Machine Learning Principles Can Improve Hip Fracture Prediction

Applications of machine learning and deep learning in musculoskeletal medicine: a narrative review

Artificial intelligence (AI), with its technologies such as machine perception, robotics, natural language processing, expert systems, and machine learning (ML) with its subset deep learning, have transformed patient care and administration in all fields of modern medicine. For many clinicians, however, the nature, scope, and resulting possibilities of ML and deep learning might not yet be fully clear. This narrative review provides an overview of the application of ML and deep learning in musculoskeletal medicine. It first introduces the concept of AI and machine learning and its associated fields. Different machine concepts such as supervised, unsupervised and reinforcement learning will then be presented with current applications and clinical perspective. Finally deep learning applications will be discussed. With significant improvements over the last decade, ML and its subset deep learning today offer potent tools for numerous applications to implement in clinical practice. While initial setup costs are high, these investments can reduce workload and cost globally. At the same time, many challenges remain, such as standardisation in data labelling and often insufficient validity of the obtained results. In addition, legal aspects still will have to be clarified. Until good analyses and predictions are obtained by an ML tool, patience in training and suitable data sets are required. Awareness of the strengths of ML and the limitations that lie within it will help put this technique to good use.

Accuracy of artificial intelligence in prediction of osteoporotic fractures in comparison with dual-energy X-ray absorptiometry and the Fracture Risk Assessment Tool: A systematic review

BACKGROUND

Osteoporotic fractures, whether due to postmenopausal or senile causes, impose a significant financial burden on developing countries and diminish quality of life. Recent advancements in artificial intelligence (AI) algorithms have demonstrated immense potential in predicting osteoporotic fractures.

AIM

To assess and compare the efficacy of AI models against dual-energy X-ray absorptiometry (DXA) and the Fracture Risk Assessment Tool (FRAX) in predicting fragility fractures.

METHODS

We conducted a literature search in English using electronic databases, including PubMed, Web of Science, and Scopus, for studies published until May 2024. The keywords employed were fragility fractures, osteoporosis, AI, deep learning, machine learning, and convolutional neural network. The inclusion criteria for selecting publications were based on studies involving patients with proximal femur and vertebral column fractures due to osteoporosis, utilizing AI algorithms, and analyzing the site of fracture and accuracy for predicting fracture risk using SPSS version 29 (Chicago, IL, United States).

RESULTS

We identified 156 publications for analysis. After applying our inclusion criteria, 24489 patients were analyzed from 13 studies. The mean area under the receiver operating characteristic curve was 0.925 ± 0.69. The mean sensitivity was 68.3% ± 15.3%, specificity was 85.5% ± 13.4%, and positive predictive value was 86.5% ± 6.3%. DXA showed a sensitivity of 37.0% and 74.0%, while FRAX demonstrated a sensitivity of 45.7% and 84.7%. The P value for sensitivity between DXA and AI was < 0.0001, while for FRAX it was < 0.0001 and 0.2.

CONCLUSION

This review found that AI is a valuable tool to analyze and identify patients who will suffer from fragility fractures before they occur, demonstrating superiority over DXA and FRAX. Further studies are necessary to be conducted across various centers with diverse population groups, larger datasets, and a longer duration of follow-up to enhance the predictive performance of the AI models before their universal application.

Prevention of Osteoporosis in SAMP6 Mice by Rikkunshi-To: Japanese Kampo Medicine

Osteoporosis can increase the risk of fracture in elderly patients, and insufficient control affects quality of life. Rikkunshi-To (RKT) has been prescribed for elderly patients to improve gastrointestinal function. We postulated that RKT has preventive potential for the development of osteoporosis. Thus, we developed a simple method to evaluate osteoporosis using a continuous series of X-ray images of femurs in mice, and investigated the effects of RKT on the development of osteoporosis in these mice. Male senescence-accelerated mouse strain P6 (SAMP6) mice, a model of senile osteoporosis in humans, were fed diets with or without RKT (1%). We collected X-ray images of the whole body of each mouse weekly and measured the ratio of cortical thickness of the femur (C/F index). The C/F index in SAMP6 mice fed the normal diet was increased between 50 and 80 days old, but it was significantly decreased after 120 days old. On the other hand, the C/F index in SAMP6 mice fed the RKT diet was increased between 50 and 80 days old; however, it remained unchanged throughout the experimental period. We also confirmed that the C/F index in SAMP6 mice fed the RKT diet suddenly decreased on the replacement of the RKT diet with a normal diet, suggesting that we can collect data related to a series of continuous changes in bone mass, and that RKT is useful for the prevention of osteoporosis.

An electronic health record (EHR)-based risk calculator can predict fractures comparably to FRAX: a proof-of-concept study

Information in the electronic health record (EHR), such as diagnoses, vital signs, utilization, medications, and laboratory values, may predict fractures well without the need to verbally ascertain risk factors. In our study, as a proof of concept, we developed and internally validated a fracture risk calculator using only information in the EHR.

PURPOSE

Fracture risk calculators, such as the Fracture Risk Assessment Tool, or FRAX, typically lie outside the clinician workflow. Conversely, the electronic health record (EHR) is at the center of the clinical workflow, and many variables in the EHR could predict fractures without having to verbally ascertain FRAX risk factors. We sought to evaluate the utility of EHR variables to predict fractures and, as a proof of concept, to create an EHR-based fracture risk model.

METHODS

Routine clinical data from 24,189 subjects presenting to primary care from 2010 to 2018 was utilized. Major osteoporotic fractures (MOFs) were captured by physician diagnosis codes. Data was split into training (n = 18,141) and test sets (n = 6048). We fit Cox regression models for candidate risk factors in the training set, and then created a global model using a backward stepwise approach. We then applied the model to the test set and compared the discrimination and calibration to FRAX.

RESULTS

We found variables related to vital signs, utilization, diagnoses, medications, and laboratory values to be associated with incident MOF. Our final model included 19 variables, including age, BMI, Parkinson's disease, chronic kidney disease, and albumin levels. When applied to the test set, we found the discrimination (AUC 0.73 vs. 0.70, p = 0.08) and calibration were comparable to FRAX.

CONCLUSION

Routinely collected data in EHR systems can generate adequate fracture predictions without the need to verbally ascertain fracture risk factors. In the future, this could allow for automated fracture prediction at the point of care to improve osteoporosis screening and treatment rates.

Generative Artificial Intelligence and Prompt Engineering: A Primer for Orthopaedic Surgeons

» Generative artificial intelligence (AI), a rapidly evolving field, has the potential to revolutionize orthopedic care by enhancing diagnostic accuracy, treatment planning, and patient management through data-driven insights and personalized strategies.» Unlike traditional AI, generative AI has the potential to generate relevant information for orthopaedic surgeons when instructed through prompts, automating tasks such as literature reviews, streamlining workflows, predicting health outcomes, and improving patient interactions.» Prompt engineering is essential for crafting effective prompts for large language models (LLMs), ensuring accurate and reliable AI-generated outputs, and promoting ethical decision-making in clinical settings.» Orthopaedic surgeons can choose between various prompt types-including open-ended, focused, and choice-based prompts-to tailor AI responses for specific clinical tasks to enhance the precision and utility of generated information.» Understanding the limitations of LLMs, such as token limits, context windows, and hallucinations, is crucial for orthopaedic surgeons to effectively use generative AI while addressing ethical concerns related to bias, privacy, and accountability.

ChatGPT Provides Unsatisfactory Responses to Frequently Asked Questions Regarding Anterior Cruciate Ligament Reconstruction

PURPOSE

To determine whether the free online artificial intelligence platform ChatGPT could accurately, adequately, and appropriately answer questions regarding anterior cruciate ligament (ACL) reconstruction surgery.

METHODS

A list of 10 questions about ACL surgery was created based on a review of frequently asked questions that appeared on websites of various orthopaedic institutions. Each question was separately entered into ChatGPT (version 3.5), and responses were recorded, scored, and graded independently by 3 authors. The reading level of the ChatGPT response was calculated using the WordCalc software package, and readability was assessed using the Flesch-Kincaid grade level, Simple Measure of Gobbledygook index, Coleman-Liau index, Gunning fog index, and automated readability index.

RESULTS

Of the 10 frequently asked questions entered into ChatGPT, 6 were deemed as unsatisfactory and requiring substantial clarification; 1, as adequate and requiring moderate clarification; 1, as adequate and requiring minor clarification; and 2, as satisfactory and requiring minimal clarification. The mean DISCERN score was 41 (inter-rater reliability, 0.721), indicating the responses to the questions were average. According to the readability assessments, a full understanding of the ChatGPT responses required 13.4 years of education, which corresponds to the reading level of a college sophomore.

CONCLUSIONS

Most of the ChatGPT-generated responses were outdated and failed to provide an adequate foundation for patients' understanding regarding their injury and treatment options. The reading level required to understand the responses was too advanced for some patients, leading to potential misunderstanding and misinterpretation of information. ChatGPT lacks the ability to differentiate and prioritize information that is presented to patients.

CLINICAL RELEVANCE

Recognizing the shortcomings in artificial intelligence platforms may equip surgeons to better set expectations and provide support for patients considering and preparing for ACL reconstruction.

Multivariable machine learning models for clinical prediction of subsequent hip fractures in older people using the Chinese population database

PURPOSE

This study aimed to develop and validate clinical prediction models using machine learning (ML) algorithms for reliable prediction of subsequent hip fractures in older individuals, who had previously sustained a first hip fracture, and facilitate early prevention and diagnosis, therefore effectively managing rapidly rising healthcare costs in China.

