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

Development and reporting of artificial intelligence in osteoporosis management

An abundance of medical data and enhanced computational power have led to a surge in artificial intelligence (AI) applications. Published studies involving AI in bone and osteoporosis research have increased exponentially, raising the need for transparent model development and reporting strategies. This review offers a comprehensive overview and systematic quality assessment of AI articles in osteoporosis while highlighting recent advancements. A systematic search in the PubMed database, from December 17, 2020 to February 1, 2023 was conducted to identify AI articles that relate to osteoporosis. The quality assessment of the studies relied on the systematic evaluation of 12 quality items derived from the minimum information about clinical artificial intelligence modeling checklist. The systematic search yielded 97 articles that fell into 5 areas; bone properties assessment (11 articles), osteoporosis classification (26 articles), fracture detection/classification (25 articles), risk prediction (24 articles), and bone segmentation (11 articles). The average quality score for each study area was 8.9 (range: 7-11) for bone properties assessment, 7.8 (range: 5-11) for osteoporosis classification, 8.4 (range: 7-11) for fracture detection, 7.6 (range: 4-11) for risk prediction, and 9.0 (range: 6-11) for bone segmentation. A sixth area, AI-driven clinical decision support, identified the studies from the 5 preceding areas that aimed to improve clinician efficiency, diagnostic accuracy, and patient outcomes through AI-driven models and opportunistic screening by automating or assisting with specific clinical tasks in complex scenarios. The current work highlights disparities in study quality and a lack of standardized reporting practices. Despite these limitations, a wide range of models and examination strategies have shown promising outcomes to aid in the earlier diagnosis and improve clinical decision-making. Through careful consideration of sources of bias in model performance assessment, the field can build confidence in AI-based approaches, ultimately leading to improved clinical workflows and patient outcomes.

Establishment and validation of a nomogram for predicting the risk of hip fracture in patients with stroke: A multicenter retrospective study

PURPOSE

There are currently no models for predicting hip fractures after stroke. This study wanted to investigate the risk factors leading to hip fracture in stroke patients and to establish a risk prediction model to visualize this risk.

PATIENTS AND METHODS

We reviewed 439 stroke patients with or without hip fractures admitted to the Affiliated Hospital of Xuzhou Medical University from June 2014 to June 2017 as the training set, and collected 83 patients of the same type from the First Affiliated Hospital of Harbin Medical University and the Affiliated Hospital of Xuzhou Medical University from June 2020 to June 2023 as the testing set. Patients were divided into fracture group and non-fracture group based on the presence of hip fractures. Multivariate logistic regression analysis was used to screen for meaningful factors. Nomogram predicting the risk of hip fracture occurrence were created based on the multifactor analysis, and performance was evaluated using receiver operating characteristic curve (ROC), calibration curves, and decision curve analysis (DCA). A web calculator was created to facilitate a more convenient interactive experience for clinicians.

RESULTS

In training set, there were 35 cases (7.9 %) of hip fractures after stroke, while in testing set, this data was 13 cases (15.6 %). In training set, univariate analysis showed significant differences between the two groups in the number of falls, smoking, hypertension, glucocorticoids, number of strokes, Mini-Mental State Examination (MMSE), visual acuity level, National Institute of Health stroke scale (NIHSS), Berg Balance Scale (BBS), and Stop Walking When Talking (SWWT) (P<0.05). Multivariate analysis showed that number of falls [OR=17.104, 95 % CI (3.727-78.489), P = 0.000], NIHSS [OR=1.565, 95 % CI (1.193-2.052), P = 0.001], SWWT [OR=12.080, 95 % CI (2.398-60.851), P = 0.003] were independent risk factors positively associated with new fractures. BMD [OR = 0.155, 95 % CI (0.044-0.546), P = 0.012] and BBS [OR = 0.840, 95 % CI (0.739-0.954), P = 0.007] were negatively associated with new fractures. The area under the curve (AUC) of nomogram were 0.939 (95 % CI: 0.748-0.943) and 0.980 (95 % CI: 0.886-1.000) in training and testing sets, respectively, and the calibration curves showed a high agreement between predicted and actual status with an area under the decision curve of 0.034 and 0.109, respectively.

CONCLUSIONS

The number of falls, fracture history, low BBS score, high NIHSS score, and positive SWWT are risk factors for hip fracture after stroke. Based on this, a nomogram with high accuracy was developed and a web calculator (https://stroke.shinyapps.io/DynNomapp/) was created.

From plan to delivery: Machine learning based positional accuracy prediction of multi-leaf collimator and estimation of delivery effect in volumetric modulated arc therapy

PURPOSE

The positional accuracy of MLC is an important element in establishing the exact dosimetry in VMAT. We comprehensively analyzed factors that may affect MLC positional accuracy in VMAT, and constructed a model to predict MLC positional deviation and estimate planning delivery quality according to the VMAT plans before delivery.

METHODS

A total of 744 "dynalog" files for 23 VMAT plans were extracted randomly from treatment database. Multi-correlation was used to analyzed the potential influences on MLC positional accuracy, including the spatial characteristics and temporal variability of VMAT fluence, and the mechanical wear parameters of MLC. We developed a model to forecast the accuracy of MLC moving position utilizing the random forest (RF) ensemble learning method. Spearman correlation was used to further investigate the associations between MLC positional deviation and dosage deviations as well as gamma passing rates.

RESULTS

The MLC positional deviation and effective impact factors show a strong multi-correlation (R = 0.701, p-value < 0.05). This leads to the development of a highly accurate prediction model with average variables explained of 95.03% and average MSE of 0.059 in the 5-fold cross-validation, and MSE of 0.074 for the test data was obtained. The absolute dose deviations caused by MLC positional deviation ranging from 12.948 to 210.235 cGy, while the relative volume deviation remained small at 0.470%-5.161%. The average MLC positional deviation correlated substantially with gamma passing rates (with correlation coefficient of -0.506 to -0.720 and p-value < 0.05) but marginally with dosage deviations (with correlation coefficient < 0.498 and p-value > 0.05).

CONCLUSIONS

The RF predictive model provides a prior tool for VMAT quality assurance.

A comprehensive approach for osteoporosis detection through chest CT analysis and bone turnover markers: harnessing radiomics and deep learning techniques

Purpose

The main objective of this study is to assess the possibility of using radiomics, deep learning, and transfer learning methods for the analysis of chest CT scans. An additional aim is to combine these techniques with bone turnover markers to identify and screen for osteoporosis in patients.

Method

A total of 488 patients who had undergone chest CT and bone turnover marker testing, and had known bone mineral density, were included in this study. ITK-SNAP software was used to delineate regions of interest, while radiomics features were extracted using Python. Multiple 2D and 3D deep learning models were trained to identify these regions of interest. The effectiveness of these techniques in screening for osteoporosis in patients was compared.

Result

Clinical models based on gender, age, and β-cross achieved an accuracy of 0.698 and an AUC of 0.665. Radiomics models, which utilized 14 selected radiomics features, achieved a maximum accuracy of 0.750 and an AUC of 0.739. The test group yielded promising results: the 2D Deep Learning model achieved an accuracy of 0.812 and an AUC of 0.855, while the 3D Deep Learning model performed even better with an accuracy of 0.854 and an AUC of 0.906. Similarly, the 2D Transfer Learning model achieved an accuracy of 0.854 and an AUC of 0.880, whereas the 3D Transfer Learning model exhibited an accuracy of 0.740 and an AUC of 0.737. Overall, the application of 3D deep learning and 2D transfer learning techniques on chest CT scans showed excellent screening performance in the context of osteoporosis.

Conclusion

Bone turnover markers may not be necessary for osteoporosis screening, as 3D deep learning and 2D transfer learning techniques utilizing chest CT scans proved to be equally effective alternatives.

Does vitamin D deficiency affect functional outcomes in hip fracture patients? A meta-analysis of cohort studies

BACKGROUND

Vitamin D deficiency is common in patients with hip fractures and may negatively affect functional recovery and quality of life (QOL).

OBJECTIVE

This study aimed to conduct a meta-analysis to quantify the effects of vitamin D deficiency on physical function and quality of life after hip fractures.

METHODS

The PubMed, EMBASE, Scopus, and Cochrane Library databases were searched for relevant studies. The inclusion criteria were hip fracture, comparison between vitamin D deficiency and normal vitamin D levels in patients with hip fracture, and functional outcome as the primary outcome. The exclusion criteria were case reports, reviews, duplicates, studies with a high risk of bias, and non-comparable or missing data. Two independent reviewers selected studies, extracted data, assessed bias, and performed meta-analyses using the Review Manager. Heterogeneity and publication bias were also assessed. Two independent reviewers selected the studies, extracted data, and assessed the risk of bias. We performed a meta-analysis using Review Manager and assessed heterogeneity and publication bias.

