CT-radiomics for adjuvant treatment decisions

OBJECTIVES

Previous trial results suggest that only a small number of patients with non-metastatic renal cell carcinoma (RCC) benefit from adjuvant therapy. We assessed whether the addition of CT-based radiomics to established clinico-pathological biomarkers improves recurrence risk prediction for adjuvant treatment decisions.

METHODS

This retrospective study included 453 patients with non-metastatic RCC undergoing nephrectomy. Cox models were trained to predict disease-free survival (DFS) using post-operative biomarkers (age, stage, tumor size and grade) with and without radiomics selected on pre-operative CT. Models were assessed using C-statistic, calibration, and decision curve analyses (repeated tenfold cross-validation).

RESULTS

At multivariable analysis, one of four selected radiomic features (wavelet-HHL_glcm_ClusterShade) was prognostic for DFS with an adjusted hazard ratio (HR) of 0.44 (p = 0.02), along with American Joint Committee on Cancer (AJCC) stage group (III versus I, HR 2.90; p = 0.002), grade 4 (versus grade 1, HR 8.90; p = 0.001), age (per 10 years HR 1.29; p = 0.03), and tumor size (per cm HR 1.13; p = 0.003). The discriminatory ability of the combined clinical-radiomic model (C = 0.80) was superior to that of the clinical model (C = 0.78; p < 0.001). Decision curve analysis revealed a net benefit of the combined model when used for adjuvant treatment decisions. At an exemplary threshold probability of ≥ 25% for disease recurrence within 5 years, using the combined versus the clinical model was equivalent to treating 9 additional patients (per 1000 assessed) who would recur without treatment (i.e., true-positive predictions) with no increase in false-positive predictions.

CONCLUSION

Adding CT-based radiomic features to established prognostic biomarkers improved post-operative recurrence risk assessment in our internal validation study and may help guide decisions regarding adjuvant therapy.

KEY POINTS

In patients with non-metastatic renal cell carcinoma undergoing nephrectomy, CT-based radiomics combined with established clinical and pathological biomarkers improved recurrence risk assessment. Compared to a clinical base model, the combined risk model enabled superior clinical utility if used to guide decisions on adjuvant treatment.

Road map for clinicians to develop and evaluate AI predictive models to inform clinical decision-making

BACKGROUND

Predictive models have been used in clinical care for decades. They can determine the risk of a patient developing a particular condition or complication and inform the shared decision-making process. Developing artificial intelligence (AI) predictive models for use in clinical practice is challenging; even if they have good predictive performance, this does not guarantee that they will be used or enhance decision-making. We describe nine stages of developing and evaluating a predictive AI model, recognising the challenges that clinicians might face at each stage and providing practical tips to help manage them.

FINDINGS

The nine stages included clarifying the clinical question or outcome(s) of interest (output), identifying appropriate predictors (features selection), choosing relevant datasets, developing the AI predictive model, validating and testing the developed model, presenting and interpreting the model prediction(s), licensing and maintaining the AI predictive model and evaluating the impact of the AI predictive model. The introduction of an AI prediction model into clinical practice usually consists of multiple interacting components, including the accuracy of the model predictions, physician and patient understanding and use of these probabilities, expected effectiveness of subsequent actions or interventions and adherence to these. Much of the difference in whether benefits are realised relates to whether the predictions are given to clinicians in a timely way that enables them to take an appropriate action.

CONCLUSION

The downstream effects on processes and outcomes of AI prediction models vary widely, and it is essential to evaluate the use in clinical practice using an appropriate study design.

Artificial intelligence in lung cancer diagnostic imaging: a review of the reporting and conduct of research published 2018-2019

Objective

This study aimed to describe the methodologies used to develop and evaluate models that use artificial intelligence (AI) to analyse lung images in order to detect, segment (outline borders of), or classify pulmonary nodules as benign or malignant.

Methods

In October 2019, we systematically searched the literature for original studies published between 2018 and 2019 that described prediction models using AI to evaluate human pulmonary nodules on diagnostic chest images. Two evaluators independently extracted information from studies, such as study aims, sample size, AI type, patient characteristics, and performance. We summarised data descriptively.

Results

The review included 153 studies: 136 (89%) development-only studies, 12 (8%) development and validation, and 5 (3%) validation-only. CT scans were the most common type of image type used (83%), often acquired from public databases (58%). Eight studies (5%) compared model outputs with biopsy results. 41 studies (26.8%) reported patient characteristics. The models were based on different units of analysis, such as patients, images, nodules, or image slices or patches.