METHODS

Data were obtained from Grade A Tertiary hospitals for older patients (age ≥ 60 years) diagnosed with hip fractures in southwest China between 1 January 2009 and 1 April 2020. The database was built by collecting clinical and administrative data from outpatients and inpatients nationwide. Data were randomly split into training (80%) and testing datasets (20%), followed by six ML-based prediction models using 19 variables for hip fracture patients within 2 years of the first fracture.

RESULTS

A total of 40,237 patients with a median age of 66.0 years, who were admitted to acute-care hospitals for hip fractures, were randomly split into a training dataset (32,189 patients) and a testing dataset (8,048 patients). Our results indicated that three of our ML-based models delivered an excellent prediction of subsequent hip fracture outcomes (the area under the receiver operating characteristics curve: 0.92 (0.91-0.92), 0.92 (0·92-0·93), 0.92 (0·92-0·93)), outperforming previous prediction models based on claims and cohort data.

CONCLUSIONS

Our prediction models identify Chinese older people at high risk of subsequent hip fractures with specific baseline clinical and demographic variables such as length of hospital stay. These models might guide future targeted preventative treatments.

[Development of prognostic clinical and genetic models of the risk of low bone mineral density using neural network training]

BACKGROUND

Osteoporosis is a common age-related disease with disabling consequences, the early diagnosis of which is difficult due to its long and hidden course, which often leads to diagnosis only after a fracture. In this regard, great expectations are placed on advanced developments in machine learning technologies aimed at predicting osteoporosis at an early stage of development, including the use of large data sets containing information on genetic and clinical predictors of the disease. Nevertheless, the inclusion of DNA markers in prediction models is fraught with a number of difficulties due to the complex polygenic and heterogeneous nature of the disease. Currently, the predictive power of neural network models is insufficient for their incorporation into modern osteoporosis diagnostic protocols. Studies in this area are sporadic, but are widely demanded, as their results are of great importance for preventive medicine. This leads to the need to search for the most effective machine learning approaches and optimise the selection of genetic markers as input parameters to neural network models.

AIM

to evaluate the effectiveness of machine learning and neural network analysis to develop predictive risk models for osteoporosis based on clinical predictors and genetic markers of osteoporetic fractures.

MATERIALS AND METHODS

The predictive models were trained using a database of genotyping and clinical characteristics of 701 women and 501 men living in the Volga-Ural region of Russia. Anthropometric parameters, data on gender, bone mineral density level, and the results of genotyping of 152 polymorphic loci of candidate genes and replication loci of the GEFOS consortium's full genome-wide association search were included as input parameters.

RESULTS

It was found that the model for predicting low bone mineral density, including 6 polymorphic variants of the OPG gene (rs2073618, rs2073617, rs7844539, rs3102735, rs3134069) and 5 polymorphic variants of microRNA binding sites in the mRNA of genes involved in bone metabolism (COL11A1 - rs1031820, FGF2 - rs6854081, miR-146 - rs2910164, ZNF239 - rs10793442, SPARC - rs1054204 and VDR - rs11540149) (AUC=0.81 for men and AUC=0.82 for women).

CONCLUSION

The results confirm the promising application of machine learning to predict the risk of osteoporosis at the preclinical stage of the disease based on the analysis of clinical and genetic factors.

Artificial intelligence in fracture detection with different image modalities and data types: A systematic review and meta-analysis

Artificial Intelligence (AI), encompassing Machine Learning and Deep Learning, has increasingly been applied to fracture detection using diverse imaging modalities and data types. This systematic review and meta-analysis aimed to assess the efficacy of AI in detecting fractures through various imaging modalities and data types (image, tabular, or both) and to synthesize the existing evidence related to AI-based fracture detection. Peer-reviewed studies developing and validating AI for fracture detection were identified through searches in multiple electronic databases without time limitations. A hierarchical meta-analysis model was used to calculate pooled sensitivity and specificity. A diagnostic accuracy quality assessment was performed to evaluate bias and applicability. Of the 66 eligible studies, 54 identified fractures using imaging-related data, nine using tabular data, and three using both. Vertebral fractures were the most common outcome (n = 20), followed by hip fractures (n = 18). Hip fractures exhibited the highest pooled sensitivity (92%; 95% CI: 87-96, p< 0.01) and specificity (90%; 95% CI: 85-93, p< 0.01). Pooled sensitivity and specificity using image data (92%; 95% CI: 90-94, p< 0.01; and 91%; 95% CI: 88-93, p < 0.01) were higher than those using tabular data (81%; 95% CI: 77-85, p< 0.01; and 83%; 95% CI: 76-88, p < 0.01), respectively. Radiographs demonstrated the highest pooled sensitivity (94%; 95% CI: 90-96, p < 0.01) and specificity (92%; 95% CI: 89-94, p< 0.01). Patient selection and reference standards were major concerns in assessing diagnostic accuracy for bias and applicability. AI displays high diagnostic accuracy for various fracture outcomes, indicating potential utility in healthcare systems for fracture diagnosis. However, enhanced transparency in reporting and adherence to standardized guidelines are necessary to improve the clinical applicability of AI. Review Registration: PROSPERO (CRD42021240359).

AI algorithms for accurate prediction of osteoporotic fractures in patients with diabetes: an up-to-date review

Osteoporotic fractures impose a substantial burden on patients with diabetes due to their unique characteristics in bone metabolism, limiting the efficacy of conventional fracture prediction tools. Artificial intelligence (AI) algorithms have shown great promise in predicting osteoporotic fractures. This review aims to evaluate the application of traditional fracture prediction tools (FRAX, QFracture, and Garvan FRC) in patients with diabetes and osteoporosis, review AI-based fracture prediction achievements, and assess the potential efficiency of AI algorithms in this population. This comprehensive literature search was conducted in Pubmed and Web of Science. We found that conventional prediction tools exhibit limited accuracy in predicting fractures in patients with diabetes and osteoporosis due to their distinct bone metabolism characteristics. Conversely, AI algorithms show remarkable potential in enhancing predictive precision and improving patient outcomes. However, the utilization of AI algorithms for predicting osteoporotic fractures in diabetic patients is still in its nascent phase, further research is required to validate their efficacy and assess the potential advantages of their application in clinical practice.

Predictive value of machine learning on fracture risk in osteoporosis: a systematic review and meta-analysis

OBJECTIVES

Early identification of fracture risk in patients with osteoporosis is essential. Machine learning (ML) has emerged as a promising technique to predict the risk, whereas its predictive performance remains controversial. Therefore, we conducted this systematic review and meta-analysis to explore the predictive efficiency of ML for the risk of fracture in patients with osteoporosis.

METHODS

Relevant studies were retrieved from four databases (PubMed, Embase, Cochrane Library and Web of Science) until 31 May 2023. A meta-analysis of the C-index was performed using a random-effects model, while a bivariate mixed-effects model was used for the meta-analysis of sensitivity and specificity. In addition, subgroup analysis was performed according to the types of ML models and fracture sites.

RESULTS

Fifty-three studies were included in our meta-analysis, involving 15 209 268 patients, 86 prediction models specifically developed for the osteoporosis population and 41 validation sets. The most commonly used predictors in these models encompassed age, BMI, past fracture history, bone mineral density T-score, history of falls, BMD, radiomics data, weight, height, gender and other chronic diseases. Overall, the pooled C-index of ML was 0.75 (95% CI: 0.72, 0.78) and 0.75 (95% CI: 0.71, 0.78) in the training set and validation set, respectively; the pooled sensitivity was 0.79 (95% CI: 0.72, 0.84) and 0.76 (95% CI: 0.80, 0.81) in the training set and validation set, respectively; and the pooled specificity was 0.81 (95% CI: 0.75, 0.86) and 0.83 (95% CI: 0.72, 0.90) in the training set and validation set, respectively.

CONCLUSIONS

ML has a favourable predictive performance for fracture risk in patients with osteoporosis. However, most current studies lack external validation. Thus, external validation is required to verify the reliability of ML models.

PROSPERO REGISTRATION NUMBER

CRD42022346896.

Attempt to Establish Prognostic Predictive System for Hepatocellular Carcinoma Using Artificial Intelligence for Assistance with Selection of Treatment Modality

INTRODUCTION

Because of recent developments in treatments for hepatocellular carcinoma (HCC), methods for determining suitable therapy for initial or recurrent HCC have become important. This study used artificial intelligence (AI) findings to establish a system for predicting prognosis of HCC patients at time of reoccurrence based on clinical data as a reference for selection of treatment modalities.

METHODS

As a training cohort, 5,701 observations obtained at the initial and each subsequent treatment for recurrence from 1,985 HCC patients at a single center from 2000 to 2021 were used. The validation cohort included 5,692 observations from patients at multiple centers obtained at the time of the initial treatment. An AI calculating system (PRAID) was constructed based on 25 clinical factors noted at each treatment from the training cohort, and then predictive prognostic values for 1- and 3-year survival in both cohorts were evaluated.

RESULTS

After exclusion of patients lacking clinical data regarding albumin-bilirubin (ALBI) grade or tumor-node-metastasis stage of the Liver Cancer Study Group of Japan, 6th edition (TNM-LCSGJ 6th), ALBI-TNM-LCSGJ 6th (ALBI-T) and modified ALBI-T scores confirmed that prognosis for patients in both cohorts was similar. The area under the curve for prediction of both 1- and 3-year survival in the validation cohort was 0.841 (sensitivity 0.933 [95% CI: 0.925-0.940], specificity 0.517 [95% CI: 0.484-0.549]) and 0.796 (sensitivity 0.806 [95% CI: 0.790-0.821], specificity 0.646 [95% CI: 0.624-0.668]), respectively.

CONCLUSION

The present PRAID system might provide useful prognostic information related to short and medium survival for decision-making regarding the best therapeutic modality for both initial and recurrent HCC cases.

Predicting synkinesis caused by Bell's palsy or Ramsay Hunt syndrome using machine learning-based logistic regression

Objective

To investigate whether machine learning (ML)-based algorithms, namely logistic regression (LR), random forest (RF), k-nearest neighbor (k-NN), and gradient-boosting decision tree (GBDT), utilizing early post-onset parameters can predict facial synkinesis resulting from Bell's palsy or Ramsay Hunt syndrome more accurately than the conventional statistics-based LR.

Methods

This retrospective study included 362 patients who presented to a facial palsy outpatient clinic. Median follow-up of synkinesis-positive and -negative patients was 388 (range, 177-1922) and 198 (range, 190-3021) days, respectively. Electrophysiological examinations were performed, and the rate of synkinesis in Bell's palsy and Ramsay Hunt syndrome was evaluated. Sensitivity and specificity were assessed using statistics-based LR; and electroneurography (ENoG) value, the difference in the nerve excitability test (NET), and scores of the subjective Yanagihara scaling system were evaluated using early post-onset parameters with ML-based LR, RF, k-NN, and GBDT.

Results

Synkinesis rate in Bell's palsy and Ramsay Hunt syndrome was 20.2% (53/262) and 40.0% (40/100), respectively. Sensitivity and specificity obtained with statistics-based LR were 0.796 and 0.806, respectively, and the area under the receiver operating characteristic curve (AUC) was 0.87. AUCs measured using ML-based LR of "ENoG," "difference in NET," "Yanagihara," and all three components ("all") were 0.910, 0.834, 0.711, and 0.901, respectively.

Conclusion

ML-based LR model shows potential in predicting facial synkinesis probability resulting from Bell's palsy or Ramsay Hunt syndrome and has comparable reliability to the conventional statistics-based LR.

Level of Evidence

3.

Retrospective study: risk assessment model for osteoporosis-a detailed exploration involving 4,552 Shanghai dwellers

Background

Osteoporosis, a prevalent orthopedic issue, significantly influences patients' quality of life and results in considerable financial burden. The objective of this study was to develop and validate a clinical prediction model for osteoporosis risk, utilizing computer algorithms and demographic data.

Method

In this research, a total of 4,552 residents from Shanghai were retrospectively included. LASSO regression analysis was executed on the sample's basic characteristics, and logistic regression was employed for analyzing clinical characteristics and building a predictive model. The model's diagnostic capacity for predicting osteoporosis risk was assessed using R software and computer algorithms.

Results

The predictive nomogram model for bone loss risk, derived from the LASSO analysis, comprised factors including BMI, TC, TG, HDL, Gender, Age, Education, Income, Sleep, Alcohol Consumption, and Diabetes. The nomogram prediction model demonstrated impressive discriminative capability, with a C-index of 0.908 (training set), 0.908 (validation set), and 0.910 (entire cohort). The area under the ROC curve (AUC) of the model was 0.909 (training set), 0.903 (validation set), and applicable to the entire cohort. The decision curve analysis further corroborated that the model could efficiently predict the risk of bone loss in patients.

Conclusion

The nomogram, based on essential demographic and health factors (Body Mass Index, Total Cholesterol, Triglycerides, High-Density Lipoprotein, Gender, Age, Education, Income, Sleep, Alcohol Consumption, and Diabetes), offered accurate predictions for the risk of bone loss within the studied population.

Advantages and Disadvantages of Random Forest Models for Prediction of Hip Fracture Risk Versus Mortality Risk in the Oldest Old

Targeted fracture prevention strategies among late-life adults should balance fracture risk versus competing mortality risk. Models have previously been constructed using Fine-Gray subdistribution methods. We used a machine learning method adapted for competing risk survival time to evaluate candidate risk factors and create models for hip fractures and competing mortality among men and women aged 80 years and older using data from three prospective cohorts (Study of Osteoporotic Fractures [SOF], Osteoporotic Fracture in Men study [MrOS], Health Aging and Body Composition study [HABC]). Random forest competing risk models were used to estimate absolute 5-year risk of hip fracture and absolute 5-year risk of competing mortality (excluding post-hip fracture deaths). Models were constructed for both outcomes simultaneously; minimal depth was used to rank and select variables for smaller models. Outcome specific models were constructed; variable importance was used to rank and select variables for inclusion in smaller random forest models. Random forest models were compared to simple Fine-Gray models with six variables selected a priori. Top variables for competing risk random forests were frailty and related components in men while top variables were age, bone mineral density (BMD) (total hip, femoral neck), and frailty components in women. In both men and women, outcome specific rankings strongly favored BMD variables for hip fracture prediction while frailty and components were strongly associated with competing mortality. Model discrimination for random forest models varied from 0.65 for mortality in women to 0.81 for hip fracture in men and depended on model choice and variables included. Random models performed slightly better than simple Fine-Gray model for prediction of competing mortality, but similarly for prediction of hip fractures. Random forests can be used to estimate risk of hip fracture and competing mortality among the oldest old. Modest gains in performance for mortality without hip fracture compared to Fine-Gray models must be weighed against increased complexity. © 2023 The Authors. JBMR Plus published by Wiley Periodicals LLC on behalf of American Society for Bone and Mineral Research. This article has been contributed to by U.S. Government employees and their work is in the public domain in the USA.

Effect of Artificial Intelligence or Machine Learning on Prediction of Hip Fracture Risk: Systematic Review

BACKGROUND

Dual energy X-ray absorptiometry (DXA) is a preferred modality for screening or diagnosis of osteoporosis and can predict the risk of hip fracture. However, the DXA test is difficult to implement easily in some developing countries, and fractures have been observed before patients underwent DXA. The purpose of this systematic review is to search for studies that predict the risk of hip fracture using artificial intelligence (AI) or machine learning, organize the results of each study, and analyze the usefulness of this technology.

METHODS

The PubMed, OVID Medline, Cochrane Collaboration Library, Web of Science, EMBASE, and AHRQ databases were searched including "hip fractures" AND "artificial intelligence".

RESULTS

A total of 7 studies are included in this study. The total number of subjects included in the 7 studies was 330,099. There were 3 studies that included only women, and 4 studies included both men and women. One study conducted AI training after 1:1 matching between fractured and non-fractured patients. The area under the curve of AI prediction model for hip fracture risk was 0.39 to 0.96. The accuracy of AI prediction model for hip fracture risk was 70.26% to 90%.

CONCLUSIONS

We believe that predicting the risk of hip fracture by the AI model will help select patients with high fracture risk among osteoporosis patients. However, to apply the AI model to the prediction of hip fracture risk in clinical situations, it is necessary to identify the characteristics of the dataset and AI model and use it after performing appropriate validation.

Artificial intelligence and ChatGPT in Orthopaedics and sports medicine

Artificial intelligence (AI) is looked upon nowadays as the potential major catalyst for the fourth industrial revolution. In the last decade, AI use in Orthopaedics increased approximately tenfold. Artificial intelligence helps with tracking activities, evaluating diagnostic images, predicting injury risk, and several other uses. Chat Generated Pre-trained Transformer (ChatGPT), which is an AI-chatbot, represents an extremely controversial topic in the academic community. The aim of this review article is to simplify the concept of AI and study the extent of AI use in Orthopaedics and sports medicine literature. Additionally, the article will also evaluate the role of ChatGPT in scientific research and publications.Level of evidence: Level V, letter to review.

Machine learning algorithms for diagnosis of hip bone osteoporosis: a systematic review and meta-analysis study

BACKGROUND

Osteoporosis is a significant health problem in the skeletal system, associated with bone tissue changes and its strength. Machine Learning (ML), on the other hand, has been accompanied by improvements in recent years and has been in the spotlight. This study is designed to investigate the Diagnostic Test Accuracy (DTA) of ML to detect osteoporosis through the hip dual-energy X-ray absorptiometry (DXA) images.

METHODS

The ISI Web of Science, PubMed, Scopus, Cochrane Library, IEEE Xplore Digital Library, CINAHL, Science Direct, PROSPERO, and EMBASE were systematically searched until June 2023 for studies that tested the diagnostic precision of ML model-assisted for predicting an osteoporosis diagnosis.

RESULTS

The pooled sensitivity of univariate analysis of seven studies was 0.844 (95% CI 0.791 to 0.885, I2 = 94% for 7 studies). The pooled specificity of univariate analysis was 0.781 (95% CI 0.732 to 0.824, I2 = 98% for 7 studies). The pooled diagnostic odds ratio (DOR) was 18.91 (95% CI 14.22 to 25.14, I2 = 93% for 7 studies). The pooled mean positive likelihood ratio (LR+) and the negative likelihood ratio (LR-) were 3.7 and 0.22, respectively. Also, the summary receiver operating characteristics (sROC) of the bivariate model has an AUC of 0.878.

CONCLUSION

Osteoporosis can be diagnosed by ML with acceptable accuracy, and hip fracture prediction was improved via training in an Architecture Learning Network (ALN).

Development and validation of sex-specific hip fracture prediction models using electronic health records: a retrospective, population-based cohort study

BACKGROUND

Hip fracture is associated with immobility, morbidity, mortality, and high medical cost. Due to limited availability of dual-energy X-ray absorptiometry (DXA), hip fracture prediction models without using bone mineral density (BMD) data are essential. We aimed to develop and validate 10-year sex-specific hip fracture prediction models using electronic health records (EHR) without BMD.

METHODS

In this retrospective, population-based cohort study, anonymized medical records were retrieved from the Clinical Data Analysis and Reporting System for public healthcare service users in Hong Kong aged ≥60 years as of 31 December 2005. A total of 161,051 individuals (91,926 female; 69,125 male) with complete follow-up from 1 January 2006 till the study end date on 31 December 2015 were included in the derivation cohort. The sex-stratified derivation cohort was randomly divided into 80% training and 20% internal testing datasets. An independent validation cohort comprised 3046 community-dwelling participants aged ≥60 years as of 31 December 2005 from the Hong Kong Osteoporosis Study, a prospective cohort which recruited participants between 1995 and 2010. With 395 potential predictors (age, diagnosis, and drug prescription records from EHR), 10-year sex-specific hip fracture prediction models were developed using stepwise selection by logistic regression (LR) and four machine learning (ML) algorithms (gradient boosting machine, random forest, eXtreme gradient boosting, and single-layer neural networks) in the training cohort. Model performance was evaluated in both internal and independent validation cohorts.

FINDINGS

In female, the LR model had the highest AUC (0.815; 95% Confidence Interval [CI]: 0.805-0.825) and adequate calibration in internal validation. Reclassification metrics showed the LR model had better discrimination and classification performance than the ML algorithms. Similar performance was attained by the LR model in independent validation, with high AUC (0.841; 95% CI: 0.807-0.87) comparable to other ML algorithms. In internal validation for male, LR model had high AUC (0.818; 95% CI: 0.801-0.834) and it outperformed all ML models as indicated by reclassification metrics, with adequate calibration. In independent validation, the LR model had high AUC (0.898; 95% CI: 0.857-0.939) comparable to ML algorithms. Reclassification metrics demonstrated that LR model had the best discrimination performance.

INTERPRETATION

Even without using BMD data, the 10-year hip fracture prediction models developed by conventional LR had better discrimination performance than the models developed by ML algorithms. Upon further validation in independent cohorts, the LR models could be integrated into the routine clinical workflow, aiding the identification of people at high risk for DXA scan.

FUNDING

Health and Medical Research Fund, Health Bureau, Hong Kong SAR Government (reference: 17181381).

Machine learning applied to HR-pQCT images improves fracture discrimination provided by DXA and clinical risk factors

BACKGROUND

Traditional analysis of High Resolution peripheral Quantitative Computed Tomography (HR-pQCT) images results in a multitude of cortical and trabecular parameters which would be potentially cumbersome to interpret for clinicians compared to user-friendly tools utilising clinical parameters. A computer vision approach (by which the entire scan is 'read' by a computer algorithm) to ascertain fracture risk, would be far simpler. We therefore investigated whether a computer vision and machine learning technique could improve upon selected clinical parameters in assessing fracture risk.

METHODS

Participants of the Hertfordshire Cohort Study (HCS) attended research visits at which height and weight were measured; fracture history was determined via self-report and vertebral fracture assessment. Bone microarchitecture was assessed via HR-pQCT scans of the non-dominant distal tibia (Scanco XtremeCT), and bone mineral density measurement and lateral vertebral assessment were performed using dual-energy X-ray absorptiometry (DXA) (Lunar Prodigy Advanced). Images were cropped, pre-processed and texture analysis was performed using a three-dimensional local binary pattern method. These image data, together with age, sex, height, weight, BMI, dietary calcium and femoral neck BMD, were used in a random-forest classification algorithm. Receiver operating characteristic (ROC) analysis was used to compare fracture risk identification methods.

RESULTS

Overall, 180 males and 165 females were included in this study with a mean age of approximately 76 years and 97 (28 %) participants had sustained a previous fracture. Using clinical risk factors alone resulted in an area under the curve (AUC) of 0.70 (95 % CI: 0.56-0.84), which improved to 0.71 (0.57-0.85) with the addition of DXA-measured BMD. The addition of HR-pQCT image data to the machine learning classifier with clinical risk factors and DXA-measured BMD as inputs led to an improved AUC of 0.90 (0.83-0.96) with a sensitivity of 0.83 and specificity of 0.74.

CONCLUSION

These results suggest that using a three-dimensional computer vision method to HR-pQCT scanning may enhance the identification of those at risk of fracture beyond that afforded by clinical risk factors and DXA-measured BMD. This approach has the potential to make the information offered by HR-pQCT more accessible (and therefore) applicable to healthcare professionals in the clinic if the technology becomes more widely available.

Screening for Osteoporosis from Blood Test Data in Elderly Women Using a Machine Learning Approach

The diagnosis of osteoporosis is made by measuring bone mineral density (BMD) using dual-energy X-ray absorptiometry (DXA). Machine learning, one of the artificial intelligence methods, was used to predict low BMD without using DXA in elderly women. Medical records from 2541 females who visited the osteoporosis clinic were used in this study. As hyperparameters for machine learning, patient age, body mass index (BMI), and blood test data were used. As machine learning models, logistic regression, decision tree, random forest, gradient boosting trees, and lightGBM were used. Each model was trained to classify and predict low-BMD patients. The model performance was compared using a confusion matrix. The accuracy of each trained model was 0.772 in logistic regression, 0.739 in the decision tree, 0.775 in the random forest, 0.800 in gradient boosting, and 0.834 in lightGBM. The area under the curve (AUC) was 0.595 in the decision tree, 0.673 in logistic regression, 0.699 in the random forest, 0.840 in gradient boosting, and 0.961, which was the highest, in the lightGBM model. Important features were BMI, age, and the number of platelets. Shapley additive explanation scores in the lightGBM model showed that BMI, age, and ALT were ranked as important features. Among several machine learning models, the lightGBM model showed the best performance in the present research.

Bone Mineral Density Prediction from CT Image: A Novel Approach using ANN

Background

Though treatable, osteoporosis continues as a substantially underdiagnosed and undertreated condition. Bone mineral density (BMD) monitoring will definitely aid in the prediction and prevention of medical emergencies arising from osteoporosis. Although quantitative computed tomography (QCT) is one of the most widely accepted tools for measuring BMD, it lacks the contribution of bone architecture in predicting BMD, which is significant as aging progresses. This paper presents an innovative approach for the prediction of BMD incorporating bone architecture that involves no extra cost, time, and exposure to severe radiation.

Methods

In this approach, the BMD is predicted using clinical CT scan images taken for other indications based on image processing and artificial neural network (ANN). The network used in this study is a standard backpropagation neural network having five input neurons with one hidden layer having 40 neurons with a tan-sigmoidal activation function. The Digital Imaging and Communications in Medicine (DICOM) image properties extracted from QCT of human skull and femur bone of rabbit that are closely associated with the BMD are used as input parameters of the ANN. The density value of the bone which is computed from the Hounsfield units of QCT scan image through phantom calibration is used as the target value for training the network.

Results

The ANN model predicts the density values using the image properties from the clinical CT of the same rabbit femur bone and is compared with the density value computed from QCT scan. The correlation coefficient between predicted BMD and QCT density valued to 0.883. The proposed network can assist clinicians in identifying early stage of osteoporosis and devise suitable strategies to improve BMD with no additional cost.

Applying machine learning methods to predict the hospital re-admission within 30 days of total hip arthroplasty and hemiarthroplasty

BACKGROUND

Total hip arthroplasty (THA) and hemiarthroplasty are common treatments for severe hip joint disease. To predict the probability of re-admission after discharge when patients are hospitalized will support providing appropriate health education and guidance.

METHODS

The research aims to use logistic regression (LR), decision trees (DT), random forests (RF), and artificial neural networks (ANN) to establish predictive models and compare their performances on re-admissions within 30 days after THA or hemiarthroplasty. The data of this study includes patient demographics, physiological measurements, disease history, and clinical laboratory test results.

RESULTS

There were 508 and 309 patients in the THA and hemiarthroplasty studies respectively from September 2016 to December 2018. The accuracies of the four models LR, DT, RF, and ANN in the THA experiment are 94.3%, 93.2%, 97.3%, and 93.9%, respectively. In the hemiarthroplasty experiment, the accuracies of the four models are 92.4%, 86.1%, 94.2%, and 94.8%, respectively. Among these, we found that the RF model has the best sensitivity and ANN model has the best area under the receiver operating characteristic (AUROC) score in both experiments.

CONCLUSIONS

The THA experiment confirmed that the performance of the RF model is better than the other models. The key factors affecting the prognosis after THA surgery are creatinine, sodium, anesthesia duration, and dialysis. In the hemiarthroplasty experiment, the ANN model showed more accurate results. Poor kidney function increases the risk of hospital re-admission. This research highlights that RF and ANN model perform well on the hip replacement surgery outcome prediction.

Potential of Health Insurance Claims Data to Predict Fractures in Older Adults: A Prospective Cohort Study

Purpose

In older adults, fractures are associated with mortality, disability, loss of independence and high costs. Knowledge on their predictors can help to identify persons at high risk who may benefit from measures to prevent fractures. We aimed to assess the potential of German claims data to predict fractures in older adults.

Patients and Methods

Using the German Pharmacoepidemiological Research Database (short GePaRD; claims data from ~20% of the German population), we included persons aged ≥65 years with at least one year of continuous insurance coverage and no fractures prior to January 1, 2017 (baseline). We randomly divided the study population into a training (80%) and a test sample (20%) and used logistic regression and random forest models to predict the risk of fractures within one year after baseline based on different combinations of potential predictors.

Results

Among 2,997,872 persons (56% female), the incidence per 10,000 person years of any fracture in women increased from 133 in age group 65–74 years (men: 71) to 583 in age group 85+ (men: 332). The maximum predictive performance as measured by the area under the curve (AUC) across models was 0.63 in men and 0.60 in women and was achieved by combining information on drugs and morbidities. AUCs were lowest in age group 85+.

Conclusion

Our study showed that the performance of models using German claims data to predict the risk of fractures in older adults is moderate. Given that the models used data readily available to health insurance providers in Germany, it may still be worthwhile to explore the cost–benefit ratio of interventions aiming to reduce the risk of fractures based on such prediction models in certain risk groups.

