-
Ultrasound in Obstetrics & Gynecology :... May 2024This systematic review and meta-analysis aimed to evaluate the performance of existing externally validated prediction models for pre-eclampsia (PE) (specifically,... (Meta-Analysis)
Meta-Analysis
OBJECTIVE
This systematic review and meta-analysis aimed to evaluate the performance of existing externally validated prediction models for pre-eclampsia (PE) (specifically, any-onset, early-onset, late-onset and preterm PE).
METHODS
A systematic search was conducted in five databases (MEDLINE, EMBASE, Emcare, CINAHL and Maternity & Infant Care Database) and using Google Scholar/reference search to identify studies based on the Population, Index prediction model, Comparator, Outcome, Timing and Setting (PICOTS) approach until 20 May 2023. We extracted data using the CHARMS checklist and appraised the risk of bias using the PROBAST tool. A meta-analysis of discrimination and calibration performance was conducted when appropriate.
RESULTS
Twenty-three studies reported 52 externally validated prediction models for PE (one preterm, 20 any-onset, 17 early-onset and 14 late-onset PE models). No model had the same set of predictors. Fifteen any-onset PE models were validated externally once, two were validated twice and three were validated three times, while the Fetal Medicine Foundation (FMF) competing-risks model for preterm PE prediction was validated widely in 16 different settings. The most common predictors were maternal characteristics (prepregnancy body mass index, prior PE, family history of PE, chronic medical conditions and ethnicity) and biomarkers (uterine artery pulsatility index and pregnancy-associated plasma protein-A). The FMF model for preterm PE (triple test plus maternal factors) had the best performance, with a pooled area under the receiver-operating-characteristics curve (AUC) of 0.90 (95% prediction interval (PI), 0.76-0.96), and was well calibrated. The other models generally had poor-to-good discrimination performance (median AUC, 0.66 (range, 0.53-0.77)) and were overfitted on external validation. Apart from the FMF model, only two models that were validated multiple times for any-onset PE prediction, which were based on maternal characteristics only, produced reasonable pooled AUCs of 0.71 (95% PI, 0.66-0.76) and 0.73 (95% PI, 0.55-0.86).
CONCLUSIONS
Existing externally validated prediction models for any-, early- and late-onset PE have limited discrimination and calibration performance, and include inconsistent input variables. The triple-test FMF model had outstanding discrimination performance in predicting preterm PE in numerous settings, but the inclusion of specialized biomarkers may limit feasibility and implementation outside of high-resource settings. © 2023 The Authors. Ultrasound in Obstetrics & Gynecology published by John Wiley & Sons Ltd on behalf of International Society of Ultrasound in Obstetrics and Gynecology.
Topics: Female; Humans; Pregnancy; Pre-Eclampsia; Predictive Value of Tests; Pulsatile Flow; Risk Assessment
PubMed: 37724649
DOI: 10.1002/uog.27490 -
Cancers Dec 2023This systematic review aims to identify, evaluate, and summarize the findings of the literature on existing computational models for radiofrequency and microwave thermal... (Review)
Review
PURPOSE
This systematic review aims to identify, evaluate, and summarize the findings of the literature on existing computational models for radiofrequency and microwave thermal liver ablation planning and compare their accuracy.
METHODS
A systematic literature search was performed in the MEDLINE and Web of Science databases. Characteristics of the computational model and validation method of the included articles were retrieved.
RESULTS
The literature search identified 780 articles, of which 35 were included. A total of 19 articles focused on simulating radiofrequency ablation (RFA) zones, and 16 focused on microwave ablation (MWA) zones. Out of the 16 articles simulating MWA, only 2 used in vivo experiments to validate their simulations. Out of the 19 articles simulating RFA, 10 articles used in vivo validation. Dice similarity coefficients describing the overlap between in vivo experiments and simulated RFA zones varied between 0.418 and 0.728, with mean surface deviations varying between 1.1 mm and 8.67 mm.
