Machine learning outperforms clinical experts in classification of hip fractures

Murphy, Ellen; Ehrhardt, Beate; Gregson, Celia L; Arx, O.A. von; Hartley, April; Whitehouse, Michael R; Thomas, Marie; Stenhouse, Gregor; Chesser, T.J.S.; Budd, C. J.; Gill, Harmandeep Singh

doi:10.1038/s41598-022-06018-9

Cited by 26 publications

(17 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Among the included studies, the architecture based on the GoogLeNet architectural model [ 7 , 11 , 18 ] or the DenseNet architectural model [ 13 , 14 , 20 ] was the most common with three each. Among the data input proportions, the study of Adams et al had the lowest training rate of 57% [ 11 ], and the study of Yamada et al had the largest training rate of 95% [ 19 ].…”

Section: Resultsmentioning

confidence: 99%

“…The remaining 45 studies underwent full-text reviews, and subsequently, 31 studies were excluded. Finally, 14 studies are included in this study [1,7,8,[11][12][13][14][15][16][17][18][19][20][21]. The details of the identification of relevant studies are shown in the flow chart of the study selection process (Fig.…”

Section: Resultsmentioning

confidence: 99%

“…Delayed diagnosis and treatment may lead to complications, such as malunion, osteonecrosis, and arthritis [19]. Moreover, as total number of imaging and radiological examinations has increased, radiology departments cannot report all acquired radiographs in timely manner [7]. For this reason, several studies on detecting hip fractures using ML have already been reported [1,7,8,[11][12][13][14][15][16][17][18][19][20][21].…”

Section: Expected Effects Of Ai In Hip Fracture Diagnosismentioning

confidence: 99%

“…In addition, fracture classification is important for determining the surgical method and restoring the patient's mobility [ 6 ]. Since the surgical method is directly related to the medical cost, several countries have provided guidelines for treatment methods according to the classification of hip fractures [ 7 ]. However, classifying fractures from a lot of image information is time-consuming [ 8 ].…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Artificial intelligence and machine learning on diagnosis and classification of hip fracture: systematic review

Cha

Kim

Park³

et al. 2022

J Orthop Surg Res

View full text Add to dashboard Cite

Background In the emergency room, clinicians spend a lot of time and are exposed to mental stress. In addition, fracture classification is important for determining the surgical method and restoring the patient's mobility. Recently, with the help of computers using artificial intelligence (AI) or machine learning (ML), diagnosis and classification of hip fractures can be performed easily and quickly. The purpose of this systematic review is to search for studies that diagnose and classify for hip fracture using AI or ML, organize the results of each study, analyze the usefulness of this technology and its future use value. Methods PubMed Central, OVID Medline, Cochrane Collaboration Library, Web of Science, EMBASE, and AHRQ databases were searched to identify relevant studies published up to June 2022 with English language restriction. The following search terms were used [All Fields] AND (", "[MeSH Terms] OR (""[All Fields] AND "bone"[All Fields]) OR "bone fractures"[All Fields] OR "fracture"[All Fields]). The following information was extracted from the included articles: authors, publication year, study period, type of image, type of fracture, number of patient or used images, fracture classification, reference diagnosis of fracture diagnosis and classification, and augments of each studies. In addition, AI name, CNN architecture type, ROI or important region labeling, data input proportion in training/validation/test, and diagnosis accuracy/AUC, classification accuracy/AUC of each studies were also extracted. Results In 14 finally included studies, the accuracy of diagnosis for hip fracture by AI was 79.3–98%, and the accuracy of fracture diagnosis in AI aided humans was 90.5–97.1. The accuracy of human fracture diagnosis was 77.5–93.5. AUC of fracture diagnosis by AI was 0.905–0.99. The accuracy of fracture classification by AI was 86–98.5 and AUC was 0.873–1.0. The forest plot represented that the mean AI diagnosis accuracy was 0.92, the mean AI diagnosis AUC was 0.969, the mean AI classification accuracy was 0.914, and the mean AI classification AUC was 0.933. Among the included studies, the architecture based on the GoogLeNet architectural model or the DenseNet architectural model was the most common with three each. Among the data input proportions, the study with the lowest training rate was 57%, and the study with the highest training rate was 95%. In 14 studies, 5 studies used Grad-CAM for highlight important regions. Conclusion We expected that our study may be helpful in making judgments about the use of AI in the diagnosis and classification of hip fractures. It is clear that AI is a tool that can help medical staff reduce the time and effort required for hip fracture diagnosis with high accuracy. Further studies are needed to determine what effect this causes in actual clinical situations.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Resultsmentioning

confidence: 99%

Section: Expected Effects Of Ai In Hip Fracture Diagnosismentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Artificial intelligence and machine learning on diagnosis and classification of hip fracture: systematic review

Cha

Kim

Park³

et al. 2022

J Orthop Surg Res

View full text Add to dashboard Cite

show abstract

“…Hip fracture affects 1.6 million people globally each year, and increases morbidity and mortality (1,2) . There is potential for risk reduction through diet modification, but prospective evidence for associations between intake of several foods and nutrients and hip fracture risk is limited.…”

mentioning

confidence: 99%

Diet and hip fracture risk in the UK women's cohort study

2022

View full text Add to dashboard Cite

Hip fracture affects 1.6 million people globally each year, and increases morbidity and mortality (1,2) . There is potential for risk reduction through diet modification, but prospective evidence for associations between intake of several foods and nutrients and hip fracture risk is limited. This study aimed to investigate associations between food and nutrient intakes and hip fracture risk in the UK Women's Cohort Study, and to determine the role of body mass index (BMI) as a potential effect modifier. Dietary, lifestyle, anthropometric, and socio-economic information of 35372 UK women, ages 35-69 years, were collected in a survey at recruitment (1995)(1996)(1997)(1998) and included a validated 217-item food frequency questionnaire. Hip fracture cases were identified by linking participant data at recruitment with their Hospital Episode Statistics up to March 2019. Cox regression models were used to estimate associations between standard portion increases in food and nutrient intakes and hip fracture risk over a mean follow-up time of 21.1 years. Among 30,244 women included, 993 hip fracture cases were observed (637,427 person-years). After adjustment for confounders, every additional cup of tea or coffee was associated with a reduced risk of hip fracture (0.96 (0.92, 0.996). A 25 g/day increase in dietary protein intake was associated with a reduced risk of hip fracture (HR (95% CI): 0.86 (0.73, 1.00)). In subgroup analyses, BMI (<18.5, 18.5-24.9, ≥25 kg/m 2 ) modified linear associations between dietary intakes of protein, calcium, vitamin D, total dairy, milk, and tea and hip fracture risk; these foods and nutrients were associated with a reduced risk of hip fracture in underweight but not healthy or overweight participants. The HR (95% CI) for protein (per 25 g/day increase) in underweight participants was 0.55 (0.38, 0.78), though the number of cases in underweight participants was small. This is the first prospective study of multiple food and nutrient intakes in relation to hip fracture risk by BMI. Results suggest that the potential role of some foods and nutrients in hip fracture prevention, particularly in underweight women, merits confirmation.

show abstract

Artificial Intelligence for Hip Fracture Detection and Outcome Prediction

et al. 2023

View full text Add to dashboard Cite

ImportanceArtificial intelligence (AI) enables powerful models for establishment of clinical diagnostic and prognostic tools for hip fractures; however the performance and potential impact of these newly developed algorithms are currently unknown.ObjectiveTo evaluate the performance of AI algorithms designed to diagnose hip fractures on radiographs and predict postoperative clinical outcomes following hip fracture surgery relative to current practices.Data SourcesA systematic review of the literature was performed using the MEDLINE, Embase, and Cochrane Library databases for all articles published from database inception to January 23, 2023. A manual reference search of included articles was also undertaken to identify any additional relevant articles.Study SelectionStudies developing machine learning (ML) models for the diagnosis of hip fractures from hip or pelvic radiographs or to predict any postoperative patient outcome following hip fracture surgery were included.Data Extraction and SynthesisThis study followed the Preferred Reporting Items for Systematic Reviews and Meta-analyses and was registered with PROSPERO. Eligible full-text articles were evaluated and relevant data extracted independently using a template data extraction form. For studies that predicted postoperative outcomes, the performance of traditional predictive statistical models, either multivariable logistic or linear regression, was recorded and compared with the performance of the best ML model on the same out-of-sample data set.Main Outcomes and MeasuresDiagnostic accuracy of AI models was compared with the diagnostic accuracy of expert clinicians using odds ratios (ORs) with 95% CIs. Areas under the curve for postoperative outcome prediction between traditional statistical models (multivariable linear or logistic regression) and ML models were compared.ResultsOf 39 studies that met all criteria and were included in this analysis, 18 (46.2%) used AI models to diagnose hip fractures on plain radiographs and 21 (53.8%) used AI models to predict patient outcomes following hip fracture surgery. A total of 39 598 plain radiographs and 714 939 hip fractures were used for training, validating, and testing ML models specific to diagnosis and postoperative outcome prediction, respectively. Mortality and length of hospital stay were the most predicted outcomes. On pooled data analysis, compared with clinicians, the OR for diagnostic error of ML models was 0.79 (95% CI, 0.48-1.31; P = .36; I2 = 60%) for hip fracture radiographs. For the ML models, the mean (SD) sensitivity was 89.3% (8.5%), specificity was 87.5% (9.9%), and F1 score was 0.90 (0.06). The mean area under the curve for mortality prediction was 0.84 with ML models compared with 0.79 for alternative controls (P = .09).Conclusions and RelevanceThe findings of this systematic review and meta-analysis suggest that the potential applications of AI to aid with diagnosis from hip radiographs are promising. The performance of AI in diagnosing hip fractures was comparable with that of expert radiologists and surgeons. However, current implementations of AI for outcome prediction do not seem to provide substantial benefit over traditional multivariable predictive statistics.

show abstract

Machine learning outperforms clinical experts in classification of hip fractures

Cited by 26 publications

References 41 publications

Artificial intelligence and machine learning on diagnosis and classification of hip fracture: systematic review

Artificial intelligence and machine learning on diagnosis and classification of hip fracture: systematic review

Diet and hip fracture risk in the UK women's cohort study

Artificial Intelligence for Hip Fracture Detection and Outcome Prediction

Contact Info

Product

Resources

About