Can machine learning predict pharmacotherapy outcomes? An application study in osteoporosis

BACKGROUND AND OBJECTIVE

The specific aim of this study is to develop machine learning models as a clinical approach for personalized treatment of osteoporosis. The model performance on outcome prediction was compared between four machine learning algorithms.

METHODS

Retrospective, electronic clinical data for patients with suspected or confirmed osteoporosis treated at Wan Fang Hospital between 2011 to 2018 were used as inputs for building the following predictive machine learning models,i.e., artificial neural network (ANN), random forest (RF), support vector machine (SVM) and logistic regression (LR) models. The predicted outcome was defined as an increase/decrease in T-score after treatment. A genetic algorithm was employed to select relevant variables as input features for each model; the leave-one-out method was applied for model building and internal validation. The model with best performance was selected by a separate set of testing. Area under the receiver operating characteristic curve, accuracy, precision, sensitivity and F1 score were calculated to evaluate model performance. Main analysis for all the patients with subclinical or confirmed osteoporosis and subgroup analysis for the patients with confirmed osteoporosis (T score < -2.5) were carried out in this study.

RESULTS

A genetic algorithm was employed to select 12 to 18 features from all 33 variables for the four models. No difference was found in accuracy (ANN, 71.7%; LR, 70.0%; RF, 75.0%; SVM, 66.7%), precision (ANN, 80.0%; LR, 59.3%; RF, 70.0%; SVM, 63.6%), and AUC (ANN, 0.709; LR, 0.731; RF, 0.719; SVM, 0.702) among the ANN, LR, RF and SVM models. Main analysis in performance revealed significant recall in the LR model, as compared to ANN and SVM model; while subgroup revealed significant recall in ANN model, compared to LR and SVM model.

CONCLUSIONS

Machine learning-based models hold potential in forecasting the outcomes of treatment for osteoporosis via early initiation of first-line therapy for patients with subclinical disease; or a switch to second-line treatment for patients with a high risk of impending treatment failure. This convenient approach can assist clinicians in adjusting treatment tailored to individual patient for prevention of disease progression or ineffective therapy.

[Artificial intelligence and novel approaches for treatment of non-union in bone : From established standard methods in medicine up to novel fields of research]

Methods of artificial intelligence (AI) have found applications in many fields of medicine within the last few years. Some disciplines already use these methods regularly within their clinical routine. However, the fields of application are wide and there are still many opportunities to apply these new AI concepts. This review article gives an insight into the history of AI and defines the special terms and fields, such as machine learning (ML), neural networks and deep learning. The classical steps in developing AI models are demonstrated here, as well as the iteration of data rectification and preparation, the training of a model and subsequent validation before transfer into a clinical setting are explained. Currently, musculoskeletal disciplines implement methods of ML and also neural networks, e.g. for identification of fractures or for classifications. Also, predictive models based on risk factor analysis for prevention of complications are being initiated. As non-union in bone is a rare but very complex disease with dramatic socioeconomic impact for the healthcare system, many open questions arise which could be better understood by using methods of AI in the future. New fields of research applying AI models range from predictive models and cost analysis to personalized treatment strategies.

Prediction Models for Osteoporotic Fractures Risk: A Systematic Review and Critical Appraisal

Osteoporotic fractures (OF) are a global public health problem currently. Many risk prediction models for OF have been developed, but their performance and methodological quality are unclear. We conducted this systematic review to summarize and critically appraise the OF risk prediction models. Three databases were searched until April 2021. Studies developing or validating multivariable models for OF risk prediction were considered eligible. Used the prediction model risk of bias assessment tool to appraise the risk of bias and applicability of included models. All results were narratively summarized and described. A total of 68 studies describing 70 newly developed prediction models and 138 external validations were included. Most models were explicitly developed (n=31, 44%) and validated (n=76, 55%) only for female. Only 22 developed models (31%) were externally validated. The most validated tool was Fracture Risk Assessment Tool. Overall, only a few models showed outstanding (n=3, 1%) or excellent (n=32, 15%) prediction discrimination. Calibration of developed models (n=25, 36%) or external validation models (n=33, 24%) were rarely assessed. No model was rated as low risk of bias, mostly because of an insufficient number of cases and inappropriate assessment of calibration. There are a certain number of OF risk prediction models. However, few models have been thoroughly internally validated or externally validated (with calibration being unassessed for most of the models), and all models showed methodological shortcomings. Instead of developing completely new models, future research is suggested to validate, improve, and analyze the impact of existing models.

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

The Fracture Risk Assessment Tool (FRAX) is a computational tool developed to predict the 10-year probability of hip fracture and major osteoporotic fracture based on inputs of patient characteristics, bone mineral density (BMD), and a set of seven clinical risk factors. While the FRAX tool is widely available and clinically validated, its underlying algorithm is not public. The relative contribution and necessity of each input parameter to the final FRAX score is unknown. We systematically collected hip fracture risk scores from the online FRAX calculator for osteopenic Caucasian women across 473,088 unique inputs. This dataset was used to dissect the FRAX algorithm and construct a reverse-engineered fracture risk model to assess the relative contribution of each input variable. Within the reverse-engineered model, age and T-Score were the strongest contributors to hip fracture risk, while BMI had marginal contribution. Of the clinical risk factors, parent history of fracture and ongoing glucocorticoid treatment had the largest additive effect on risk score. A generalized linear model largely recapitulated the FRAX tool with an R2 of 0.91. Observed effect sizes were then compared to a true patient population by creating a logistic regression model of the Study of Osteoporotic Fractures (SOF) cohort, which closely paralleled the effect sizes seen in the reverse-engineered fracture risk model. Analysis identified several clinically relevant observations of interest to FRAX users. The role of major osteoporotic fracture risk prediction in contributing to an indication of treatment need is very narrow, as the hip fracture risk prediction accounted for 98% of treatment indications for the SOF cohort. Removing any risk factor from the model substantially decreased its accuracy and confirmed that more parsimonious models are not ideal for fracture prediction. For women 65 years and older with a previous fracture, 98% of FRAX combinations exceeded the treatment threshold, regardless of T-score or other factors. For women age 70+ with a parent history of fracture, 99% of FRAX combinations exceed the treatment threshold. Based on these analyses, we re-affirm the efficacy of the FRAX as the best tool for fracture risk assessment and provide deep insight into the interplay between risk factors.

Implementation of a machine learning application in preoperative risk assessment for hip repair surgery

Background

This study aims to develop a machine learning-based application in a real-world medical domain to assist anesthesiologists in assessing the risk of complications in patients after a hip surgery.

Methods

Data from adult patients who underwent hip repair surgery at Chi-Mei Medical Center and its 2 branch hospitals from January 1, 2013, to March 31, 2020, were analyzed. Patients with incomplete data were excluded. A total of 22 features were included in the algorithms, including demographics, comorbidities, and major preoperative laboratory data from the database. The primary outcome was a composite of adverse events (in-hospital mortality, acute myocardial infarction, stroke, respiratory, hepatic and renal failure, and sepsis). Secondary outcomes were intensive care unit (ICU) admission and prolonged length of stay (PLOS). The data obtained were imported into 7 machine learning algorithms to predict the risk of adverse outcomes. Seventy percent of the data were randomly selected for training, leaving 30% for testing. The performances of the models were evaluated by the area under the receiver operating characteristic curve (AUROC). The optimal algorithm with the highest AUROC was used to build a web-based application, then integrated into the hospital information system (HIS) for clinical use.

Results

Data from 4,448 patients were analyzed; 102 (2.3%), 160 (3.6%), and 401 (9.0%) patients had primary composite adverse outcomes, ICU admission, and PLOS, respectively. Our optimal model had a superior performance (AUROC by DeLong test) than that of ASA-PS in predicting the primary composite outcomes (0.810 vs. 0.629, p < 0.01), ICU admission (0.835 vs. 0.692, p < 0.01), and PLOS (0.832 vs. 0.618, p < 0.01).

Conclusions

The hospital-specific machine learning model outperformed the ASA-PS in risk assessment. This web-based application gained high satisfaction from anesthesiologists after online use.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12871-022-01648-y.

Finite element derived femoral strength is a better predictor of hip fracture risk than aBMD in the AGES Reykjavik study cohort

Hip fractures associated with a high economic burden, loss of independence, and a high rate of post-fracture mortality, are a major health concern for modern societies. Areal bone mineral density is the current clinical metric of choice when assessing an individual's future risk of fracture. However, this metric has been shown to lack sensitivity and specificity in the targeted selection of individuals for preventive interventions. Although femoral strength derived from computed tomography based finite element models has been proposed as an alternative based on its superior femoral strength prediction ex vivo, such predictions have only shown marginal or no improvement for assessing hip fracture risk. This study compares finite element derived femoral strength to aBMD as a metric for hip fracture risk assessment in subjects (N = 601) from the AGES Reykjavik Study cohort and analyses the dependence of femoral strength predictions and classification accuracy on the material model and femoral loading alignment. We found hip fracture classification based on finite element derived femoral strength to be significantly improved compared to aBMD. Finite element models with non-linear material models performed better at classifying hip fractures compared to finite element models with linear material models and loading alignments with low internal rotation and adduction, which do not correspond to weak femur alignments, were found to be most suitable for hip fracture classification.