Conclusion

The methods used to develop and evaluate prediction models using AI to detect, segment, or classify pulmonary nodules in medical imaging vary, are poorly reported, and therefore difficult to evaluate. Transparent and complete reporting of methods, results and code would fill the gaps in information we observed in the study publications.

Advances in knowledge

We reviewed the methodology of AI models detecting nodules on lung images and found that the models were poorly reported and had no description of patient characteristics, with just a few comparing models' outputs with biopsies results. When lung biopsy is not available, lung-RADS could help standardise the comparisons between the human radiologist and the machine. The field of radiology should not give up principles from the diagnostic accuracy studies, such as the choice for the correct ground truth, just because AI is used. Clear and complete reporting of the reference standard used would help radiologists trust in the performance that AI models claim to have. This review presents clear recommendations about the essential methodological aspects of diagnostic models that should be incorporated in studies using AI to help detect or segmentate lung nodules. The manuscript also reinforces the need for more complete and transparent reporting, which can be helped using the recommended reporting guidelines.

Machine learning for predicting opioid use disorder from healthcare data: A systematic review

INTRODUCTION

The US opioid epidemic has been one of the leading causes of injury-related deaths according to the CDC Injury Center. The increasing availability of data and tools for machine learning (ML) resulted in more researchers creating datasets and models to help analyze and mitigate the crisis. This review investigates peer-reviewed journal papers that applied ML models to predict opioid use disorder (OUD). The review is split into two parts. The first part summarizes the current research in OUD prediction with ML. The second part evaluates how ML techniques and processes were used to achieve these results and suggests improvements to refine further attempts to use ML for OUD prediction.

METHODS

The review includes peer-reviewed journal papers published on or after 2012 that use healthcare data to predict OUD. We searched Google Scholar, Semantic Scholar, PubMed, IEEE Xplore, and Science.gov in September of 2022. Data extracted includes the study's goal, dataset used, cohort selected, types of ML models created, model evaluation metrics, and the details of the ML tools and techniques used to create the models.

RESULTS

The review analyzed 16 papers. Three papers created their dataset, five used a publicly available dataset, and the remaining eight used a private dataset. Cohort size ranged from the low hundreds to over half a million. Six papers used one type of ML model, and the remaining ten used up to five different ML models. The reported ROC AUC was higher than 0.8 for all but one of the papers. Five papers used only non-interpretable models, and the other 11 used interpretable models exclusively or in combination with non-interpretable ones. The interpretable models were the highest or second-highest ROC AUC values. Most papers did not sufficiently describe the ML techniques and tools used to produce their results. Only three papers published their source code.

CONCLUSIONS

We found that while there are indications that ML methods applied to OUD prediction may be valuable, the lack of details and transparency in creating the ML models limits their usefulness. We end the review with recommendations to improve studies on this critical healthcare subject.

Current state and completeness of reporting clinical prediction models using machine learning in systemic lupus erythematosus: A systematic review

OBJECTIVE

We carried out a systematic review (SR) of adherence in diagnostic and prognostic applications of ML in SLE using the Transparent Reporting of a multivariable prediction model for Individual Prognosis Or Diagnosis (TRIPOD) Statement.

METHODS

A SR employing five databases was conducted from its inception until December 2021. We identified articles that evaluated the utilization of ML for prognostic and/or diagnostic purposes. This SR was reported based on the PRISMA guidelines. The TRIPOD statement assessed adherence to reporting standards. Assessment for risk of bias was done using PROBAST tool.

RESULTS

We included 45 studies: 29 (64.4%) diagnostic and 16 (35.5%) prognostic prediction- model studies. Overall, articles adhered by between 17% and 67% (median 43%, IQR 37-49%) to TRIPOD items. Only few articles reported the model's predictive performance (2.3%, 95% CI 0.06-12.0), testing of interaction terms (2.3%, 95% CI 0.06-12.0), flow of participants (50%, 95% CI; 34.6-65.4), blinding of predictors (2.3%, 95% CI 0.06-12.0), handling of missing data (36.4%, 95% CI 22.4-52.2), and appropriate title (20.5%, 95% CI 9.8-35.3). Some items were almost completely reported: the source of data (88.6%, 95% CI 75.4-96.2), eligibility criteria (86.4%, 95% CI 76.2-96.5), and interpretation of findings (88.6%, 95% CI 75.4-96.2). In addition, most of model studies had high risk of bias.

CONCLUSIONS

The reporting adherence of ML-based model developed for SLE, is currently inadequate. Several items deemed crucial for transparent reporting were not fully reported in studies on ML-based prediction models.

REVIEW REGISTRATION

PROSPERO ID# CRD42021284881. (Amended to limit the scope).

