Dataset Information

Artificial Intelligence Applied to Osteoporosis: A Performance Comparison of Machine Learning Algorithms in Predicting Fragility Fractures From MRI Data.

ABSTRACT: BACKGROUND:A current challenge in osteoporosis is identifying patients at risk of bone fracture. PURPOSE:To identify the machine learning classifiers that predict best osteoporotic bone fractures and, from the data, to highlight the imaging features and the anatomical regions that contribute most to prediction performance. STUDY TYPE:Prospective (cross-sectional) case-control study. POPULATION:Thirty-two women with prior fragility bone fractures, of mean age?=?61.6 and body mass index (BMI)?=?22.7?kg/m2 , and 60 women without fractures, of mean age?=?62.3 and BMI?=?21.4?kg/m2 . Field Strength/ Sequence: 3D FLASH at 3T. ASSESSMENT:Quantitative MRI outcomes by software algorithms. Mechanical and topological microstructural parameters of the trabecular bone were calculated for five femoral regions, and added to the vector of features together with bone mineral density measurement, fracture risk assessment tool (FRAX) score, and personal characteristics such as age, weight, and height. We fitted 15 classifiers using 200 randomized cross-validation datasets. Statistical Tests: Data: Kolmogorov-Smirnov test for normality. Model Performance: sensitivity, specificity, precision, accuracy, F1-test, receiver operating characteristic curve (ROC). Two-sided t-test, with P < 0.05 for statistical significance. RESULTS:The top three performing classifiers are RUS-boosted trees (in particular, performing best with head data, F1?=?0.64?±?0.03), the logistic regression and the linear discriminant (both best with trochanteric datasets, F1?=?0.65?±?0.03 and F1?=?0.67?±?0.03, respectively). A permutation of these classifiers comprised the best three performers for four out of five anatomical datasets. After averaging across all the anatomical datasets, the score for the best performer, the boosted trees, was F1?=?0.63?±?0.03 for All-features dataset, F1?=?0.52?±?0.05 for the no-MRI dataset, and F1?=?0.48?±?0.06 for the no-FRAX dataset. Data Conclusion: Of many classifiers, the RUS-boosted trees, the logistic regression, and the linear discriminant are best for predicting osteoporotic fracture. Both MRI and FRAX independently add value in identifying osteoporotic fractures. The femoral head, greater trochanter, and inter-trochanter anatomical regions within the proximal femur yielded better F1-scores for the best three classifiers. LEVEL OF EVIDENCE:2 Technical Efficacy: Stage 2 J. Magn. Reson. Imaging 2019;49:1029-1038.

SUBMITTER: Ferizi U

PROVIDER: S-EPMC7340101 | biostudies-literature | 2019 Apr

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Artificial Intelligence Applied to Osteoporosis: A Performance Comparison of Machine Learning Algorithms in Predicting Fragility Fractures From MRI Data.

Ferizi Uran U Besser Harrison H Hysi Pirro P Jacobs Joseph J Rajapakse Chamith S CS Chen Cheng C Saha Punam K PK Honig Stephen S Chang Gregory G

Journal of magnetic resonance imaging : JMRI 20180925 4

<h4>Background</h4>A current challenge in osteoporosis is identifying patients at risk of bone fracture.<h4>Purpose</h4>To identify the machine learning classifiers that predict best osteoporotic bone fractures and, from the data, to highlight the imaging features and the anatomical regions that contribute most to prediction performance.<h4>Study type</h4>Prospective (cross-sectional) case-control study.<h4>Population</h4>Thirty-two women with prior fragility bone fractures, of mean age = 61.6 a ...[more]

PMID: 30252971

Similar Datasets

Project description:IntroductionThe increasing availability of healthcare data and rapid development of big data analytic methods has opened new avenues for use of Artificial Intelligence (AI)- and Machine Learning (ML)-based technology in medical practice. However, applications at the point of care are still scarce.ObjectiveReview and discuss case studies to understand current capabilities for applying AI/ML in the healthcare setting, and regulatory requirements in the US, Europe and China.MethodsA targeted narrative literature review of AI/ML based digital tools was performed. Scientific publications (identified in PubMed) and grey literature (identified on the websites of regulatory agencies) were reviewed and analyzed.ResultsFrom the regulatory perspective, AI/ML-based solutions can be considered medical devices (i.e., Software as Medical Device, SaMD). A case series of SaMD is presented. First, tools for monitoring and remote management of chronic diseases are presented. Second, imaging applications for diagnostic support are discussed. Finally, clinical decision support tools to facilitate the choice of treatment and precision dosing are reviewed. While tested and validated algorithms for precision dosing exist, their implementation at the point of care is limited, and their regulatory and commercialization pathway is not clear. Regulatory requirements depend on the level of risk associated with the use of the device in medical practice, and can be classified into administrative (manufacturing and quality control), software-related (design, specification, hazard analysis, architecture, traceability, software risk analysis, cybersecurity, etc.), clinical evidence (including patient perspectives in some cases), non-clinical evidence (dosing validation and biocompatibility/toxicology) and other, such as e.g. benefit-to-risk determination, risk assessment and mitigation. There generally is an alignment between the US and Europe. China additionally requires that the clinical evidence is applicable to the Chinese population and recommends that a third-party central laboratory evaluates the clinical trial results.ConclusionsThe number of promising AI/ML-based technologies is increasing, but few have been implemented widely at the point of care. The need for external validation, implementation logistics, and data exchange and privacy remain the main obstacles.