Conceptual design of the dual X-ray absorptiometry health informatics prediction system for osteoporosis care

Osteoporotic fractures are a major and growing public health problem, which is strongly associated with other illnesses and multi-morbidity. Big data analytics has the potential to improve care for osteoporotic fractures and other non-communicable diseases (NCDs), reduces healthcare costs and improves healthcare decision-making for patients with multi-disorders. However, robust and comprehensive utilization of healthcare big data in osteoporosis care practice remains unsatisfactory. In this paper, we present a conceptual design of an intelligent analytics system, namely, the dual X-ray absorptiometry (DXA) health informatics prediction (HIP) system, for healthcare big data research and development. Comprising data source, extraction, transformation, loading, modelling and application, the DXA HIP system was applied in an osteoporosis healthcare context for fracture risk prediction and the investigation of multi-morbidity risk. Data was sourced from four DXA machines located in three healthcare centres in Ireland. The DXA HIP system is novel within the Irish context as it enables the study of fracture-related issues in a larger and more representative Irish population than previous studies. We propose this system is applicable to investigate other NCDs which have the potential to improve the overall quality of patient care and substantially reduce the burden and cost of all NCDs.

Artificial Neural Networks Predict 30-Day Mortality After Hip Fracture: Insights From Machine Learning

OBJECTIVES

Accurately stratifying patients in the preoperative period according to mortality risk informs treatment considerations and guides adjustments to bundled reimbursements. We developed and compared three machine learning models to determine which best predicts 30-day mortality after hip fracture.

METHODS

The 2016 to 2017 National Surgical Quality Improvement Program for hip fracture (AO/OTA 31-A-B-C) procedure-targeted data were analyzed. Three models-artificial neural network, naive Bayes, and logistic regression-were trained and tested using independent variables selected via backward variable selection. The data were split into 80% training and 20% test sets. Predictive accuracy between models was evaluated using area under the curve receiver operating characteristics. Odds ratios were determined using multivariate logistic regression with P < 0.05 for significance.

RESULTS

The study cohort included 19,835 patients (69.3% women). The 30-day mortality rate was 5.3%. In total, 47 independent patient variables were identified to train the testing models. Area under the curve receiver operating characteristics for 30-day mortality was highest for artificial neural network (0.92), followed by the logistic regression (0.87) and naive Bayes models (0.83).

DISCUSSION

Machine learning is an emerging approach to develop accurate risk calculators that account for the weighted interactions between variables. In this study, we developed and tested a neural network model that was highly accurate for predicting 30-day mortality after hip fracture. This was superior to the naive Bayes and logistic regression models. The role of machine learning models to predict orthopaedic outcomes merits further development and prospective validation but shows strong promise for positively impacting patient care.

Identifying the predictive effectiveness of a genetic risk score for incident hypertension using machine learning methods among populations in rural China

Current studies have shown the controversial effect of genetic risk scores (GRSs) in hypertension prediction. Machine learning methods are used extensively in the medical field but rarely in the mining of genetic information. This study aims to determine whether genetic information can improve the prediction of incident hypertension using machine learning approaches in a prospective study. The study recruited 4592 subjects without hypertension at baseline from a cohort study conducted in rural China. A polygenic risk score (PGGRS) was calculated using 13 SNPs. According to a ratio of 7:3, subjects were randomly allocated to the train and test datasets. Models with and without the PGGRS were established using the train dataset with Cox regression, artificial neural network (ANN), random forest (RF), and gradient boosting machine (GBM) methods. The discrimination and reclassification of models were estimated using the test dataset. The PGGRS showed a significant association with the risk of incident hypertension (HR (95% CI), 1.046 (1.004, 1.090), P = 0.031) irrespective of baseline blood pressure. Models that did not include the PGGRS achieved AUCs (95% CI) of 0.785 (0.763, 0.807), 0.790 (0.768, 0.811), 0.838 (0.817, 0.857), and 0.854 (0.835, 0.873) for the Cox, ANN, RF, and GBM methods, respectively. The addition of the PGGRS led to the improvement of the AUC by 0.001, 0.008, 0.023, and 0.017; IDI by 1.39%, 2.86%, 4.73%, and 4.68%; and NRI by 25.05%, 13.01%, 44.87%, and 22.94%, respectively. Incident hypertension risk was better predicted by the traditional+PGGRS model, especially when machine learning approaches were used, suggesting that genetic information may have the potential to identify new hypertension cases using machine learning methods in resource-limited areas. CLINICAL TRIAL REGISTRATION: The Henan Rural Cohort Study has been registered at the Chinese Clinical Trial Register (Registration number: ChiCTR-OOC-15006699). http://www.chictr.org.cn/showproj.aspx?proj=11375 .

Machine Learning Can Improve Clinical Detection of Low BMD: The DXA-HIP Study

BACKGROUND

Identification of those at high risk before a fracture occurs is an essential part of osteoporosis management. This topic remains a significant challenge for researchers in the field, and clinicians worldwide. Although many algorithms have been developed to either identify those with a diagnosis of osteoporosis or predict their risk of fracture, concern remains regarding their accuracy and application. Scientific advances including machine learning methods are rapidly gaining appreciation as alternative techniques to develop or enhance risk assessment and current practice. Recent evidence suggests that these methods could play an important role in the assessment of osteoporosis and fracture risk.

METHODS

Data used for this study included Dual-energy X-ray Absorptiometry (DXA) bone mineral density and T-scores, and multiple clinical variables drawn from a convenience cohort of adult patients scanned on one of 4 DXA machines across three hospitals in the West of Ireland between January 2000 and November 2018 (the DXA-Heath Informatics Prediction Cohort). The dataset was cleaned, validated and anonymized, and then split into an exploratory group (80%) and a development group (20%) using the stratified sampling method. We first established the validity of a simple tool, the Osteoporosis Self-assessment Tool Index (OSTi) to identify those classified as osteoporotic by the modified International Society for Clinical Densitometry DXA criteria. We then compared these results to seven machine learning techniques (MLTs): CatBoost, eXtreme Gradient Boosting, Neural network, Bagged flexible discriminant analysis, Random forest, Logistic regression and Support vector machine to enhance the discrimination of those classified as osteoporotic or not. The performance of each prediction model was measured by calculating the area under the curve (AUC) with 95% confidence interval (CI), and was compared against the OSTi.

RESULTS

A cohort of 13,577 adults aged ≥40 yr at the age of their first scan was identified including 11,594 women and 1983 men. 2102 (18.13%) females and 356 (17.95%) males were identified with osteoporosis based on their lowest T-score. The OSTi performed well in our cohort in both men (AUC 0.723, 95% CI 0.659-0.788) and women (AUC 0.810, 95% CI 0.787-0.833). Four MLTs improved discrimination in both men and women, though the incremental benefit was small. eXtreme Gradient Boosting showed the most promising results: +4.5% (AUC 0.768, 95% CI 0.706-0.829) for men and +2.3% (AUC 0.833, 95% CI 0.812-0.853) for women. Similarly MLTs outperformed OSTi in sensitivity analyses-which excluded those subjects taking osteoporosis medications-though the absolute improvements differed.

CONCLUSION

The OSTi retains an important role in identifying older men and women most likely to have osteoporosis by bone mineral density classification. MLTs could improve DXA detection of osteoporosis classification in older men and women. Further exploration of MLTs is warranted in other populations, and with additional data.

Applications of Machine Learning in Bone and Mineral Research

In this unprecedented era of the overwhelming volume of medical data, machine learning can be a promising tool that may shed light on an individualized approach and a better understanding of the disease in the field of osteoporosis research, similar to that in other research fields. This review aimed to provide an overview of the latest studies using machine learning to address issues, mainly focusing on osteoporosis and fractures. Machine learning models for diagnosing and classifying osteoporosis and detecting fractures from images have shown promising performance. Fracture risk prediction is another promising field of research, and studies are being conducted using various data sources. However, these approaches may be biased due to the nature of the techniques or the quality of the data. Therefore, more studies based on the proposed guidelines are needed to improve the technical feasibility and generalizability of artificial intelligence algorithms.

Machine learning in orthopaedic surgery

Artificial intelligence and machine learning in orthopaedic surgery has gained mass interest over the last decade or so. In prior studies, researchers have demonstrated that machine learning in orthopaedics can be used for different applications such as fracture detection, bone tumor diagnosis, detecting hip implant mechanical loosening, and grading osteoarthritis. As time goes on, the utility of artificial intelligence and machine learning algorithms, such as deep learning, continues to grow and expand in orthopaedic surgery. The purpose of this review is to provide an understanding of the concepts of machine learning and a background of current and future orthopaedic applications of machine learning in risk assessment, outcomes assessment, imaging, and basic science fields. In most cases, machine learning has proven to be just as effective, if not more effective, than prior methods such as logistic regression in assessment and prediction. With the help of deep learning algorithms, such as artificial neural networks and convolutional neural networks, artificial intelligence in orthopaedics has been able to improve diagnostic accuracy and speed, flag the most critical and urgent patients for immediate attention, reduce the amount of human error, reduce the strain on medical professionals, and improve care. Because machine learning has shown diagnostic and prognostic uses in orthopaedic surgery, physicians should continue to research these techniques and be trained to use these methods effectively in order to improve orthopaedic treatment.

Development of Machine Learning Models for Prediction of Osteoporosis from Clinical Health Examination Data

Osteoporosis is treatable but often overlooked in clinical practice. We aimed to construct prediction models with machine learning algorithms to serve as screening tools for osteoporosis in adults over fifty years old. Additionally, we also compared the performance of newly developed models with traditional prediction models. Data were acquired from community-dwelling participants enrolled in health checkup programs at a medical center in Taiwan. A total of 3053 men and 2929 women were included. Models were constructed for men and women separately with artificial neural network (ANN), support vector machine (SVM), random forest (RF), k-nearest neighbor (KNN), and logistic regression (LoR) to predict the presence of osteoporosis. Area under receiver operating characteristic curve (AUROC) was used to compare the performance of the models. We achieved AUROC of 0.837, 0.840, 0.843, 0.821, 0.827 in men, and 0.781, 0.807, 0.811, 0.767, 0.772 in women, for ANN, SVM, RF, KNN, and LoR models, respectively. The ANN, SVM, RF, and LoR models in men, and the ANN, SVM, and RF models in women performed significantly better than the traditional Osteoporosis Self-Assessment Tool for Asians (OSTA) model. We have demonstrated that machine learning algorithms improve the performance of screening for osteoporosis. By incorporating the models in clinical practice, patients could potentially benefit from earlier diagnosis and treatment of osteoporosis.

Machine Learning Solutions for Osteoporosis-A Review

Osteoporosis and its clinical consequence, bone fracture, is a multifactorial disease that has been the object of extensive research. Recent advances in machine learning (ML) have enabled the field of artificial intelligence (AI) to make impressive breakthroughs in complex data environments where human capacity to identify high-dimensional relationships is limited. The field of osteoporosis is one such domain, notwithstanding technical and clinical concerns regarding the application of ML methods. This qualitative review is intended to outline some of these concerns and to inform stakeholders interested in applying AI for improved management of osteoporosis. A systemic search in PubMed and Web of Science resulted in 89 studies for inclusion in the review. These covered one or more of four main areas in osteoporosis management: bone properties assessment (n = 13), osteoporosis classification (n = 34), fracture detection (n = 32), and risk prediction (n = 14). Reporting and methodological quality was determined by means of a 12-point checklist. In general, the studies were of moderate quality with a wide range (mode score 6, range 2 to 11). Major limitations were identified in a significant number of studies. Incomplete reporting, especially over model selection, inadequate splitting of data, and the low proportion of studies with external validation were among the most frequent problems. However, the use of images for opportunistic osteoporosis diagnosis or fracture detection emerged as a promising approach and one of the main contributions that ML could bring to the osteoporosis field. Efforts to develop ML-based models for identifying novel fracture risk factors and improving fracture prediction are additional promising lines of research. Some studies also offered insights into the potential for model-based decision-making. Finally, to avoid some of the common pitfalls, the use of standardized checklists in developing and sharing the results of ML models should be encouraged. © 2021 American Society for Bone and Mineral Research (ASBMR).

Comparing three machine learning approaches to design a risk assessment tool for future fractures: predicting a subsequent major osteoporotic fracture in fracture patients with osteopenia and osteoporosis

Four machine learning models were developed and compared to predict the risk of a future major osteoporotic fracture (MOF), defined as hip, wrist, spine and humerus fractures, in patients with a prior fracture. We developed a user-friendly tool for risk calculation of subsequent MOF in osteopenia patients, using the best performing model.

INTRODUCTION

Major osteoporotic fractures (MOFs), defined as hip, wrist, spine and humerus fractures, can have serious consequences regarding morbidity and mortality. Machine learning provides new opportunities for fracture prediction and may aid in targeting preventive interventions to patients at risk of MOF. The primary objective is to develop and compare several models, capable of predicting the risk of MOF as a function of time in patients seen at the fracture and osteoporosis outpatient clinic (FO-clinic) after sustaining a fracture.

METHODS

Patients aged > 50 years visiting an FO-clinic were included in this retrospective study. We compared discriminative ability (concordance index) for predicting the risk on MOF with a Cox regression, random survival forests (RSF) and an artificial neural network (ANN)-DeepSurv model. Missing data was imputed using multiple imputations by chained equations (MICE) or RSF's imputation function. Analyses were performed for the total cohort and a subset of osteopenia patients without vertebral fracture.

RESULTS

A total of 7578 patients were included, 805 (11%) patients sustained a subsequent MOF. The highest concordance-index in the total dataset was 0.697 (0.664-0.730) for Cox regression; no significant difference was determined between the models. In the osteopenia subset, Cox regression outperformed RSF (p = 0.043 and p = 0.023) and ANN-DeepSurv (p = 0.043) with a c-index of 0.625 (0.562-0.689). Cox regression was used to develop a MOF risk calculator on this subset.

CONCLUSION

We show that predicting the risk of MOF in patients who already sustained a fracture can be done with adequate discriminative performance. We developed a user-friendly tool for risk calculation of subsequent MOF in patients with osteopenia.

Machine learning approaches for the prediction of bone mineral density by using genomic and phenotypic data of 5130 older men

The study aimed to utilize machine learning (ML) approaches and genomic data to develop a prediction model for bone mineral density (BMD) and identify the best modeling approach for BMD prediction. The genomic and phenotypic data of Osteoporotic Fractures in Men Study (n = 5130) was analyzed. Genetic risk score (GRS) was calculated from 1103 associated SNPs for each participant after a comprehensive genotype imputation. Data were normalized and divided into a training set (80%) and a validation set (20%) for analysis. Random forest, gradient boosting, neural network, and linear regression were used to develop BMD prediction models separately. Ten-fold cross-validation was used for hyper-parameters optimization. Mean square error and mean absolute error were used to assess model performance. When using GRS and phenotypic covariates as the predictors, all ML models' performance and linear regression in BMD prediction were similar. However, when replacing GRS with the 1103 individual SNPs in the model, ML models performed significantly better than linear regression (with lasso regularization), and the gradient boosting model performed the best. Our study suggested that ML models, especially gradient boosting, can improve BMD prediction in genomic data.

Deep Learning With Electronic Health Records for Short-Term Fracture Risk Identification: Crystal Bone Algorithm Development and Validation

Background

Fractures as a result of osteoporosis and low bone mass are common and give rise to significant clinical, personal, and economic burden. Even after a fracture occurs, high fracture risk remains widely underdiagnosed and undertreated. Common fracture risk assessment tools utilize a subset of clinical risk factors for prediction, and often require manual data entry. Furthermore, these tools predict risk over the long term and do not explicitly provide short-term risk estimates necessary to identify patients likely to experience a fracture in the next 1-2 years.

Objective

The goal of this study was to develop and evaluate an algorithm for the identification of patients at risk of fracture in a subsequent 1- to 2-year period. In order to address the aforementioned limitations of current prediction tools, this approach focused on a short-term timeframe, automated data entry, and the use of longitudinal data to inform the predictions.

Methods

Using retrospective electronic health record data from over 1,000,000 patients, we developed Crystal Bone, an algorithm that applies machine learning techniques from natural language processing to the temporal nature of patient histories to generate short-term fracture risk predictions. Similar to how language models predict the next word in a given sentence or the topic of a document, Crystal Bone predicts whether a patient’s future trajectory might contain a fracture event, or whether the signature of the patient’s journey is similar to that of a typical future fracture patient. A holdout set with 192,590 patients was used to validate accuracy. Experimental baseline models and human-level performance were used for comparison.

Results

The model accurately predicted 1- to 2-year fracture risk for patients aged over 50 years (area under the receiver operating characteristics curve [AUROC] 0.81). These algorithms outperformed the experimental baselines (AUROC 0.67) and showed meaningful improvements when compared to retrospective approximation of human-level performance by correctly identifying 9649 of 13,765 (70%) at-risk patients who did not receive any preventative bone-health-related medical interventions from their physicians.

Conclusions

These findings indicate that it is possible to use a patient’s unique medical history as it changes over time to predict the risk of short-term fracture. Validating and applying such a tool within the health care system could enable automated and widespread prediction of this risk and may help with identification of patients at very high risk of fracture.

What Is the Accuracy of Three Different Machine Learning Techniques to Predict Clinical Outcomes After Shoulder Arthroplasty?

BACKGROUND

Machine learning techniques can identify complex relationships in large healthcare datasets and build prediction models that better inform physicians in ways that can assist in patient treatment decision-making. In the domain of shoulder arthroplasty, machine learning appears to have the potential to anticipate patients' results after surgery, but this has not been well explored.

QUESTIONS/PURPOSES

(1) What is the accuracy of machine learning to predict the American Shoulder and Elbow Surgery (ASES), University of California Los Angeles (UCLA), Constant, global shoulder function, and VAS pain scores, as well as active abduction, forward flexion, and external rotation at 1 year, 2 to 3 years, 3 to 5 years, and more than 5 years after anatomic total shoulder arthroplasty (aTSA) or reverse total shoulder arthroplasty (rTSA)? (2) What is the accuracy of machine learning to identify whether a patient will achieve clinical improvement that exceeds the minimum clinically important difference (MCID) threshold for each outcome measure? (3) What is the accuracy of machine learning to identify whether a patient will achieve clinical improvement that exceeds the substantial clinical benefit threshold for each outcome measure?

METHODS

A machine learning analysis was conducted on a database of 7811 patients undergoing shoulder arthroplasty of one prosthesis design to create predictive models for multiple clinical outcome measures. Excluding patients with revisions, fracture indications, and hemiarthroplasty resulted in 6210 eligible primary aTSA and rTSA patients, of whom 4782 patients with 11,198 postoperative follow-up visits had sufficient preoperative, intraoperative, and postoperative data to train and test the predictive models. Preoperative clinical data from 1895 primary aTSA patients and 2887 primary rTSA patients were analyzed using three commercially available supervised machine learning techniques: linear regression, XGBoost, and Wide and Deep, to train and test predictive models for the ASES, UCLA, Constant, global shoulder function, and VAS pain scores, as well as active abduction, forward flexion, and external rotation. Our primary study goal was to quantify the accuracy of three machine learning techniques to predict each outcome measure at multiple postoperative timepoints after aTSA and rTSA using the mean absolute error between the actual and predicted values. Our secondary study goals were to identify whether a patient would experience clinical improvement greater than the MCID and substantial clinical benefit anchor-based thresholds of patient satisfaction for each outcome measure as quantified by the model classification parameters of precision, recall, accuracy, and area under the receiver operating curve.

