A Machine Learning Algorithm to Predict the Probability of (Occult) Posterior Malleolar Fractures Associated With Tibial Shaft Fractures to Guide “Malleolus First” Fixation

Hendrickx, Laurent A M; Sobol, Garret; Langerhuizen, David W. G.; Bulstra, Anne Eva J.; Hreha, Jeremy; Sprague, Sheila; Sirkin, Michael; Ring, David; Kerkhoffs, Gino M. M. J.; Jaarsma, Ruurd L.; Doornberg, Job N.

doi:10.1097/bot.0000000000001663

Cited by 28 publications

(24 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Thus, small significant changes in daily decision-making in high-volume patient care will result in important overall public health advances. 51 , 52 In orthopaedics, ML-derived decision tools to assist clinicians in treatment outcomes have been developed in arthroplasty, 53 trauma, 10 , 12 , 38 oncology and spinal disorders. 54 – 57 In orthopaedic oncology, decision tools show accurate performance characteristics in pre-operative estimation of survival in patients with spinal or extremity metastatic disease.…”

Section: Part Ii: Three Forms Of Machine Learning To Aid Clinical Decmentioning

confidence: 99%

“… 6 In orthopaedics, our Massachusetts General Hospital-based SORG (Skeletal Oncology Research Group) is on the frontier of ML in orthopaedic musculosketal oncology to provide advanced models for predicting surgical outcomes to improve patient-centred care, 7 and the Traumaplatform ML Consortium is broadening the scope of AI to orthopaedic trauma. 8 – 10 However, critics may argue: ‘Why do so many promising applications have yet to be adopted in patients’ clinical care or doctors’ workflow?’…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Artificial intelligence in orthopaedics: false hope or not? A narrative review along the line of Gartner’s hype cycle

Oosterhoff

Doornberg

2020

EFORT Open Reviews

Self Cite

View full text Add to dashboard Cite

Artificial Intelligence (AI) in general, and Machine Learning (ML)-based applications in particular, have the potential to change the scope of healthcare, including orthopaedic surgery. The greatest benefit of ML is in its ability to learn from real-world clinical use and experience, and thereby its capability to improve its own performance. Many successful applications are known in orthopaedics, but have yet to be adopted and evaluated for accuracy and efficacy in patients’ care and doctors’ workflows. The recent hype around AI triggered hope for development of better risk stratification tools to personalize orthopaedics in all subsequent steps of care, from diagnosis to treatment. Computer vision applications for fracture recognition show promising results to support decision-making, overcome bias, process high-volume workloads without fatigue, and hold the promise of even outperforming doctors in certain tasks. In the near future, AI-derived applications are very likely to assist orthopaedic surgeons rather than replace us. ‘If the computer takes over the simple stuff, doctors will have more time again to practice the art of medicine’.76 Cite this article: EFORT Open Rev 2020;5:593-603. DOI: 10.1302/2058-5241.5.190092

show abstract

Section: Part Ii: Three Forms Of Machine Learning To Aid Clinical Decmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Artificial intelligence in orthopaedics: false hope or not? A narrative review along the line of Gartner’s hype cycle

Oosterhoff

Doornberg

2020

EFORT Open Reviews

Self Cite

View full text Add to dashboard Cite

show abstract

“…For patients with TSFs, the mean incidence of PMFs was 7.3% (0.9–24.3%) based on radiographic findings [ 1 , 11 , 18 – 20 , 22 ]. Based on a CT scan or MRI, the mean incidence was 25.5% (7.2–47.9%) (Table 1 ) [ 6 , 8 , 14 , 21 – 24 ]. For patients with spiral TSFs and distal third spiral TSFs, the mean incidences of PMFs were 7.5% and 28%, respectively, based on radiographs [ 1 , 2 , 4 ].…”