Project description:ObjectiveTo determine the rigor, generalizability, and reproducibility of published classification and detection artificial intelligence (AI) models for prostate cancer (PCa) on MRI using the Checklist for Artificial Intelligence in Medical Imaging (CLAIM) guidelines, a 42-item checklist that is considered a measure of best practice for presenting and reviewing medical imaging AI research.Materials and methodsThis review searched English literature for studies proposing PCa AI detection and classification models on MRI. Each study was evaluated with the CLAIM checklist. The additional outcomes for which data were sought included measures of AI model performance (eg, area under the curve [AUC], sensitivity, specificity, free-response operating characteristic curves), training and validation and testing group sample size, AI approach, detection versus classification AI, public data set utilization, MRI sequences used, and definition of gold standard for ground truth. The percentage of CLAIM checklist fulfillment was used to stratify studies into quartiles. Wilcoxon's rank-sum test was used for pair-wise comparisons.ResultsIn all, 75 studies were identified, and 53 studies qualified for analysis. The original CLAIM items that most studies did not fulfill includes item 12 (77% no): de-identification methods; item 13 (68% no): handling missing data; item 15 (47% no): rationale for choosing ground truth reference standard; item 18 (55% no): measurements of inter- and intrareader variability; item 31 (60% no): inclusion of validated interpretability maps; item 37 (92% no): inclusion of failure analysis to elucidate AI model weaknesses. An AUC score versus percentage CLAIM fulfillment quartile revealed a significant difference of the mean AUC scores between quartile 1 versus quartile 2 (0.78 versus 0.86, P = .034) and quartile 1 versus quartile 4 (0.78 versus 0.89, P = .003) scores. Based on additional information and outcome metrics gathered in this study, additional measures of best practice are defined. These new items include disclosure of public dataset usage, ground truth definition in comparison to other referenced works in the defined task, and sample size power calculation.ConclusionA large proportion of AI studies do not fulfill key items in CLAIM guidelines within their methods and results sections. The percentage of CLAIM checklist fulfillment is weakly associated with improved AI model performance. Additions or supplementations to CLAIM are recommended to improve publishing standards and aid reviewers in determining study rigor.

Project description:Orthogeriatric co-management (OGCM) may provide benefits for geriatric fragility fracture patients in terms of more frequent osteoporosis treatment and fewer re-fractures. Yet, we did not find higher costs in OGCM hospitals for re-fractures or antiosteoporotic medication for most fracture sites within 12 months, although antiosteoporotic medication was more often prescribed.PurposeEvidence suggests benefits of orthogeriatric co-management (OGCM) for hip fracture patients. Yet, evidence for other fractures is rare. The aim of our study was to conduct an evaluation of economic and health outcomes after the German OGCM for geriatric fragility fracture patients.MethodsThis retrospective cohort study was based on German health and long-term care insurance data. Individuals were 80 years and older, sustained a fragility fracture in 2014-2018, and were treated in hospitals certified for OGCM (ATZ group), providing OGCM without certification (OGCM group) or usual care (control group). Healthcare costs from payer perspective, prescribed medications, and re-fractures were investigated within 6 and 12 months. We used weighted gamma and two-part models and applied entropy balancing to account for the lack of randomization. All analyses were stratified per fracture site.ResultsWe observed 206,273 patients within 12-month follow-up, of whom 14,100 were treated in ATZ, 133,353 in OGCM, and 58,820 in other hospitals. Total average inpatient costs per patient were significantly higher in the OGCM and particularly ATZ group for all fracture sites, compared to control group. We did not find significant differences in costs for re-fractures or antiosteoporotic medication for most fracture sites, although antiosteoporotic medication was significantly more often observed in the OGCM and particularly ATZ group for hip, pelvic, and humerus fractures.ConclusionThe observed healthcare costs were higher in ATZ and OGCM hospitals within 12 months. Antiosteoporotic medication was prescribed more often in both groups for most fracture sites, although the corresponding medication costs did not increase.

Project description:This systematic review identified patients have unmet information needs about the nature of osteoporosis, medication, self-management and follow-up. Clinician knowledge and attitudes appear to be of key importance in determining whether these needs are met. Unmet information needs appear to have psychosocial consequences and result in poor treatment adherence. PURPOSE:Patient education is an integral component of the management of osteoporosis, yet patients are dissatisfied with the information they receive and see this as an area of research priority. This study aimed to describe and summarise the specific expressed information needs of patients in previously published qualitative research. METHODS:Using terms relating to osteoporosis, fragility fracture and information needs, seven databases were searched. Articles were screened using predefined inclusion and exclusion criteria. Full-text articles selected for inclusion underwent data extraction and quality appraisal. Findings were drawn together using narrative synthesis. RESULTS:The search identified 11,024 articles. Sixteen empirical studies were included in the review. Thematic analysis revealed three overarching themes relating to specific information needs, factors influencing whether information needs are met and the impact of unmet information needs. Specific information needs identified included the following: the nature of osteoporosis/fracture risk; medication; self-management and understanding the role of dual energy x-ray absorptiometry and follow-up. Perceived physician knowledge and attitudes, and the attitudes, beliefs and behaviours of patients were important factors in influencing whether information needs were met, in addition to contextual factors and the format of educational resources. Failure to elicit and address information needs appears to be associated with poor treatment adherence, deterioration of the doctor-patient relationship and important psychosocial consequences. CONCLUSION:This is the first study to describe the information needs of patients with osteoporosis and fracture, the impact of this information gap and possible solutions. Further research is needed to co-design and evaluate educational interventions with patients.

Dataset Information

Artificial Intelligence Applied to Osteoporosis: A Performance Comparison of Machine Learning Algorithms in Predicting Fragility Fractures From MRI Data.

Publications

Artificial Intelligence Applied to Osteoporosis: A Performance Comparison of Machine Learning Algorithms in Predicting Fragility Fractures From MRI Data.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets