+1 Recommend
0 collections
      • Record: found
      • Abstract: found
      • Article: found
      Is Open Access

      A narrative review of machine learning as promising revolution in clinical practice of scoliosis


      Read this article at

          There is no author summary for this article yet. Authors can add summaries to their articles on ScienceOpen to make them more accessible to a non-specialist audience.


          Machine learning (ML), as an advanced domain of artificial intelligence (AI), is progressively changing our view of the world. By implementing its algorithms, our ability to detect previously undiscoverable patterns in data has the potential to revolutionize predictive analytics. Scoliosis, as a relatively specialized branch in the spine field, mainly covers the pediatric, adult and the elderly populations, and its diagnosis and treatment remain difficult. With recent efforts and interdisciplinary cooperation, ML has been widely applied to investigate issues related to scoliosis, and surprisingly augment a surgeon’s ability in clinical practice related to scoliosis. Meanwhile, ML models penetrate in every stage of the clinical practice procedure of scoliosis. In this review, we first present a brief description of the application of ML in the clinical practice procedures regarding scoliosis, including screening, diagnosis and classification, surgical decision making, intraoperative manipulation, complication prediction, prognosis prediction and rehabilitation. Meanwhile, the ML models and specific applications adopted are presented. Additionally, current limitations and future directions are briefly discussed regarding its use in the field of scoliosis. We believe that the implementation of ML is a promising revolution to assist surgeons in all aspects of clinical practice related to scoliosis in the near future.

          Related collections

          Most cited references79

          • Record: found
          • Abstract: found
          • Article: found
          Is Open Access

          Artificial intelligence versus clinicians: systematic review of design, reporting standards, and claims of deep learning studies

          Abstract Objective To systematically examine the design, reporting standards, risk of bias, and claims of studies comparing the performance of diagnostic deep learning algorithms for medical imaging with that of expert clinicians. Design Systematic review. Data sources Medline, Embase, Cochrane Central Register of Controlled Trials, and the World Health Organization trial registry from 2010 to June 2019. Eligibility criteria for selecting studies Randomised trial registrations and non-randomised studies comparing the performance of a deep learning algorithm in medical imaging with a contemporary group of one or more expert clinicians. Medical imaging has seen a growing interest in deep learning research. The main distinguishing feature of convolutional neural networks (CNNs) in deep learning is that when CNNs are fed with raw data, they develop their own representations needed for pattern recognition. The algorithm learns for itself the features of an image that are important for classification rather than being told by humans which features to use. The selected studies aimed to use medical imaging for predicting absolute risk of existing disease or classification into diagnostic groups (eg, disease or non-disease). For example, raw chest radiographs tagged with a label such as pneumothorax or no pneumothorax and the CNN learning which pixel patterns suggest pneumothorax. Review methods Adherence to reporting standards was assessed by using CONSORT (consolidated standards of reporting trials) for randomised studies and TRIPOD (transparent reporting of a multivariable prediction model for individual prognosis or diagnosis) for non-randomised studies. Risk of bias was assessed by using the Cochrane risk of bias tool for randomised studies and PROBAST (prediction model risk of bias assessment tool) for non-randomised studies. Results Only 10 records were found for deep learning randomised clinical trials, two of which have been published (with low risk of bias, except for lack of blinding, and high adherence to reporting standards) and eight are ongoing. Of 81 non-randomised clinical trials identified, only nine were prospective and just six were tested in a real world clinical setting. The median number of experts in the comparator group was only four (interquartile range 2-9). Full access to all datasets and code was severely limited (unavailable in 95% and 93% of studies, respectively). The overall risk of bias was high in 58 of 81 studies and adherence to reporting standards was suboptimal (<50% adherence for 12 of 29 TRIPOD items). 61 of 81 studies stated in their abstract that performance of artificial intelligence was at least comparable to (or better than) that of clinicians. Only 31 of 81 studies (38%) stated that further prospective studies or trials were required. Conclusions Few prospective deep learning studies and randomised trials exist in medical imaging. Most non-randomised trials are not prospective, are at high risk of bias, and deviate from existing reporting standards. Data and code availability are lacking in most studies, and human comparator groups are often small. Future studies should diminish risk of bias, enhance real world clinical relevance, improve reporting and transparency, and appropriately temper conclusions. Study registration PROSPERO CRD42019123605.
            • Record: found
            • Abstract: found
            • Article: not found

            Adolescent idiopathic scoliosis: a new classification to determine extent of spinal arthrodesis.