RESULTS

Each machine learning technique demonstrated similar accuracy to predict each outcome measure at each postoperative point for both aTSA and rTSA, though small differences in prediction accuracy were observed between techniques. Across all postsurgical timepoints, the Wide and Deep technique was associated with the smallest mean absolute error and predicted the postoperative ASES score to ± 10.1 to 11.3 points, the UCLA score to ± 2.5 to 3.4, the Constant score to ± 7.3 to 7.9, the global shoulder function score to ± 1.0 to 1.4, the VAS pain score to ± 1.2 to 1.4, active abduction to ± 18 to 21°, forward elevation to ± 15 to 17°, and external rotation to ± 10 to 12°. These models also accurately identified the patients who did and did not achieve clinical improvement that exceeded the MCID (93% to 99% accuracy for patient-reported outcome measures (PROMs) and 85% to 94% for pain, function, and ROM measures) and substantial clinical benefit (82% to 93% accuracy for PROMs and 78% to 90% for pain, function, and ROM measures) thresholds.

CONCLUSIONS

Machine learning techniques can use preoperative data to accurately predict clinical outcomes at multiple postoperative points after shoulder arthroplasty and accurately risk-stratify patients by preoperatively identifying who may and who may not achieve MCID and substantial clinical benefit improvement thresholds for each outcome measure.

CLINICAL RELEVANCE

Three different commercially available machine learning techniques were used to train and test models that predicted clinical outcomes after aTSA and rTSA; this device-type comparison was performed to demonstrate how predictive modeling techniques can be used in the near future to help answer unsolved clinical questions and augment decision-making to improve outcomes after shoulder arthroplasty.

Machine Learning Approaches for Fracture Risk Assessment: A Comparative Analysis of Genomic and Phenotypic Data in 5130 Older Men

The study aims were to develop fracture prediction models by using machine learning approaches and genomic data, as well as to identify the best modeling approach for fracture prediction. The genomic data of Osteoporotic Fractures in Men, cohort Study (n = 5130), were analyzed. After a comprehensive genotype imputation, genetic risk score (GRS) was calculated from 1103 associated Single Nucleotide Polymorphisms for each participant. Data were normalized and split into a training set (80%) and a validation set (20%) for analysis. Random forest, gradient boosting, neural network, and logistic regression were used to develop prediction models for major osteoporotic fractures separately, with GRS, bone density, and other risk factors as predictors. In model training, the synthetic minority oversampling technique was used to account for low fracture rate, and tenfold cross-validation was employed for hyperparameters optimization. In the testing, the area under curve (AUC) and accuracy were used to assess the model performance. The McNemar test was employed to examine the accuracy difference between models. The results showed that the prediction performance of gradient boosting was the best, with AUC of 0.71 and an accuracy of 0.88, and the GRS ranked as the 7th most important variable in the model. The performance of random forest and neural network were also significantly better than that of logistic regression. This study suggested that improving fracture prediction in older men can be achieved by incorporating genetic profiling and by utilizing the gradient boosting approach. This result should not be extrapolated to women or young individuals.

Using Machine Learning to Predict Rehabilitation Outcomes in Postacute Hip Fracture Patients

OBJECTIVE

To use machine learning-based methods in designing a predictive model of rehabilitation outcomes for postacute hip fracture patients.

DESIGN

A retrospective analysis using linear models, AdaBoost, CatBoost, ExtraTrees, K-Nearest Neighbors, RandomForest, Support vector machine, XGBoost, and voting of all models to develop and validate a predictive model.

SETTING

A university-affiliated 300-bed major postacute geriatric rehabilitation center.

PARTICIPANTS

Consecutive hip fracture patients (N=1625) admitted to an postacute rehabilitation department.

MAIN OUTCOME MEASURES

The FIM instrument, motor FIM (mFIM), and the relative functional gain on mFIM (mFIM effectiveness) as a continuous and binary variable. Ten predictive models were created: base models (linear/logistic regression), and 8 machine learning models (AdaBoost, CatBoost, ExtraTrees, K-Nearest Neighbors, RandomForest, Support vector machine, XGBoost, and a voting ensemble). R² was used to evaluate their performance in predicting a continuous outcome variable, and the area under the receiver operating characteristic curve was used to evaluate the binary outcome. A paired 2-tailed t test compared the results of the different models.

RESULTS

Machine learning-based models yielded better results than the linear and logistic regression models in predicting rehabilitation outcomes. The 3 most important predictors of the mFIM effectiveness score were the Mini Mental State Examination (MMSE), prefracture mFIM scores, and age. The 3 most important predictors of the discharge mFIM score were the admission mFIM, MMSE, and prefracture mFIM scores. The most contributing factors for favorable outcomes (mFIM effectiveness > median) with higher prediction confidence level were high MMSE (25.7±2.8), high prefacture mFIM (81.5±7.8), and high admission mFIM (48.6±8) scores. We present a simple prediction instrument for estimating the expected performance of postacute hip fracture patients.

CONCLUSIONS

The use of machine learning models to predict rehabilitation outcomes of postacute hip fracture patients is superior to linear and logistic regression models. The higher the MMSE, prefracture mFIM, and admission mFIM scores are, the higher the confidence levels of the predicted parameters.

Artificial intelligence: A tool for sports trauma prediction

Injuries exert an enormous impact on athletes and teams. This is seen especially in professional soccer, with a marked negative impact on team performance and considerable costs of rehabilitation for players. Existing studies provide some preliminary understanding of which factors are mostly associated with injury risk, but scientific systematic evaluation of the potential of statistical models in forecasting injuries is still missing. Some factors raise the risk of a sport injury, but there are also elements that predispose athletes to sports injuries. The biological mechanisms involved in non-contact musculoskeletal soft tissue injuries are poorly understood. Genetic risk factors may be associated with susceptibility to injuries, and may exert marked influence on recovery times. Athletes are complex systems, and depend on internal and external factors to attain and maintain stability of their health and their performance. Organisms, participants or traits within a dynamic system adapt and change when factors within that system change. Scientists routinely predict risk in a variety of dynamic systems, including weather, political forecasting and projecting traffic fatalities and the last years have started the use of predictive models in the human health industry. We propose that the use of artificial intelligence may well help in assessing risk and help to predict the occurrence of sport injuries.

A Comparative Systematic Literature Review on Knee Bone Reports from MRI, X-rays and CT Scans Using Deep Learning and Machine Learning Methodologies

The purpose of this research was to provide a “systematic literature review” of knee bone reports that are obtained by MRI, CT scans, and X-rays by using deep learning and machine learning techniques by comparing different approaches—to perform a comprehensive study on the deep learning and machine learning methodologies to diagnose knee bone diseases by detecting symptoms from X-ray, CT scan, and MRI images. This study will help those researchers who want to conduct research in the knee bone field. A comparative systematic literature review was conducted for the accomplishment of our work. A total of 32 papers were reviewed in this research. Six papers consist of X-rays of knee bone with deep learning methodologies, five papers cover the MRI of knee bone using deep learning approaches, and another five papers cover CT scans of knee bone with deep learning techniques. Another 16 papers cover the machine learning techniques for evaluating CT scans, X-rays, and MRIs of knee bone. This research compares the deep learning methodologies for CT scan, MRI, and X-ray reports on knee bone, comparing the accuracy of each technique, which can be used for future development. In the future, this research will be enhanced by comparing X-ray, CT-scan, and MRI reports of knee bone with information retrieval and big data techniques. The results show that deep learning techniques are best for X-ray, MRI, and CT scan images of the knee bone to diagnose diseases.

Osteoporotic hip fracture prediction from risk factors available in administrative claims data - A machine learning approach

Objective

Hip fractures are among the most frequently occurring fragility fractures in older adults, associated with a loss of quality of life, high mortality, and high use of healthcare resources. The aim was to apply the superlearner method to predict osteoporotic hip fractures using administrative claims data and to compare its performance to established methods.

Methods

We devided claims data of 288,086 individuals aged 65 years and older without care level into a training (80%) and a validation set (20%). Subsequently, we trained a superlearner algorithm that considered both regression and machine learning algorithms (e.g., support vector machines, RUSBoost) on a large set of clinical risk factors. Mean squared error and measures of discrimination and calibration were employed to assess prediction performance.

Results

All algorithms used in the analysis showed similar performance with an AUC ranging from 0.66 to 0.72 in the training and 0.65 to 0.70 in the validation set. Superlearner showed good discrimination in the training set but poorer discrimination and calibration in the validation set.

Conclusions

The superlearner achieved similar predictive performance compared to the individual algorithms included. Nevertheless, in the presence of non-linearity and complex interactions, this method might be a flexible alternative to be considered for risk prediction in large datasets.

Artificial Intelligence and Orthopaedics: An Introduction for Clinicians

➤Artificial intelligence (AI) provides machines with the ability to perform tasks using algorithms governed by pattern recognition and self-correction on large amounts of data to narrow options in order to avoid errors. ➤The 4 things necessary for AI in medicine include big data sets, powerful computers, cloud computing, and open source algorithmic development. ➤The use of AI in health care continues to expand, and its impact on orthopaedic surgery can already be found in diverse areas such as image recognition, risk prediction, patient-specific payment models, and clinical decision-making. ➤Just as the business of medicine was once considered outside the domain of the orthopaedic surgeon, emerging technologies such as AI warrant ownership, leverage, and application by the orthopaedic surgeon to improve the care that we provide to the patients we serve. ➤AI could provide solutions to factors contributing to physician burnout and medical mistakes. However, challenges regarding the ethical deployment, regulation, and the clinical superiority of AI over traditional statistics and decision-making remain to be resolved.