RESULTS

Seven studies with 1,972 patients were included. Vitamin D deficiency was defined as a 25(OH)D level < 20 ng/mL. There were no significant differences in the ability to walk (OR 0.68, 95% CI 0.31-1.53, I2 = 69%) or length of hospital stay (MD 2.27 days, 95% CI - 2.47 to 7.01, I2 = 93%) between patients with and without vitamin D deficiency. However, patients with vitamin D deficiency had significantly worse functional ability and quality of life (SMD - 1.50, 95% CI - 2.88 to - 0.12, I2 = 96%).

CONCLUSIONS

Despite the limitations of this study, such as small sample size, heterogeneous outcome assessments, and variable vitamin D measurement techniques, the results demonstrated that screening for vitamin D status and optimizing levels through supplementation could facilitate rehabilitation, promote lifestyle changes, aid in the recovery of independence, and help reduce long-term burdens.

Systematic review of machine-learning models in orthopaedic trauma

Aims

Machine-learning (ML) prediction models in orthopaedic trauma hold great promise in assisting clinicians in various tasks, such as personalized risk stratification. However, an overview of current applications and critical appraisal to peer-reviewed guidelines is lacking. The objectives of this study are to 1) provide an overview of current ML prediction models in orthopaedic trauma; 2) evaluate the completeness of reporting following the Transparent Reporting of a multivariable prediction model for Individual Prognosis Or Diagnosis (TRIPOD) statement; and 3) assess the risk of bias following the Prediction model Risk Of Bias Assessment Tool (PROBAST) tool.

Methods

A systematic search screening 3,252 studies identified 45 ML-based prediction models in orthopaedic trauma up to January 2023. The TRIPOD statement assessed transparent reporting and the PROBAST tool the risk of bias.

Results

A total of 40 studies reported on training and internal validation; four studies performed both development and external validation, and one study performed only external validation. The most commonly reported outcomes were mortality (33%, 15/45) and length of hospital stay (9%, 4/45), and the majority of prediction models were developed in the hip fracture population (60%, 27/45). The overall median completeness for the TRIPOD statement was 62% (interquartile range 30 to 81%). The overall risk of bias in the PROBAST tool was low in 24% (11/45), high in 69% (31/45), and unclear in 7% (3/45) of the studies. High risk of bias was mainly due to analysis domain concerns including small datasets with low number of outcomes, complete-case analysis in case of missing data, and no reporting of performance measures.

Conclusion

The results of this study showed that despite a myriad of potential clinically useful applications, a substantial part of ML studies in orthopaedic trauma lack transparent reporting, and are at high risk of bias. These problems must be resolved by following established guidelines to instil confidence in ML models among patients and clinicians. Otherwise, there will remain a sizeable gap between the development of ML prediction models and their clinical application in our day-to-day orthopaedic trauma practice.

Predicting Prolonged Wound Drainage after Hemiarthroplasty for Hip Fractures: A Stacked Machine Learning Study

Background

Prolonged wound drainage (PWD) is one of the most important reasons that increase the risk of early periprosthetic joint infection after arthroplasty. It is very important to evaluate the risk factors for PWD in the surgical field after arthroplasty surgery. This can be accomplished using machine learning or artificial intelligence methods. Our aim in this study was to compare machine learning methods in predicting possible PWD.

Methods

The study was carried out on clinical, laboratory, and radiological data of 313 patients who underwent hemiarthroplasty (HA) for proximal femur fractures. We preprocessed the dataset and trained and tested machine learning methods using cross validation. We compared various machine learning algorithms (linear discriminant analysis, decision tree, k-nearest neighbors, gradient boosting machine, and logistic regression [LR]) based on performance measures. We also combined the most successful algorithms with a metaclassifier. To help understand the relationship between risk factors, we provided a risk factor severity ranking.

Results

To estimate the risk of PWD, classification was performed with first-level classifiers and then integrated as a LR-based meta-learner stacking method. More performance improvements were achieved with the stacking method.

Conclusions

We found that the stacking method was superior to other methods in PWD classification. We determined that the volume of fluid collected from the drain, morbid obesity class, blood transfusion, and body mass index score were the four most important risk factors according to stacking.

Anticoagulation drug use and rehabilitation outcomes in post-acute hip fractured patients

PURPOSE

To assess the relationship between anticoagulant use and rehabilitation outcomes in post-acute hip fracture patients.

METHODS

A retrospective study (1/2017 to 5/2019) of 299 hip fractured patients.

OUTCOME MEASURES

Functional Independence Measure (FIM) and the motor FIM's effectiveness.

RESULTS

Patients treated with anticoagulation drugs exhibited a significant longer latency time from fracture to surgery (U = -4.37, p < 0.001) and from surgery to rehabilitation (U=-2.27, p = 0.023), and a significantly higher rate of cardiovascular diseases (χ2=0.15, p= 0.023) compared with untreated patients. No significant differences between the two patient groups were found regarding the rate of blood transfusions, perioperative complications (infections, reoperation), or functional outcome measures.

CONCLUSIONS

Oral anticoagulants are not associated with rehabilitation outcomes of hip fracture patients.Implications rehabilitationAnticoagulation drug use is not associated with functional outcome of post-acute hip fracture patients.It is recommended to renew oral anticoagulants for patients on chronic treatment after surgery since no negative outcomes were found during rehabilitation under anticoagulant treatment and in light of the importance of these drugs in preventing thromboembolic complications.

Unveiling Osteoporosis Through Radiomics Analysis of Hip CT Imaging

RATIONALE AND OBJECTIVES

This study aims to investigate the use of radiomics analysis of hip CT imaging to unveil osteoporosis.

MATERIALS AND METHODS

The researchers analyzed hip CT scans from a cohort of patients, including both osteoporotic and healthy individuals. Radiomics technique are employed to extract a comprehensive array of features from these images, encompassing texture, shape, and intensity alterations. Radiomics analysis using the 10 most commonly used machine learning models was employed to identify screened radiomics features for the detection of osteoporosis in patients. In addition to radiomics features, the basic information of patients is also utilized as training data for these machine learning models to accurately identify the presence of osteoporosis. A comparison would be made between the efficiency of recognizing radiomics features and the efficiency of recognizing patient basic information. The machine learning model that achieves the highest performance would be chosen to integrate patient basic information and radiomics features for the development of clinical nomograms.

RESULT

After a thorough screening process, 16 radiomics features were selected as input parameters for the machine learning model. In the test group, the highest accuracy achieved using radiomics features was 0.849, with an area under the curve (AUC) of 0.919. Evaluation of clinical features identified age and gender as closely associated with osteoporosis. Among these features, the KNN model exhibited the highest accuracy of 0.731 and an AUC of 0.658 in the test group. Comparing the performance of radiomics and clinical features, radiomics features demonstrated superior AUC values in the machine learning models. Ultimately, the XGBoost model, utilizing both radiomics and clinical features, was selected as the final Nomogram prediction model. In the test group, this model achieved an accuracy of 0.882 and an AUC of 0.886 in screening for osteoporosis.

CONCLUSION

Radiomics features derived from hip CT scans exhibit strong screening capabilities for osteoporosis. Furthermore, when combined with easily obtainable clinical features like patient age and gender, an effective screening efficacy for osteoporosis can be achieved.

Machine learning applications for the prediction of extended length of stay in geriatric hip fracture patients

BACKGROUND

Geriatric hip fractures are one of the most common fractures in elderly individuals, and prolonged hospital stays increase the risk of death and complications. Machine learning (ML) has become prevalent in clinical data processing and predictive models. This study aims to develop ML models for predicting extended length of stay (eLOS) among geriatric patients with hip fractures and to identify the associated risk factors.

AIM

To develop ML models for predicting the eLOS among geriatric patients with hip fractures, identify associated risk factors, and compare the performance of each model.

METHODS

A retrospective study was conducted at a single orthopaedic trauma centre, enrolling all patients who underwent hip fracture surgery between January 2018 and December 2022. The study collected various patient characteristics, encompassing demographic data, general health status, injury-related data, laboratory examinations, surgery-related data, and length of stay. Features that exhibited significant differences in univariate analysis were integrated into the ML model establishment and subsequently cross-verified. The study compared the performance of the ML models and determined the risk factors for eLOS.

RESULTS

The study included 763 patients, with 380 experiencing eLOS. Among the models, the decision tree, random forest, and extreme Gradient Boosting models demonstrated the most robust performance. Notably, the artificial neural network model also exhibited impressive results. After cross-validation, the support vector machine and logistic regression models demonstrated superior performance. Predictors for eLOS included delayed surgery, D-dimer level, American Society of Anaesthesiologists (ASA) classification, type of surgery, and sex.

CONCLUSION

ML proved to be highly accurate in predicting the eLOS for geriatric patients with hip fractures. The identified key risk factors were delayed surgery, D-dimer level, ASA classification, type of surgery, and sex. This valuable information can aid clinicians in allocating resources more efficiently to meet patient demand effectively.

Prediction of emergence from prolonged disorders of consciousness from measures within the UK rehabilitation outcomes collaborative database: a multicentre analysis using machine learning

PURPOSE

Predicting emergence from prolonged disorders of consciousness (PDOC) is important for planning care and treatment. We used machine learning to examine which variables from routine clinical data on admission to specialist rehabilitation units best predict emergence by discharge.

MATERIALS AND METHODS

A multicentre national cohort analysis of prospectively collected clinical data from the UK Rehabilitation Outcomes (UKROC) database 2010-2018. Patients (n = 1170) were operationally defined as "still in PDOC" or "emerged" by their total UK Functional Assessment Measure (FIM + FAM) discharge score. Variables included: Age, aetiology, length of stay, time since onset, and all items of the Neurological Impairment Scale, Rehabilitation Complexity Scale, Northwick Park Dependency Scale, and the Patient Categorisation Tool. After filtering, prediction of emergence was explored using four techniques: binary logistic regression, linear discriminant analysis, artificial neural networks, and rule induction.

RESULTS

Triangulation through these techniques consistently identified characteristics associated with emergence from PDOC. More severe motor impairment, complex disability, medical and behavioural instability, and anoxic aetiology were predictive of non-emergence, whereas those with less severe motor impairment, agitated behaviour and complex disability were predictive of emergence.

CONCLUSIONS

This initial exploration demonstrates the potential opportunities to enhance prediction of outcome using machine learning techniques to explore routinely collected clinical data. Implications for rehabilitationPredicting emergence from prolonged disorders of consciousness is important for planning care and treatment.Few evidence-based criteria exist for aiding clinical decision-making and existing criteria are mostly based upon acute admission data.Whilst acknowledging the limitations of using proxy data for diagnosis of emergence, this study suggests that key items from the UKROC dataset, routinely collected on admission to specialist rehabilitation some months post injury, may help to predict those patients who are more (or less) likely to regain consciousness.Machine learning can help to enhance our understanding of the best predictors of outcome and thus assist with clinical decision-making in PDOC.

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).

Artificial Intelligence for Hip Fracture Detection and Outcome Prediction: A Systematic Review and Meta-analysis

IMPORTANCE

Artificial intelligence (AI) enables powerful models for establishment of clinical diagnostic and prognostic tools for hip fractures; however the performance and potential impact of these newly developed algorithms are currently unknown.

OBJECTIVE

To evaluate the performance of AI algorithms designed to diagnose hip fractures on radiographs and predict postoperative clinical outcomes following hip fracture surgery relative to current practices.

DATA SOURCES

A systematic review of the literature was performed using the MEDLINE, Embase, and Cochrane Library databases for all articles published from database inception to January 23, 2023. A manual reference search of included articles was also undertaken to identify any additional relevant articles.

STUDY SELECTION

Studies developing machine learning (ML) models for the diagnosis of hip fractures from hip or pelvic radiographs or to predict any postoperative patient outcome following hip fracture surgery were included.

DATA EXTRACTION AND SYNTHESIS

This study followed the Preferred Reporting Items for Systematic Reviews and Meta-analyses and was registered with PROSPERO. Eligible full-text articles were evaluated and relevant data extracted independently using a template data extraction form. For studies that predicted postoperative outcomes, the performance of traditional predictive statistical models, either multivariable logistic or linear regression, was recorded and compared with the performance of the best ML model on the same out-of-sample data set.

MAIN OUTCOMES AND MEASURES

Diagnostic accuracy of AI models was compared with the diagnostic accuracy of expert clinicians using odds ratios (ORs) with 95% CIs. Areas under the curve for postoperative outcome prediction between traditional statistical models (multivariable linear or logistic regression) and ML models were compared.

RESULTS

Of 39 studies that met all criteria and were included in this analysis, 18 (46.2%) used AI models to diagnose hip fractures on plain radiographs and 21 (53.8%) used AI models to predict patient outcomes following hip fracture surgery. A total of 39 598 plain radiographs and 714 939 hip fractures were used for training, validating, and testing ML models specific to diagnosis and postoperative outcome prediction, respectively. Mortality and length of hospital stay were the most predicted outcomes. On pooled data analysis, compared with clinicians, the OR for diagnostic error of ML models was 0.79 (95% CI, 0.48-1.31; P = .36; I2 = 60%) for hip fracture radiographs. For the ML models, the mean (SD) sensitivity was 89.3% (8.5%), specificity was 87.5% (9.9%), and F1 score was 0.90 (0.06). The mean area under the curve for mortality prediction was 0.84 with ML models compared with 0.79 for alternative controls (P = .09).

CONCLUSIONS AND RELEVANCE

The findings of this systematic review and meta-analysis suggest that the potential applications of AI to aid with diagnosis from hip radiographs are promising. The performance of AI in diagnosing hip fractures was comparable with that of expert radiologists and surgeons. However, current implementations of AI for outcome prediction do not seem to provide substantial benefit over traditional multivariable predictive statistics.

