Integrative blockwise sparse analysis for tissue characterization and classification

Machine Learning Solutions for Osteoporosis—A Review

“…( 32,50 ) Twelve studies validated their model using accuracy with an average performance of 90.1% (range 70.0% to 98.9%); 22 validated their model using AUC with a mean of 0.90 (range 0.74 to 1.00). Surprisingly, six reported near perfect AUCs (AUC ≥0.99), ( 29,43,48,54,56,60 ) indicating potential overfitting with risk for poor generalization. Other studies presented a clear risk of overfitting by using data with important bias between case/control groups, (54,58 ) model selection based on the testing set, (29,40,48,51,60 ) reporting high discrepancies between training and test sets, (37,59 ) or including a part of the training data set in the testing data.…”

“…Other studies presented a clear risk of overfitting by using data with important bias between case/control groups, (54,58 ) model selection based on the testing set, (29,40,48,51,60 ) reporting high discrepancies between training and test sets, (37,59 ) or including a part of the training data set in the testing data. ( 33,63,65 ) Several studies did not report characteristics of their data set ( 48,55,56,59–64 ) or the model selection process. ( 33,39,41,42,45,46,50,51,53,56–61,64,65 ) Performance was significantly impacted by case prevalence where accuracy dropped from 94.0% to 88.4% when tested on 13% and 50% positive (osteoporotic) cases, respectively.…”

“…( 29,32–34,36–65 ) Osteoporosis classification was made based on lumbar BMD, ( 32–34,37,51 ) hip BMD, ( 38,50,58 ) lumbar and hip BMD, ( 29,39–42,46–48,53,59,60 ) other non‐standard assessments, ( 43,44,49,54–56,65 ) or unspecified. ( 36,45,52,57,61–64 ) Studies identified osteoporosis based on opportunistic imaging from CT, ( 32–34 ) X‐ray, ( 37,38,43–45,55–59,63,64 ) or dental imaging; (36,47–49,53,54,60,62 ) other studies used data from patient characteristics, ( 40,41,50,51,61,65 ) bone biomarkers, (29,39 ) or acoustical responses. ( 42,52 ) As outcome, studies classified osteoporotic versus normal patients, ( 29,36,39,40,43,49,50,52,54–57,62 ) osteoporotic versus non‐osteoporotic patients (based on a BMD T ‐score threshold of –2.5 SD), ( 34,38,44,64 ) normal versus abnormal subjects (based on the BMD T ‐score threshold of −1 SD), ( 33,41,42,45,47,48,58–60,65 ) experimented multiple classifications, ( 46,63 ) or assigned to three classes: osteoporosis (BMD T ‐score ≤ −2.5 SD), osteopenia (−2.5 < BMD T ‐score ≤ −1), and normal (BMD T ‐score > −1 SD).…”

“…( 29,51,60,72,92 ) Acknowledging potential biases or limitations is fundamental for the accurate interpretation and especially for claims related to clinical implication. Nevertheless, several studies showed a greater awareness of the potential existence of bias and made efforts to address this either directly by controlling for the risks of overfitting, ( 23,28,30,32,34,37–40,43–46,49,53,54,56,57,59,64,77–85,90,91,93–95 ) indirectly by visualizing decision‐making, ( 36,38,48,66,67,78,79,84,90,94,104 ) or by using gold standard strategies for comparison. ( 66,71,78–83,85,91,93,94,104,107 )…”

“…Nevertheless, the highest reported results in regression and classification tasks achieved almost perfect performance, which cannot be explained solely by their popularity. ( 26,27,29,30,35,43,48,51,54,56,60,72,78,79,91,92,94 ) Indeed, certain limitations, such as potential bias in the input data ( 78 ) or the use of a region of interest instead of full images, ( 79,91 ) help to explain these impressive performances. Although our review presents simple comparisons between studies, any model performance metrics reported and direct comparisons should be interpreted with caution.…”