CONCLUSION
Computational models to simulate ablation zones of MWA and RFA show considerable heterogeneity in model type and validation methods. It is currently unknown which model is most accurate and best suitable for use in clinical practice.
PubMed: 38067386
DOI: 10.3390/cancers15235684 -
Critical Reviews in Oncology/hematology Nov 2023Various assessment instruments have been proposed to document and evaluate radiation dermatitis. In this systematic review, we identified nineteen instruments or scales... (Review)
Review
Various assessment instruments have been proposed to document and evaluate radiation dermatitis. In this systematic review, we identified nineteen instruments or scales for the evaluation of radiation dermatitis and performed a critical review of the signs and symptoms included in each of them. Of those scales, only two have been validated. There is a need to revise the currently used instruments so to improve their capability to measure all relevant aspects of radiation dermatitis and their severity. In addition, it would be important to add the patients' view of their conditions and how they affect their lives. Finally, in order to be useful in clinical and research settings, instruments for evaluation of radiation dermatitis should be submitted to the validation process that is currently prescribed in the field of outcome measures development.
PubMed: 37648000
DOI: 10.1016/j.critrevonc.2023.104116 -
BMC Public Health Aug 2023Pain is a common reason for seeking out healthcare professionals and support services. However, certain populations, such as people with deafness, may encounter...
BACKGROUND
Pain is a common reason for seeking out healthcare professionals and support services. However, certain populations, such as people with deafness, may encounter difficulties in effectively communicating their pain; on the other side, health care professionals may also encounter challenges to assess pain in this specific population.
AIMS
To describe (a) the state of the research in the field of pain assessment in individuals with deafness; (b) instruments validated; and (b) strategies facilitating the pain communication or assessment in this population.
METHODS
A systematic review in accordance with the Preferred Reporting Items for Systematic Reviews and Meta-Analysis guidelines were performed, searching Medline, CINAHL, Scopus, Embase and PsycInfo databases, from their initiation to July 2023. Primary and secondary studies, involving adults with deafness and investigating pain assessment and communication difficulties, facilitators, or barriers, were eligible. The included studies were assessed in their methodological quality with the Quality Assessment for Diverse Studies tool; data extraction and the narrative synthesis was provided by two researchers.
RESULTS
Five studies were included. Two were validation studies, while the remaining were a case report, a case study and a qualitative study. The interRAI Community Health Assessment and the Deafblind Supplement scale have been validated among people with deafness by reporting few psychometric properties; in contrast, instruments well established in the general population (e.g. Visual Analogue Scale) have been assessed in their usability and understandability among individuals with deafness, suggesting their limitations. Some strategies have been documented as facilitating pain communication and assessment: (a) ensuring inclusiveness (the presence of family members as mediators); (b) ensuring the preparedness of healthcare professionals (e.g. in sign language); and (c) making the environment friendly to this population (e.g. removing masks).
CONCLUSIONS
The research regarding pain in this population is in its infancy, resulting in limited evidence. In recommending more research capable of establishing the best pain assessment instrument, some strategies emerged for assessing pain in which the minimum standards of care required to offer to this vulnerable population should be considered.
Topics: Adult; Humans; Communication; Deafness; Narration; Pain; Pain Measurement
PubMed: 37608263
DOI: 10.1186/s12889-023-16535-5 -
American Journal of Obstetrics &... Oct 2023Valid and reliable maternity patient-reported experience measures are critical to understanding women's experiences of care. They can support clinical practice, health... (Review)
Review
OBJECTIVE
Valid and reliable maternity patient-reported experience measures are critical to understanding women's experiences of care. They can support clinical practice, health service and system performance measurement, and research. The aim of this review is to identify and critically appraise the risk of bias, woman-centricity (content validity), and psychometric properties of maternity patient-reported experience measures published in the scientific literature.
DATA SOURCES
MEDLINE, CINAHL Plus, PsycINFO, and Embase were systematically searched for relevant records between January 1, 2010 and July 10, 2021.
STUDY ELIGIBILITY CRITERIA
We searched for articles describing the instrument development of maternity patient-reported experience measures and measurement properties associated with instrument validity and reliability testing. Articles that described patient-reported experience measures developed outside of the maternity context and articles that did not contribute to the instruments' development, content validation, and/or psychometric evaluation were excluded.
METHODS
Included articles underwent risk of bias, content validity, and psychometric properties assessments in line with the COSMIN (COnsensus-based Standards for the selection of health Measurement INstruments) guidance. Patient-reported experience measure results were summarized according to language subgroups. An overall recommendation for use was determined for each patient-reported experience measure language subgroup.
RESULTS
A total of 54 studies reported on the development and psychometric evaluation of 25 maternity patient-reported experience measures, grouped into 45 language subgroups. The quality of evidence underpinning the instruments' development was generally poor. Only 2 (4.4%) patient-reported experience measures reported sufficient content validity, and only 1 (2.2%) received a level "A" recommendation, required for real-world use.
CONCLUSION
Maternity patient-reported experience measures demonstrated poor-quality evidence for their measurement properties and insufficient detail about content validity. Future maternity patient-reported experience measure development needs to prioritize women's involvement in deciding what is relevant, comprehensive, and comprehensible to measure. Improving the content validity of maternity patient-reported experience measures will improve overall validity and reliability and facilitate real-world practice improvements. Standardized patient-reported experience measure implementation also needs to be prioritized to support advancements in clinical practice for women.
PubMed: 37517609
DOI: 10.1016/j.ajogmf.2023.101102 -
Drug and Alcohol Review Nov 2023Consideration of an individual's quality of life (QoL) can benefit assessment and treatment of addictive disorders, however, uncertainty remains over operationalisation... (Review)
Review
ISSUES
Consideration of an individual's quality of life (QoL) can benefit assessment and treatment of addictive disorders, however, uncertainty remains over operationalisation of the construct as an outcome and the appropriateness of existing measures for these populations. This systematic review aimed to identify and evaluate QoL and health-related QoL outcome instruments used in addiction-related risk and harm research and map their conceptualised domains.
APPROACH
Three electronic databases and a specialised assessment library were searched on 1 February 2022 for QoL or health-related QoL outcome instruments used with addiction-related risk and harm populations. PRISMA reporting guidance was followed and included outcome instruments were appraised using mixed methods. Psychometric evidence supporting their use was summarised. The COSMIN risk of bias tool was used to assess validation studies.
KEY FINDINGS
A total of 298 articles (330 studies) used 53 outcome instruments and 41 unique domains of QoL. Eleven instruments' psychometric properties were evaluated. No instrument was assessed for any parameter in at least five studies for meta-analytic pooling. Cronbach's alpha (α) internal consistency was the most widely assessed parameter with the AQoLS, WHOQOL-BREF, ALQoL-9, Q-LES-Q-SF, SF-12, DUQoL, QLI and SF-36 displaying promising statistics (α > 0.70).
IMPLICATIONS AND CONCLUSION
Many instruments have been utilised. However, a significant proportion of studies applied a small number of instruments with minimal high-quality validation evidence supporting their use within addiction-related risk and harm. Promising instruments are recommended, however, the paucity of supporting evidence limits confidence in the reliability and validity of QoL measurement in these populations.
Topics: Humans; Behavior, Addictive; Psychometrics; Quality of Life; Reproducibility of Results
PubMed: 37439397
DOI: 10.1111/dar.13717 -
Virology Journal Aug 2023Our study aimed to compare the predictive performance of different hepatocellular carcinoma (HCC) prediction models in chronic hepatitis B patients receiving entecavir... (Meta-Analysis)
Meta-Analysis Review
BACKGROUND
Our study aimed to compare the predictive performance of different hepatocellular carcinoma (HCC) prediction models in chronic hepatitis B patients receiving entecavir or tenofovir, including discrimination, calibration, negative predictive value (NPV) in low-risk, and proportion of low-risk.
METHODS
We conducted a systematic literature research in PubMed, EMbase, the Cochrane Library, and Web of Science before January 13, 2022. The predictive performance was assessed by area under receiver operating characteristic curve (AUROC), calibration index, negative predictive value, and the proportion in low-risk. Subgroup and meta-regression analyses of discrimination and calibration were conducted. Sensitivity analysis was conducted to validate the stability of the results.
RESULTS
We identified ten prediction models in 23 studies. The pooled 3-, 5-, and 10-year AUROC varied from 0.72 to 0.84, 0.74 to 0.83, and 0.76 to 0.86, respectively. REAL-B, AASL-HCC, and HCC-RESCUE achieved the best discrimination. HCC-RESCUE, PAGE-B, and mPAGE-B overestimated HCC development, whereas mREACH-B, AASL-HCC, REAL-B, CAMD, CAGE-B, SAGE-B, and aMAP underestimated it. All models were able to identify people with a low risk of HCC accurately. HCC-RESCUE and aMAP recognized over half of the population as low-risk. Subgroup analysis and sensitivity analysis showed similar results.
CONCLUSION
Considering the predictive performance of all four aspects, we suggest that HCC-RESCUE was the best model to utilize in clinical practice, especially in primary care and low-income areas. To confirm our findings, further validation studies with the above four components were required.
Topics: Humans; Tenofovir; Carcinoma, Hepatocellular; Hepatitis B, Chronic; Liver Neoplasms; Antiviral Agents
PubMed: 37582759
DOI: 10.1186/s12985-023-02145-5 -
Diabetes Care Feb 2024Diabetic macular edema (DME) is the leading cause of vision loss in people with diabetes. Application of artificial intelligence (AI) in interpreting fundus photography... (Meta-Analysis)
Meta-Analysis Review
Performance of Artificial Intelligence in Detecting Diabetic Macular Edema From Fundus Photography and Optical Coherence Tomography Images: A Systematic Review and Meta-analysis.
BACKGROUND
Diabetic macular edema (DME) is the leading cause of vision loss in people with diabetes. Application of artificial intelligence (AI) in interpreting fundus photography (FP) and optical coherence tomography (OCT) images allows prompt detection and intervention.
PURPOSE
To evaluate the performance of AI in detecting DME from FP or OCT images and identify potential factors affecting model performances.
DATA SOURCES
We searched seven electronic libraries up to 12 February 2023.
STUDY SELECTION
We included studies using AI to detect DME from FP or OCT images.
DATA EXTRACTION
We extracted study characteristics and performance parameters.
DATA SYNTHESIS
Fifty-three studies were included in the meta-analysis. FP-based algorithms of 25 studies yielded pooled area under the receiver operating characteristic curve (AUROC), sensitivity, and specificity of 0.964, 92.6%, and 91.1%, respectively. OCT-based algorithms of 28 studies yielded pooled AUROC, sensitivity, and specificity of 0.985, 95.9%, and 97.9%, respectively. Potential factors improving model performance included deep learning techniques, larger size, and more diversity in training data sets. Models demonstrated better performance when validated internally than externally, and those trained with multiple data sets showed better results upon external validation.
LIMITATIONS
Analyses were limited by unstandardized algorithm outcomes and insufficient data in patient demographics, OCT volumetric scans, and external validation.
CONCLUSIONS
This meta-analysis demonstrates satisfactory performance of AI in detecting DME from FP or OCT images. External validation is warranted for future studies to evaluate model generalizability. Further investigations may estimate optimal sample size, effect of class balance, patient demographics, and additional benefits of OCT volumetric scans.
Topics: Humans; Diabetic Retinopathy; Macular Edema; Artificial Intelligence; Tomography, Optical Coherence; Photography; Diabetes Mellitus
PubMed: 38241500
DOI: 10.2337/dc23-0993 -
Surgical Endoscopy Oct 2023Technical skill assessment in surgery relies on expert opinion. Therefore, it is time-consuming, costly, and often lacks objectivity. Analysis of intraoperative data by... (Review)
Review
BACKGROUND
Technical skill assessment in surgery relies on expert opinion. Therefore, it is time-consuming, costly, and often lacks objectivity. Analysis of intraoperative data by artificial intelligence (AI) has the potential for automated technical skill assessment. The aim of this systematic review was to analyze the performance, external validity, and generalizability of AI models for technical skill assessment in minimally invasive surgery.
METHODS
A systematic search of Medline, Embase, Web of Science, and IEEE Xplore was performed to identify original articles reporting the use of AI in the assessment of technical skill in minimally invasive surgery. Risk of bias (RoB) and quality of the included studies were analyzed according to Quality Assessment of Diagnostic Accuracy Studies criteria and the modified Joanna Briggs Institute checklists, respectively. Findings were reported according to the Preferred Reporting Items for Systematic Reviews and Meta-Analyses statement.
RESULTS
In total, 1958 articles were identified, 50 articles met eligibility criteria and were analyzed. Motion data extracted from surgical videos (n = 25) or kinematic data from robotic systems or sensors (n = 22) were the most frequent input data for AI. Most studies used deep learning (n = 34) and predicted technical skills using an ordinal assessment scale (n = 36) with good accuracies in simulated settings. However, all proposed models were in development stage, only 4 studies were externally validated and 8 showed a low RoB.
CONCLUSION
AI showed good performance in technical skill assessment in minimally invasive surgery. However, models often lacked external validity and generalizability. Therefore, models should be benchmarked using predefined performance metrics and tested in clinical implementation studies.
Topics: Humans; Artificial Intelligence; Minimally Invasive Surgical Procedures; Academies and Institutes; Benchmarking; Checklist
PubMed: 37584774
DOI: 10.1007/s00464-023-10335-z -
Journal of Diabetes Science and... Mar 2024Diabetic microvascular complications significantly impact morbidity and mortality. This review focuses on machine learning/artificial intelligence (ML/AI) in predicting... (Review)
Review
IMPORTANCE AND AIMS
Diabetic microvascular complications significantly impact morbidity and mortality. This review focuses on machine learning/artificial intelligence (ML/AI) in predicting diabetic retinopathy (DR), diabetic kidney disease (DKD), and diabetic neuropathy (DN).
METHODS
A comprehensive PubMed search from 1990 to 2023 identified studies on ML/AI models for diabetic microvascular complications. The review analyzed study design, cohorts, predictors, ML techniques, prediction horizon, and performance metrics.
RESULTS
Among the 74 identified studies, 256 featured internally validated ML models and 124 had externally validated models, with about half being retrospective. Since 2010, there has been a rise in the use of ML for predicting microvascular complications, mainly driven by DKD research across 27 countries. A more modest increase in ML research on DR and DN was observed, with publications from fewer countries. For all microvascular complications, predictive models achieved a mean (standard deviation) c-statistic of 0.79 (0.09) on internal validation and 0.72 (0.12) on external validation. Diabetic kidney disease models had the highest discrimination, with c-statistics of 0.81 (0.09) on internal validation and 0.74 (0.13) on external validation, respectively. Few studies externally validated prediction of DN. The prediction horizon, outcome definitions, number and type of predictors, and ML technique significantly influenced model performance.
CONCLUSIONS AND RELEVANCE
There is growing global interest in using ML for predicting diabetic microvascular complications. Research on DKD is the most advanced in terms of publication volume and overall prediction performance. Both DR and DN require more research. External validation and adherence to recommended guidelines are crucial.
Topics: Humans; Artificial Intelligence; Diabetes Mellitus; Diabetic Nephropathies; Diabetic Neuropathies; Diabetic Retinopathy; Machine Learning; Retrospective Studies
PubMed: 38189280
DOI: 10.1177/19322968231223726