Indicators of Improvement in Performing Activities of Daily Living Among Older Patients Undergoing Rehabilitation Following Hip Fractures

This study aimed to evaluate the relationship between improvement in activities of daily living (ADL) and cognitive status during rehabilitation and assess factors associated with ADL improvement among older patients undergoing rehabilitation after hip fractures. This retrospective cohort study comprised 306 patients aged ≥80 years who underwent hip fracture rehabilitation. The functional independence measure gain during rehabilitation was significantly lower in the group with abnormal cognition than in the group with normal cognition. Mini-Mental State Examination, Charlson Comorbidity Index, daily duration of rehabilitation, and length of hospitalization for rehabilitation were independent factors associated with functional independence measure gain during rehabilitation in the multivariate regression analysis. Although older patients with cognitive impairment had lower ADL improvements during hip fracture rehabilitation, such patients may be able to improve their ADL by undergoing intensive and long rehabilitation programs. They should not refrain from such rehabilitation programs due to older age, fracture, and cognitive impairment.

Efficacy of a machine learning-based approach in predicting neurological prognosis of cervical spinal cord injury patients following urgent surgery within 24 h after injury

We aimed to develop a machine learning (ML) model for predicting the neurological outcomes of cervical spinal cord injury (CSCI). We retrospectively analyzed 135 patients with CSCI who underwent surgery within 24 h after injury. Patients were assessed with the American Spinal Injury Association Impairment Scale (AIS; grades A to E) 6 months after injury. A total of 34 features extracted from demographic variables, surgical factors, laboratory variables, neurological status, and radiological findings were analyzed. The ML model was created using Light GBM, XGBoost, and CatBoost. We evaluated Shapley Additive Explanations (SHAP) values to determine the variables that contributed most to the prediction models. We constructed multiclass prediction models for the five AIS grades and binary classification models to predict more than one-grade improvement in AIS 6 months after injury. Of the ML models used, CatBoost showed the highest accuracy (0.800) for the prediction of AIS grade and the highest AUC (0.90) for predicting improvement in AIS. AIS grade at admission, intramedullary hemorrhage, longitudinal extent of intramedullary T2 hyperintensity, and HbA1c were identified as important features for these prediction models. The ML models successfully predicted neurological outcomes 6 months after injury following urgent surgery in patients with CSCI.

A Scoping Review of the Use of Machine Learning in Health Economics and Outcomes Research: Part 2-Data From Nonwearables

OBJECTIVES

Despite the increasing interest in applying machine learning (ML) methods in health economics and outcomes research (HEOR), stakeholders face uncertainties in when and how ML can be used. We reviewed the recent applications of ML in HEOR.

METHODS

We searched PubMed for studies published between January 2020 and March 2021 and randomly chose 20% of the identified studies for the sake of manageability. Studies that were in HEOR and applied an ML technique were included. Studies related to wearable devices were excluded. We abstracted information on the ML applications, data types, and ML methods and analyzed it using descriptive statistics.

RESULTS

We retrieved 805 articles, of which 161 (20%) were randomly chosen. Ninety-two of the random sample met the eligibility criteria. We found that ML was primarily used for predicting future events (86%) rather than current events (14%). The most common response variables were clinical events or disease incidence (42%) and treatment outcomes (22%). ML was less used to predict economic outcomes such as health resource utilization (16%) or costs (3%). Although electronic medical records (35%) were frequently used for model development, claims data were used less frequently (9%). Tree-based methods (eg, random forests and boosting) were the most commonly used ML methods (31%).

CONCLUSIONS

The use of ML techniques in HEOR is growing rapidly, but there remain opportunities to apply them to predict economic outcomes, especially using claims databases, which could inform the development of cost-effectiveness models.

Vitamin D levels in post-acute hip fractured patients and their association with rehabilitation outcomes

PURPOSE

To report on serum 25-hydroxyvitamin D (25(OH)D) levels in post-acute hip fractured patients, revealed the associations between serum 25(OH)D levels and hip fractured patients' baseline characteristics and rehabilitation outcomes.

MATERIALS AND METHODS

A retrospective study (9/2017-9/2020) of 493 hip fractured patients. 25(OH)D levels were recorded following the patient's baseline characteristics and outcome measures, including the functional independence measure and motor functional independence measure effectiveness. The sample was divided into three groups: deficient (<30 nmol/l), insufficient (30-75 nmol/l) and sufficient (>75 nmol/l) 25(OH)D levels. ANOVA and chi-square test tests compared the groups. Multiple linear analysis assessed the associations between the 25(OH)D and discharge functional independence measure score.

