Literature DB >> 30252971

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

Uran Ferizi1, Harrison Besser1, Pirro Hysi2, Joseph Jacobs3, Chamith S Rajapakse4, Cheng Chen5, Punam K Saha5, Stephen Honig1, Gregory Chang1.   

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.
© 2018 International Society for Magnetic Resonance in Medicine.

Entities:  

Year:  2018        PMID: 30252971      PMCID: PMC7340101          DOI: 10.1002/jmri.26280

Source DB:  PubMed          Journal:  J Magn Reson Imaging        ISSN: 1053-1807            Impact factor:   4.813


  11 in total

1.  Classification of sodium MRI data of cartilage using machine learning.

Authors:  Guillaume Madelin; Frederick Poidevin; Antonios Makrymallis; Ravinder R Regatte
Journal:  Magn Reson Med       Date:  2014-11-03       Impact factor: 4.668

2.  Cost-effectiveness of Virtual Bone Strength Testing in Osteoporosis Screening Programs for Postmenopausal Women in the United States.

Authors:  Christoph A Agten; Austin J Ramme; Stella Kang; Stephen Honig; Gregory Chang
Journal:  Radiology       Date:  2017-06-14       Impact factor: 11.105

3.  Machine Learning Principles Can Improve Hip Fracture Prediction.

Authors:  Christian Kruse; Pia Eiken; Peter Vestergaard
Journal:  Calcif Tissue Int       Date:  2017-02-14       Impact factor: 4.333

4.  Assessment of fracture risk and its application to screening for postmenopausal osteoporosis: synopsis of a WHO report. WHO Study Group.

Authors:  J A Kanis
Journal:  Osteoporos Int       Date:  1994-11       Impact factor: 4.507

5.  Clinical fracture risk evaluated by hierarchical agglomerative clustering.

Authors:  C Kruse; P Eiken; P Vestergaard
Journal:  Osteoporos Int       Date:  2016-11-16       Impact factor: 4.507

Review 6.  Structural and functional assessment of trabecular and cortical bone by micro magnetic resonance imaging.

Authors:  Felix W Wehrli
Journal:  J Magn Reson Imaging       Date:  2007-02       Impact factor: 4.813

7.  Automatic classification of prostate cancer Gleason scores from multiparametric magnetic resonance images.

Authors:  Duc Fehr; Harini Veeraraghavan; Andreas Wibmer; Tatsuo Gondo; Kazuhiro Matsumoto; Herbert Alberto Vargas; Evis Sala; Hedvig Hricak; Joseph O Deasy
Journal:  Proc Natl Acad Sci U S A       Date:  2015-11-02       Impact factor: 11.205

8.  Bone mineral density thresholds for pharmacological intervention to prevent fractures.

Authors:  Ethel S Siris; Ya-Ting Chen; Thomas A Abbott; Elizabeth Barrett-Connor; Paul D Miller; Lois E Wehren; Marc L Berger
Journal:  Arch Intern Med       Date:  2004-05-24

9.  Mechanical implications of estrogen supplementation in early postmenopausal women.

Authors:  Felix W Wehrli; Chamith S Rajapakse; Jeremy F Magland; Peter J Snyder
Journal:  J Bone Miner Res       Date:  2010-06       Impact factor: 6.741

10.  Disadvantages of using the area under the receiver operating characteristic curve to assess imaging tests: a discussion and proposal for an alternative approach.

Authors:  Steve Halligan; Douglas G Altman; Susan Mallett
Journal:  Eur Radiol       Date:  2015-01-20       Impact factor: 5.315

View more
  12 in total

Review 1.  Artificial intelligence, osteoporosis and fragility fractures.

Authors:  Uran Ferizi; Stephen Honig; Gregory Chang
Journal:  Curr Opin Rheumatol       Date:  2019-07       Impact factor: 5.006

Review 2.  Artificial Intelligence in Musculoskeletal Imaging: Current Status and Future Directions.

Authors:  Soterios Gyftopoulos; Dana Lin; Florian Knoll; Ankur M Doshi; Tatiane Cantarelli Rodrigues; Michael P Recht
Journal:  AJR Am J Roentgenol       Date:  2019-06-05       Impact factor: 3.959

3.  Reverse engineering the FRAX algorithm: Clinical insights and systematic analysis of fracture risk.

Authors:  Jules D Allbritton-King; Julia K Elrod; Philip S Rosenberg; Timothy Bhattacharyya
Journal:  Bone       Date:  2022-02-28       Impact factor: 4.626

4.  Study of the significance of parameters and their interaction on assessing femoral fracture risk by quantitative statistical analysis.

Authors:  Rabina Awal; Jalel Ben Hmida; Yunhua Luo; Tanvir Faisal
Journal:  Med Biol Eng Comput       Date:  2022-02-04       Impact factor: 2.602

5.  Fully automated radiomic screening pipeline for osteoporosis and abnormal bone density with a deep learning-based segmentation using a short lumbar mDixon sequence.

Authors:  Yinxia Zhao; Tianyun Zhao; Shenglan Chen; Xintao Zhang; Mario Serrano Sosa; Jin Liu; Xianfu Mo; Xiaojun Chen; Mingqian Huang; Shaolin Li; Xiaodong Zhang; Chuan Huang
Journal:  Quant Imaging Med Surg       Date:  2022-02

6.  Automatic estimation of knee effusion from limited MRI data.

Authors:  Sandhya Raman; Garry E Gold; Matthew S Rosen; Bragi Sveinsson
Journal:  Sci Rep       Date:  2022-02-24       Impact factor: 4.379

Review 7.  Blood factors as biomarkers in osteoporosis: points from the COVID-19 era.

Authors:  Francesca Salamanna; Melania Maglio; Veronica Borsari; Maria Paola Landini; Milena Fini
Journal:  Trends Endocrinol Metab       Date:  2021-07-07       Impact factor: 12.015

8.  Bone mineral density response prediction following osteoporosis treatment using machine learning to aid personalized therapy.

Authors:  Thiraphat Tanphiriyakun; Sattaya Rojanasthien; Piyapong Khumrin
Journal:  Sci Rep       Date:  2021-07-05       Impact factor: 4.379

9.  Applications of Machine Learning Using Electronic Medical Records in Spine Surgery.

Authors:  John T Schwartz; Michael Gao; Eric A Geng; Kush S Mody; Christopher M Mikhail; Samuel K Cho
Journal:  Neurospine       Date:  2019-12-31

Review 10.  Machine Learning in Healthcare.

Authors:  Hafsa Habehh; Suril Gohel
Journal:  Curr Genomics       Date:  2021-12-16       Impact factor: 2.689

View more

北京卡尤迪生物科技股份有限公司 © 2022-2023.