Appraising the Quality of Development and Reporting in Surgical Prediction Models

This cross-sectional study uses the Transparent Reporting of a Multivariable Prediction Model for Individual Prognosis or Diagnosis reporting guideline to assess 120 published studies about surgical prediction models.

Systematic review identifies the design and methodological conduct of studies on machine learning-based prediction models

BACKGROUND AND OBJECTIVES

We sought to summarize the study design, modelling strategies, and performance measures reported in studies on clinical prediction models developed using machine learning techniques.

METHODS

We search PubMed for articles published between 01/01/2018 and 31/12/2019, describing the development or the development with external validation of a multivariable prediction model using any supervised machine learning technique. No restrictions were made based on study design, data source, or predicted patient-related health outcomes.

RESULTS

We included 152 studies, 58 (38.2% [95% CI 30.8-46.1]) were diagnostic and 94 (61.8% [95% CI 53.9-69.2]) prognostic studies. Most studies reported only the development of prediction models (n = 133, 87.5% [95% CI 81.3-91.8]), focused on binary outcomes (n = 131, 86.2% [95% CI 79.8-90.8), and did not report a sample size calculation (n = 125, 82.2% [95% CI 75.4-87.5]). The most common algorithms used were support vector machine (n = 86/522, 16.5% [95% CI 13.5-19.9]) and random forest (n = 73/522, 14% [95% CI 11.3-17.2]). Values for area under the Receiver Operating Characteristic curve ranged from 0.45 to 1.00. Calibration metrics were often missed (n = 494/522, 94.6% [95% CI 92.4-96.3]).

CONCLUSION

Our review revealed that focus is required on handling of missing values, methods for internal validation, and reporting of calibration to improve the methodological conduct of studies on machine learning-based prediction models.

SYSTEMATIC REVIEW REGISTRATION

PROSPERO, CRD42019161764.

A Machine Learning Approach for Early Diagnosis of Cognitive Impairment Using Population-Based Data

BACKGROUND

The major mechanisms of dementia and cognitive impairment are vascular and neurodegenerative processes. Early diagnosis of cognitive impairment can facilitate timely interventions to mitigate progression.

OBJECTIVE

This study aims to develop a reliable machine learning (ML) model using socio-demographics, vascular risk factors, and structural neuroimaging markers for early diagnosis of cognitive impairment in a multi-ethnic Asian population.

METHODS

The study consisted of 911 participants from the Epidemiology of Dementia in Singapore study (aged 60- 88 years, 49.6% male). Three ML classifiers, logistic regression, support vector machine, and gradient boosting machine, were developed. Prediction results of independent classifiers were combined in a final ensemble model. Model performances were evaluated on test data using F1 score and area under the receiver operating curve (AUC) methods. Post modelling, SHapely Additive exPlanation (SHAP) was applied on the prediction results to identify the predictors that contribute most to the cognitive impairment prediction.

FINDINGS

The final ensemble model achieved a F1 score and AUC of 0.87 and 0.80 respectively. Accuracy (0.83), sensitivity (0.86), specificity (0.74) and predictive values (positive 0.88 negative 0.72) of the ensemble model were higher compared to the independent classifiers. Age, ethnicity, highest education attainment and neuroimaging markers were identified as important predictors of cognitive impairment.

CONCLUSION

This study demonstrates the feasibility of using ML tools to integrate multiple domains of data for reliable diagnosis of early cognitive impairment. The ML model uses easy-to-obtain variables and is scalable for screening individuals with a high risk of developing dementia in a population-based setting.

Great debates in cardiac computed tomography: OPINION: "Artificial intelligence and the future of cardiovascular CT - Managing expectation and challenging hype"

This manuscript has been written as a follow-up to the "AI/ML great debate" featured at the 2021 Society of Cardiovascular Computed Tomography (SCCT) Annual Scientific Meeting. In debate style, we highlighti the need for expectation management of AI/ML, debunking the hype around current AI techniques, and countering the argument that in its current day format AI/ML is the "silver bullet" for the interpretation of daily clinical CCTA practice.

Interpretable prognostic modeling of endometrial cancer

Endometrial carcinoma (EC) is one of the most common gynecological cancers in the world. In this work we apply Cox proportional hazards (CPH) and optimal survival tree (OST) algorithms to the retrospective prognostic modeling of disease-specific survival in 842 EC patients. We demonstrate that linear CPH models are preferred for the EC risk assessment based on clinical features alone, while interpretable, non-linear OST models are favored when patient profiles can be supplemented with additional biomarker data. We show how visually interpretable tree models can help generate and explore novel research hypotheses by studying the OST decision path structure, in which L1 cell adhesion molecule expression and estrogen receptor status are correctly indicated as important risk factors in the p53 abnormal EC subgroup. To aid further clinical adoption of advanced machine learning techniques, we stress the importance of quantifying model discrimination and calibration performance in the development of explainable clinical prediction models.

Statistical methods for validation of predictive models

Predictive models are widely used in clinical practice. Despite of the increasing number of published AI systems, recent systematic reviews have identified lack of statistical rigor in the development and validation of predictive models. This work reviewed the current literature for predictive performance measures and resampling methods. Furthermore, common pitfalls were discussed.

Reporting and risk of bias of prediction models based on machine learning methods in preterm birth: A systematic review

INTRODUCTION

There was limited evidence on the quality of reporting and methodological quality of prediction models using machine learning methods in preterm birth. This systematic review aimed to assess the reporting quality and risk of bias of a machine learning-based prediction model in preterm birth.

MATERIAL AND METHODS

We conducted a systematic review, searching the PubMed, Embase, the Cochrane Library, China National Knowledge Infrastructure, China Biology Medicine disk, VIP Database, and WanFang Data from inception to September 27, 2021. Studies that developed (validated) a prediction model using machine learning methods in preterm birth were included. We used the Transparent Reporting of a multivariable prediction model for Individual Prognosis Or Diagnosis (TRIPOD) statement and Prediction model Risk of Bias Assessment Tool (PROBAST) to evaluate the reporting quality and the risk of bias of included studies, respectively. Findings were summarized using descriptive statistics and visual plots. The protocol was registered in PROSPERO (no. CRD 42022301623).

RESULTS

Twenty-nine studies met the inclusion criteria, with 24 development-only studies and 5 development-with-validation studies. Overall, TRIPOD adherence per study ranged from 17% to 79%, with a median adherence of 49%. The reporting of title, abstract, blinding of predictors, sample size justification, explanation of model, and model performance were mostly poor, with TRIPOD adherence ranging from 4% to 17%. For all included studies, 79% had a high overall risk of bias, and 21% had an unclear overall risk of bias. The analysis domain was most commonly rated as high risk of bias in included studies, mainly as a result of small effective sample size, selection of predictors based on univariable analysis, and lack of calibration evaluation.

CONCLUSIONS

Reporting and methodological quality of machine learning-based prediction models in preterm birth were poor. It is urgent to improve the design, conduct, and reporting of such studies to boost the application of machine learning-based prediction models in preterm birth in clinical practice.

Joint models for dynamic prediction in localised prostate cancer: a literature review

BACKGROUND

Prostate cancer is a very prevalent disease in men. Patients are monitored regularly during and after treatment with repeated assessment of prostate-specific antigen (PSA) levels. Prognosis of localised prostate cancer is generally good after treatment, and the risk of having a recurrence is usually estimated based on factors measured at diagnosis. Incorporating PSA measurements over time in a dynamic prediction joint model enables updates of patients' risk as new information becomes available. We review joint model strategies that have been applied to model time-dependent PSA trajectories to predict time-to-event outcomes in localised prostate cancer.

METHODS

We identify articles that developed joint models for prediction of localised prostate cancer recurrence over the last two decades. We report, compare, and summarise the methodological approaches and applications that use joint modelling accounting for two processes: the longitudinal model (PSA), and the time-to-event process (clinical failure). The methods explored differ in how they specify the association between these two processes.

RESULTS

Twelve relevant articles were identified. A range of methodological frameworks were found, and we describe in detail shared-parameter joint models (9 of 12, 75%) and joint latent class models (3 of 12, 25%). Within each framework, these articles presented model development, estimation of dynamic predictions and model validations.

CONCLUSIONS

Each framework has its unique principles with corresponding advantages and differing interpretations. Regardless of the framework used, dynamic prediction models enable real-time prediction of individual patient prognosis. They utilise all available longitudinal information, in addition to baseline prognostic risk factors, and are superior to traditional baseline-only prediction models.

A descriptive appraisal of quality of reporting in a cohort of machine learning studies in anesthesiology

BACKGROUND

The field of machine learning is being employed more and more in medicine. However, studies have shown that the quality of published studies frequently lacks completeness and adherence to published reporting guidelines. This assessment has not been done in the subspecialty of anesthesiology.

METHODS

We appraised the quality of reporting of a convenience sample of 67 peer-reviewed publications sourced from the scoping review by Hashimoto et al. Each publication was appraised on the presence of reporting elements (reporting compliance) selected from 4 peer-reviewed guidelines for reporting on machine learning studies. Results are described in several cross sections, including by section of manuscript (e.g. abstract, introduction, etc.), year of publication, impact factor of journal, and impact of publication.

RESULTS

On average, reporting compliance was 64% ± 13%. There was marked heterogeneity of reporting based on section of manuscript. There was a mild trend towards increased quality of reporting with increasing impact factor of journal of publication and increasing average number of citations per year since publication, and no trend regarding recency of publication.

CONCLUSION

The quality of reporting of machine learning studies in anesthesiology is on par with other fields, but can benefit from improvement, especially in presenting methodology, results, and discussion points, including interpretation of models and pitfalls therein. Clinicians in today's learning health systems will benefit from skills in appraisal of evidence. Several reporting guidelines have been released, and updates to mainstream guidelines are under development, which we hope will usher in improvement in reporting quality.

Predicting major adverse cardiovascular events in acute coronary syndrome: A scoping review of machine learning approaches

BACKGROUND

Acute coronary syndrome is the topmost cause of death worldwide; therefore, it is necessary to predict major adverse cardiovascular events and cardiovascular deaths in patients with acute coronary syndrome to make correct and timely clinical decisions.

OBJECTIVE

The current review aimed to highlight algorithms and important predictor variables through examining those studies which used machine learning algorithms for predicting major adverse cardiovascular events in patients with acute coronary syndrome.

METHODS

In order to predict major adverse cardiovascular events in patients with acute coronary syndrome, the preferred reporting items for scoping reviews guidelines were used. PubMed, Embase, Web of Science, Scopus, Springer, and IEEE Xplore databases were searched for articles published between 2005 and 2021. The findings of the studies are presented in the form of a narrative synthesis of evidence.

RESULTS

According to the results, 14 (63.64%) studies did not perform external validation and only used registry data. The algorithms used in this study comprised, inter alia, Regression Logistic, Random Forest, Boosting Ensemble, Non-Boosting Ensemble, Decision Trees, and Naive Bayes. Multiple studies (N=20) achieved a high Area under the ROC Curve between 0.8 to 0.99 in predicting mortality and major adverse cardiovascular events. The predictor variables used in these studies were divided into demographic, clinical, and therapeutic features. However, no study reported the integration of machine learning model into clinical practice.

CONCLUSION

Machine learning algorithms rendered acceptable results to predict major adverse cardiovascular events and mortality outcomes in patients with acute coronary syndrome. However, these approaches have never been integrated into clinical practice. Further research is required to develop feasible and effective machine learning prediction models to measure their potentially important implications for optimizing the quality of care in patients with acute coronary syndrome.

Quality and transparency of reporting derivation and validation prognostic studies of recurrent stroke in patients with TIA and minor stroke: a systematic review

BACKGROUND

Clinical prediction models/scores help clinicians make optimal evidence-based decisions when caring for their patients. To critically appraise such prediction models for use in a clinical setting, essential information on the derivation and validation of the models needs to be transparently reported. In this systematic review, we assessed the quality of reporting of derivation and validation studies of prediction models for the prognosis of recurrent stroke in patients with transient ischemic attack or minor stroke.

METHODS

MEDLINE and EMBASE databases were searched up to February 04, 2020. Studies reporting development or validation of multivariable prognostic models predicting recurrent stroke within 90 days in patients with TIA or minor stroke were included. Included studies were appraised for reporting quality and conduct using a select list of items from the Transparent Reporting of a Multivariable Prediction Model for Individual Prognosis or Diagnosis (TRIPOD) Statement.

RESULTS

After screening 7026 articles, 60 eligible articles were retained, consisting of 100 derivation and validation studies of 27 unique prediction models. Four models were newly derived while 23 were developed by validating and updating existing models. Of the 60 articles, 15 (25%) reported an informative title. Among the 100 derivation and validation studies, few reported whether assessment of the outcome (24%) and predictors (12%) was blinded. Similarly, sample size justifications (49%), description of methods for handling missing data (16.1%), and model calibration (5%) were seldom reported. Among the 96 validation studies, 17 (17.7%) clearly reported on similarity (in terms of setting, eligibility criteria, predictors, and outcomes) between the validation and the derivation datasets. Items with the highest prevalence of adherence were the source of data (99%), eligibility criteria (93%), measures of discrimination (81%) and study setting (65%).

CONCLUSIONS

The majority of derivation and validation studies for the prognosis of recurrent stroke in TIA and minor stroke patients suffer from poor reporting quality. We recommend that all prediction model derivation and validation studies follow the TRIPOD statement to improve transparency and promote uptake of more reliable prediction models in practice.

TRIAL REGISTRATION

The protocol for this review was registered with PROSPERO (Registration number CRD42020201130 ).