Section: Resultsmentioning

confidence: 99%

Incidence and missed diagnosis risk of occult posterior malleolar fractures associated with the tibial shaft fractures: a systematic review

et al. 2021

View full text Add to dashboard Cite

Background Tibial shaft fractures (TSFs) combined with occult posterior malleolar fractures (PMFs) are becoming widely recognized in the field of orthopedics. The purpose of this study was to determine the clinical incidence, missed diagnosis rate, and treatment strategies of this combined injury. Methods PubMed, Cochrane, and MEDLINE Ovid databases were searched for articles of English language from 1988 to 2020, identifying 1549 papers. Results Twenty-one of the 1278 identified studies were eligible for inclusion. Each study reported on the incidence of this combined injury, and 12 studies documented the missed diagnosis rate. Seventeen studies reported surgical intervention strategies for PMFs. In the present review, PMFs frequently occurred in spiral TSFs (70%), especially distal third spiral TSFs (70.4%), based on CT scans or additional MRI. Based on the original X-ray detection, approximately 50% of PMFs were missed in patients with a combined injury. In addition, the treatment strategies for PMFs were inconsistent. Most studies (11/17) believe that specific surgical management needs to be developed based on the fragment size, displacement, and stability of the PMF. Conclusions For patients with TSFs, spiral TSFs, especially distal third spiral TSFs, are closely related to PMFs and are often not sufficiently diagnosed by X-ray alone. Advanced CT and MRI examinations can significantly reduce the missed diagnosis rate of occult PMFs. According to available literature, the treatment strategy for PMFs associated with TSFs is questionable without convincing evidence of benefit.

show abstract

“…In order to intuitively demonstrate the performance of the algorithm in this research, the PMF algorithm ( Hendrickx et al, 2020 ) and the DBN algorithm ( Zhang et al, 2019 ) were introduced for comparative analysis.…”

Section: Resultsmentioning

confidence: 99%

Adoption of Human Personality Development Theory Combined With Deep Neural Network in Entrepreneurship Education of College Students

Zhen¹,

Yu²

2020

Front. Psychol.

View full text Add to dashboard Cite

In this research, the probability matrix factorization (PMF) algorithm was introduced to optimize the deep neural network algorithm model with the purpose of studying the application value of personality development theory and deep learning neural network in college students’ entrepreneurship psychological education courses. Based on the personality development theory, a recommendation algorithm system for entrepreneurial projects under optimized deep neural network was established. A total of 518 college students from several universities were divided into an experimental group and a control group, with 259 students in each group. In addition to the normal courses of entrepreneurship psychology education, students in the experimental group were taught the entrepreneurship project recommendation system based on the optimized deep neural network designed in this research, while students in the control group were taught entrepreneurship psychology education normally. The intervention effect before and after entrepreneurship education was evaluated by the questionnaire of college students’ entrepreneurial intention and college students’ entrepreneurial mental resilience scale. The results demonstrate that the system recall rate and accuracy based on the algorithm in this research have been significantly higher than that of PMF algorithm and deep belief network (DBN) algorithm, and the difference is statistically significant ( p < 0.05); the mean square error (MSE) of the proposed algorithm is significantly smaller than that of PMF algorithm and DBN algorithm, and the difference is statistically significant ( p < 0.05); the improvement of entrepreneurial toughness, entrepreneurial strength, optimism, entrepreneurial possibility, and behavioral tendency of the experimental group after the test was significantly higher than that of the control group ( p < 0.05). Therefore, compared with traditional algorithms, the proposed method for entrepreneurial projects based on the theory of personality development and the optimized deep neural network shows better performance, and it can effectively improve the entrepreneurial intention and psychological resilience of college students.

show abstract

A Machine Learning Algorithm to Predict the Probability of (Occult) Posterior Malleolar Fractures Associated With Tibial Shaft Fractures to Guide “Malleolus First” Fixation

Cited by 28 publications

References 39 publications

Artificial intelligence in orthopaedics: false hope or not? A narrative review along the line of Gartner’s hype cycle

Artificial intelligence in orthopaedics: false hope or not? A narrative review along the line of Gartner’s hype cycle

Incidence and missed diagnosis risk of occult posterior malleolar fractures associated with the tibial shaft fractures: a systematic review

Adoption of Human Personality Development Theory Combined With Deep Neural Network in Entrepreneurship Education of College Students

Contact Info

Product

Resources

About