            The lack of a reliable, universally acceptable system for classification of adolescent idiopathic scoliosis has made comparisons between various types of operative treatment an impossible task. Furthermore, long-term outcomes cannot be determined because of the great variations in the description of study groups. We developed a new classification system with three components: curve type (1 through 6), a lumbar spine modifier (A, B, or C), and a sagittal thoracic modifier (-, N, or +). The six curve types have specific characteristics, on coronal and sagittal radiographs, that differentiate structural and nonstructural curves in the proximal thoracic, main thoracic, and thoracolumbar/lumbar regions. The lumbar spine modifier is based on the relationship of the center sacral vertical line to the apex of the lumbar curve, and the sagittal thoracic modifier is based on the sagittal curve measurement from the fifth to the twelfth thoracic level. A minus sign represents a curve of less than +10 degrees, N represents a curve of 10 degrees to 40 degrees, and a plus sign represents a curve of more than +40 degrees. Five surgeons, members of the Scoliosis Research Society who had developed the new system and who had previously tested the reliability of the King classification on radiographs of twenty-seven patients, measured the same radiographs (standing coronal and lateral as well as supine side-bending views) to test the reliability of the new classification. A randomly chosen independent group of seven surgeons, also members of the Scoliosis Research Society, tested the reliability and validity of the classification as well. The interobserver and intraobserver kappa values for the curve type were, respectively, 0.92 and 0.83 for the five developers of the system and 0.740 and 0.893 for the independent group of seven scoliosis surgeons. In the independent group, the mean interobserver and intraobserver kappa values were 0.800 and 0.840 for the lumbar modifier and 0.938 and 0.970 for the sagittal thoracic modifier. These kappa values were all in the good-to-excellent range (>0.75), except for the interobserver reliability of the independent group for the curve type (kappa = 0.74), which fell just below this level. This new two-dimensional classification of adolescent idiopathic scoliosis, as tested by two groups of surgeons, was shown to be much more reliable than the King system. Additional studies are necessary to determine the versatility, reliability, and accuracy of the classification for defining the vertebrae to be included in an arthrodesis.
              • Record: found
              • Abstract: not found
              • Article: not found

              Implementing Machine Learning in Health Care — Addressing Ethical Challenges


                Author and article information

                Ann Transl Med
                Ann Transl Med
                Annals of Translational Medicine
                AME Publishing Company
                January 2021
                January 2021
                : 9
                : 1
                : 67
                [1 ]Department of Orthopedics, Shanghai Changhai Hospital , Shanghai, China;
                [2 ]Department of Orthopedics, Shanghai Changzheng Hospital , Shanghai, China;
                [3 ]Basic medicine college, Navy Medical University , Shanghai, China
                Author notes

                Contributions: (I) Conception and design: C Yang; (II) Administrative support: M Li; (III) Provision of study materials or patients: K Chen; (IV) Collection and assembly of data: X Zhai; (V) Data analysis and interpretation: K Sun, H Wang; (VI) Manuscript writing: All authors; (VII) Final approval of manuscript: All authors.


                These authors contributed equally to this work.

                Correspondence to: Changwei Yang, MD; Ming Li, MD. Department of Orthopedics, Shanghai Changhai Hospital, No. 168, Changhai Road, Shanghai 200433, China. Email: changwei_y@ 123456qq.com ; limingch0103@ 123456126.com .
                2021 Annals of Translational Medicine. All rights reserved.

                Open Access Statement: This is an Open Access article distributed in accordance with the Creative Commons Attribution-NonCommercial-NoDerivs 4.0 International License (CC BY-NC-ND 4.0), which permits the non-commercial replication and distribution of the article with the strict proviso that no changes or edits are made and the original work is properly cited (including links to both the formal publication through the relevant DOI and the license). See: https://creativecommons.org/licenses/by-nc-nd/4.0.

                : 24 July 2020
                : 27 November 2020
                Review Article

                scoliosis,machine learning (ml),revolution,clinical practice


                Comment on this article