RESULTS

25(OH)D deficiency was found in 20.3% of the patients. The only baseline characteristic significantly associated with serum 25(OH)D levels was dementia. The group with deficient levels of 25(OH)D exhibited a significantly higher rate of low education, low admission albumin levels and a reduced handgrip strength compared to the insufficient/sufficient groups. All functional measure scores were significantly lower in the deficient (25(OH)D) group compared with the insufficient/sufficient patient groups. 25(OH)D levels were found to be significantly associated with the discharge functional independence measure score.

CONCLUSIONS

Routine screening for 25(OH)D levels is mandatory in post-acute hip fracture patients as it may affect rehabilitation outcomes.Implications for Rehabilitation25-hydroxyvitamin D 25(OH)D levels are associated with rehabilitation outcomes in post-acute hip fractured patients.A routine screening for 25(OH)D levels and standardized supplementation protocol during the acute and post-acute rehabilitation setting is recommended as it may improve the quality of care.

Medication regimen complexity index and rehabilitation outcomes in post-acute hip fracture patients study: a retrospective study

BACKGROUND

Polypharmacy is a common problem amongst the elderly population. The complexity of the drug regimen refers not only to a simple medication count, but also to the number of daily doses, frequency, and special instructions given for their use. Medication regimen complexity may affect health outcomes, including an increase in hospitalization rates, drug non-adherence, and mortality rates.

AIM

To assess whether the admission medication regimen complexity index score is associated with rehabilitation outcomes in hip fracture patients; secondary- to assess whether changes in the medication regimen complexity index scores during rehabilitation are associated with rehabilitation outcomes.

METHOD

A retrospective study of 336 hip fracture patients admitted to a post-acute rehabilitation hospital. Primary rehabilitation outcome was assessed via the discharge functional independence measure score. Secondary outcomes included functional independence measure score changes, length of stay and discharge destination.

RESULTS

Patients with low admission medication regimen complexity index scores attained significantly higher admission and discharge motor functional independence measure scores (40.1 vs. 37.1, p = 0.044; 57.1 vs. 52.9, p = 0.014, respectively), a higher motor functional independence measure score effectiveness (36.1 vs. 31.3, p = 0.030) and a higher rate of favorable motor functional independence measure effectiveness score (58.1% vs. 42.0%, p = 0.004). A multiple linear regression analysis revealed that the admission medication regimen complexity index score was not associated with the discharge functional independence measure score (standardized coefficient = - 0.058; p = 0.079).

CONCLUSION

A high medication regimen complexity which usually implies severe comorbidity should not be considered a barrier for the rehabilitation of older patients.

Early prediction of clinical scores for left ventricular reverse remodeling using extreme gradient random forest, boosting, and logistic regression algorithm representations

Objective

At present, there is no early prediction model of left ventricular reverse remodeling (LVRR) for people who are in cardiac arrest with an ejection fraction (EF) of ≤35% at first diagnosis; thus, the purpose of this article is to provide a supplement to existing research.

Materials and methods

A total of 109 patients suffering from heart attack with an EF of ≤35% at first diagnosis were involved in this single-center research study. LVRR was defined as an absolute increase in left ventricular ejection fraction (LVEF) from ≥10% to a final value of >35%, with analysis features including demographic characteristics, diseases, biochemical data, echocardiography, and drug therapy. Extreme gradient boosting (XGBoost), random forest, and logistic regression algorithm models were used to distinguish between LVRR and non-LVRR cases and to obtain the most important features.

Results

There were 47 cases (42%) of LVRR in patients suffering from heart failure with an EF of ≤35% at first diagnosis after optimal drug therapy. General statistical analysis and machine learning methods were combined to exclude a number of significant feature groups. The median duration of disease in the LVRR group was significantly lower than that in the non-LVRR group (7 vs. 48 months); the mean values of creatine kinase (CK) and MB isoenzyme of creatine kinase (CK-MB) in the LVRR group were lower than those in the non-LVRR group (80.11 vs. 94.23 U/L; 2.61 vs. 2.99 ng/ml; 27.19 vs. 28.54 mm). Moreover, AUC values for our feature combinations ranged from 97 to 94% and to 87% when using the XGBoost, random forest, and logistic regression techniques, respectively. The ablation test revealed that beats per minute (BPM) and disease duration had a greater impact on the model's ability to accurately forecast outcomes.

Conclusion

Shorter disease duration, slightly lower CK and CK-MB levels, slightly smaller right and left ventricular and left atrial dimensions, and lower mean heart rates were found to be most strongly predictive of LVRR development (BPM).

Sports Rehabilitation Treatment of Medical Information in Tertiary Hospitals Based on Computer Machine Learning

Objective

The processing and analysis of medical rehabilitation information data in tertiary hospitals is a hot research topic. Combining medical data analysis with machine learning algorithms to improve data mining efficiency is a problem that needs to be solved at present. This paper proposes an autonomous perception model of sports medicine rehabilitation equipment based on a deep learning algorithm for sports medical rehabilitation data.

Methods

This paper cites a deep learning multi-dimensional perception model for medical rehabilitation equipment autonomous perception. The model utilizes the automatic overhaul of medical rehabilitation equipment based on deep belief networks. This paper extracts features through a multi-layer neural network and obtains fault location results of medical rehabilitation equipment through softmax.

Results

In similarity prediction, the accuracy rate of the first three kinds of feedback containing the target answer is 77%. The accuracy rate of the target answers included in the top five kinds of feedback was 92%.

Conclusion

In this study, it is feasible to apply deep learning to the quality control information system of sports rehabilitation medical equipment. This improves the management efficiency of medical rehabilitation equipment to a certain extent.

An Ensemble Model for Predicting Retail Banking Churn in the Youth Segment of Customers

(1) This study aims to predict the youth customers’ defection in retail banking. The sample comprised 602 young adult bank customers. (2) The study applied Machine learning techniques, including ensembles, to predict the possibility of churn. (3) The absence of mobile banking, zero-interest personal loans, access to ATMs, and customer care and support were critical driving factors to churn. The ExtraTreeClassifier model resulted in an accuracy rate of 92%, and an AUC of 91.88% validated the findings. (4) Customer retention is one of the critical success factors for organizations so as to enhance the business value. It is imperative for banks to predict the drivers of churn among their young adult customers so as to create and deliver proactive enable quality services.

The role of predictive analytics to explain the employability of management graduates

Purpose

In India, one of the prime focuses of a post-graduate management program is to prepare students and make them job-ready. Masters in Business Management (MBA) program helps students to imbibe theoretical and practical skills which are required by the industry, which can make them hit the ground running from the day they start their career. Many students (almost 40–50%) get pre-placement offers based on their performance in summer internship. The selection for summer interns by the corporate happens within a few months of the student joining the MBA program. Signaling theory in education indicates that the level of productivity of an individual is independent of education, but the educational qualification acts as a testimony for higher ability. However, this theory does not explain the reason for the mismatch between “education and work” or “education and the disparity in salary” between individuals who earn differently but have the same qualification. The paper aims to explore three attributes namely – “employability”– the chance of being employable; “pre-placement offers” – the chance of securing a job offer based on the performance in internship and “salary” – the chance of bagging a good job offer with a high salary.

Design/methodology/approach

The authors have used longitudinal data consisting of 1,202 students who graduated from reputable business schools (B-Schools) in India. In the study, the authors have used predictive analytics on six years data set that have been gathered. The authors have considered 24 attributes including educational background at the graduate level (BE, B Tech, B Com, BSc, BBA and others), score secured in class ten (high, medium and low), score secured in class twelve (high, medium and low), score secured in graduation (high, medium and low), competency in soft skills (high, medium and low), participation in co-curricular activities (high, medium and low) and social engagement status (high, medium and low).

Findings

The findings of the study contradict the signaling theory in education. The findings suggest that the educational qualification alone cannot be the predictor of the employability and the salary offered to the student. The authors note that the better performance at a lower level of qualification (class 12) is the strong predictor in comparison to the student performance at their graduation and post-graduation level. The authors further observed at the post-graduate management education level that soft skills and participation in co-curricular activities are the major deciding factors to predict employability and pre-placement job opportunity and marks secured in class 12 is one more factor that gets added to this list to predict salary. The paper can immensely help management graduates to focus on key aspects that can help to hone appropriate skills and also can help management institutions to select the right students for management programs.

Research limitations/implications

The analysis and the predictive model may apply to Indian B-Schools wherein the quality of students are almost the same or better. Predictive analytics has been used to explain the employability of management graduates alone and not any other.

Practical implications

The authors' study might be useful for those students who often fail to understand “what” skills are the most important predictors of their performance in the pre-placement and final-placement interviews. Moreover, the study may serve as a useful guide to those organizations that often face dilemmas to understand “how” to select an ideal candidate for the particular job profile from a campus.

Originality/value

The authors believe that the current study is one of the few studies that have attempted to examine the employability of management graduates using predictive analytics. The study further contradicts that the signaling theory in education does not help better explain the employability of the students in extremely high-paced business environments.