RESUMO
BACKGROUND: Improvement in survival in patients with advanced cancer is accompanied by an increased probability of bone metastasis and related pathologic fractures (especially in the proximal femur). The few systems proposed and used to diagnose impending fractures owing to metastasis and to ultimately prevent future fractures have practical limitations; thus, novel screening tools are essential. A CT scan of the abdomen and pelvis is a standard modality for staging and follow-up in patients with cancer, and radiologic assessments of the proximal femur are possible with CT-based digitally reconstructed radiographs. Deep-learning models, such as convolutional neural networks (CNNs), may be able to predict pathologic fractures from digitally reconstructed radiographs, but to our knowledge, they have not been tested for this application. QUESTIONS/PURPOSES: (1) How accurate is a CNN model for predicting a pathologic fracture in a proximal femur with metastasis using digitally reconstructed radiographs of the abdomen and pelvis CT images in patients with advanced cancer? (2) Do CNN models perform better than clinicians with varying backgrounds and experience levels in predicting a pathologic fracture on abdomen and pelvis CT images without any knowledge of the patients' histories, except for metastasis in the proximal femur? METHODS: A total of 392 patients received radiation treatment of the proximal femur at three hospitals from January 2011 to December 2021. The patients had 2945 CT scans of the abdomen and pelvis for systemic evaluation and follow-up in relation to their primary cancer. In 33% of the CT scans (974), it was impossible to identify whether a pathologic fracture developed within 3 months after each CT image was acquired, and these were excluded. Finally, 1971 cases with a mean age of 59 ± 12 years were included in this study. Pathologic fractures developed within 3 months after CT in 3% (60 of 1971) of cases. A total of 47% (936 of 1971) were women. Sixty cases had an established pathologic fracture within 3 months after each CT scan, and another group of 1911 cases had no established pathologic fracture within 3 months after CT scan. The mean age of the cases in the former and latter groups was 64 ± 11 years and 59 ± 12 years, respectively, and 32% (19 of 60) and 53% (1016 of 1911) of cases, respectively, were female. Digitally reconstructed radiographs were generated with perspective projections of three-dimensional CT volumes onto two-dimensional planes. Then, 1557 images from one hospital were used for a training set. To verify that the deep-learning models could consistently operate even in hospitals with a different medical environment, 414 images from other hospitals were used for external validation. The number of images in the groups with and without a pathologic fracture within 3 months after each CT scan increased from 1911 to 22,932 and from 60 to 720, respectively, using data augmentation methods that are known to be an effective way to boost the performance of deep-learning models. Three CNNs (VGG16, ResNet50, and DenseNet121) were fine-tuned using digitally reconstructed radiographs. For performance measures, the area under the receiver operating characteristic curve, accuracy, sensitivity, specificity, precision, and F1 score were determined. The area under the receiver operating characteristic curve was used to evaluate three CNN models mainly, and the optimal accuracy, sensitivity, and specificity were calculated using the Youden J statistic. Accuracy refers to the proportion of fractures in the groups with and without a pathologic fracture within 3 months after each CT scan that were accurately predicted by the CNN model. Sensitivity and specificity represent the proportion of accurately predicted fractures among those with and without a pathologic fracture within 3 months after each CT scan, respectively. Precision is a measure of how few false-positives the model produces. The F1 score is a harmonic mean of sensitivity and precision, which have a tradeoff relationship. Gradient-weighted class activation mapping images were created to check whether the CNN model correctly focused on potential pathologic fracture regions. The CNN model with the best performance was compared with the performance of clinicians. RESULTS: DenseNet121 showed the best performance in identifying pathologic fractures; the area under the receiver operating characteristic curve for DenseNet121 was larger than those for VGG16 (0.77 ± 0.07 [95% CI 0.75 to 0.79] versus 0.71 ± 0.08 [95% CI 0.69 to 0.73]; p = 0.001) and ResNet50 (0.77 ± 0.07 [95% CI 0.75 to 0.79] versus 0.72 ± 0.09 [95% CI 0.69 to 0.74]; p = 0.001). Specifically, DenseNet121 scored the highest in sensitivity (0.22 ± 0.07 [95% CI 0.20 to 0.24]), precision (0.72 ± 0.19 [95% CI 0.67 to 0.77]), and F1 score (0.34 ± 0.10 [95% CI 0.31 to 0.37]), and it focused accurately on the region with the expected pathologic fracture. Further, DenseNet121 was less likely than clinicians to mispredict cases in which there was no pathologic fracture than cases in which there was a fracture; the performance of DenseNet121 was better than clinician performance in terms of specificity (0.98 ± 0.01 [95% CI 0.98 to 0.99] versus 0.86 ± 0.09 [95% CI 0.81 to 0.91]; p = 0.01), precision (0.72 ± 0.19 [95% CI 0.67 to 0.77] versus 0.11 ± 0.10 [95% CI 0.05 to 0.17]; p = 0.0001), and F1 score (0.34 ± 0.10 [95% CI 0.31 to 0.37] versus 0.17 ± 0.15 [95% CI 0.08 to 0.26]; p = 0.0001). CONCLUSION: CNN models may be able to accurately predict impending pathologic fractures from digitally reconstructed radiographs of the abdomen and pelvis CT images that clinicians may not anticipate; this can assist medical, radiation, and orthopaedic oncologists clinically. To achieve better performance, ensemble-learning models using knowledge of the patients' histories should be developed and validated. The code for our model is publicly available online at https://github.com/taehoonko/CNN_path_fx_prediction . LEVEL OF EVIDENCE: Level III, diagnostic study.
Assuntos
Neoplasias Ósseas , Fraturas Espontâneas , Humanos , Feminino , Pessoa de Meia-Idade , Idoso , Masculino , Fraturas Espontâneas/diagnóstico por imagem , Fraturas Espontâneas/etiologia , Tomografia Computadorizada por Raios X/métodos , Redes Neurais de Computação , Fêmur , Neoplasias Ósseas/complicações , Neoplasias Ósseas/diagnóstico por imagem , Pelve , AbdomeRESUMO
BACKGROUND: Cardiovascular magnetic resonance (CMR) is increasingly used for risk stratification in aortic stenosis (AS). However, the relative prognostic power of CMR markers and their respective thresholds remains undefined. OBJECTIVES: Using machine learning, the study aimed to identify prognostically important CMR markers in AS and their thresholds of mortality. METHODS: Patients with severe AS undergoing AVR (n = 440, derivation; n = 359, validation cohort) were prospectively enrolled across 13 international sites (median 3.8 years' follow-up). CMR was performed shortly before surgical or transcatheter AVR. A random survival forest model was built using 29 variables (13 CMR) with post-AVR death as the outcome. RESULTS: There were 52 deaths in the derivation cohort and 51 deaths in the validation cohort. The 4 most predictive CMR markers were extracellular volume fraction, late gadolinium enhancement, indexed left ventricular end-diastolic volume (LVEDVi), and right ventricular ejection fraction. Across the whole cohort and in asymptomatic patients, risk-adjusted predicted mortality increased strongly once extracellular volume fraction exceeded 27%, while late gadolinium enhancement >2% showed persistent high risk. Increased mortality was also observed with both large (LVEDVi >80 mL/m2) and small (LVEDVi ≤55 mL/m2) ventricles, and with high (>80%) and low (≤50%) right ventricular ejection fraction. The predictability was improved when these 4 markers were added to clinical factors (3-year C-index: 0.778 vs 0.739). The prognostic thresholds and risk stratification by CMR variables were reproduced in the validation cohort. CONCLUSIONS: Machine learning identified myocardial fibrosis and biventricular remodeling markers as the top predictors of survival in AS and highlighted their nonlinear association with mortality. These markers may have potential in optimizing the decision of AVR.
Assuntos
Estenose da Valva Aórtica , Fibrose/diagnóstico por imagem , Implante de Prótese de Valva Cardíaca , Imagem Cinética por Ressonância Magnética , Miocárdio/patologia , Remodelação Ventricular , Idoso , Estenose da Valva Aórtica/complicações , Estenose da Valva Aórtica/diagnóstico , Estenose da Valva Aórtica/mortalidade , Técnicas de Imagem Cardíaca/métodos , Feminino , Testes de Função Cardíaca/métodos , Implante de Prótese de Valva Cardíaca/métodos , Implante de Prótese de Valva Cardíaca/mortalidade , Humanos , Aprendizado de Máquina , Imagem Cinética por Ressonância Magnética/métodos , Imagem Cinética por Ressonância Magnética/estatística & dados numéricos , Masculino , Prognóstico , Reprodutibilidade dos Testes , Medição de Risco/métodos , Índice de Gravidade de Doença , Análise de SobrevidaRESUMO
PURPOSE: A blood transfusion after total knee arthroplasty (TKA) is associated with an increase in complication and infection rates. However, no studies have been conducted to predict transfusion after TKA using a machine learning algorithm. The purpose of this study was to identify informative preoperative variables to create a machine learning model, and to provide a web-based transfusion risk-assessment system for clinical use. METHODS: This study retrospectively reviewed 1686 patients who underwent TKA at our institution. Data for 43 preoperative variables, including medication history, laboratory values, and demographic characteristics, were collected. Variable selection was conducted using the recursive feature elimination algorithm. The transfusion group was defined as patients with haemoglobin (Hb) < 7 g/dL after TKA. A predictive model was developed using the gradient boosting machine, and the performance of the model was assessed by the area under the receiver operating characteristic curve (AUC). Data sets from an independent institution were tested with the model for external validation. RESULTS: Of the 1686 patients who underwent TKA, 108 (6.4%) were categorized into the transfusion group. Six preoperative variables were selected, including preoperative Hb, platelet count, type of surgery, tranexamic acid, age, and body weight. The predictive model demonstrated good predictive performance using the six variables [AUC 0.842; 95% confidence interval (CI) 0.820-0.856]. Performance was also good according to the external validation using 400 data from an independent institution (AUC 0.880; 95% CI 0.844-0.910). This web-based blood transfusion risk-assessment system can be accessed at http://safetka.net. CONCLUSIONS: A web-based predictive model for transfusion after TKA using a machine learning algorithm was developed using six preoperative variables. The model is simple, has been validated, showed good performance, and can be used before TKA to predict the risk of transfusion and guide appropriate precautions for high-risk patients. LEVEL OF EVIDENCE: Diagnostic level II.