Intraoperative blood loss is a significant concern in patients with metastatic spinal disease. Early identification of patients at high risk of experiencing massive intraoperative blood loss is crucial as it allows for the development of appropriate surgical plans and facilitates timely interventions. However, accurate prediction of intraoperative blood loss remains limited based on prior studies. The purpose of this study was to develop and validate a web-based artificial intelligence (AI) model to predict massive intraoperative blood loss during surgery for metastatic spinal disease. An observational cohort study. Two hundred seventy-six patients with metastatic spinal tumors undergoing decompressive surgery from two hospitals were included for analysis. Of these, 200 patients were assigned to the derivation cohort for model development and internal validation, while the remaining 76 were allocated to the external validation cohort. The primary outcome was massive intraoperative blood loss defined as an estimated blood loss of 2,500 cc or more. Data on patients' demographics, tumor conditions, oncological therapies, surgical strategies, and laboratory examinations were collected in the derivation cohort. SMOTETomek resampling (which is a combination of Synthetic Minority Oversampling Technique and Tomek Links Undersampling) was performed to balance the classes of the dataset and obtain an expanded dataset. The patients were randomly divided into two groups in a proportion of 7:3, with the most used for model development and the remaining for internal validation. External validation was performed in another cohort of 76 patients with metastatic spinal tumors undergoing decompressive surgery from a teaching hospital. The logistic regression (LR) model, and five machine learning models, including K-Nearest Neighbor (KNN), Decision Tree (DT), XGBoosting Machine (XGBM), Random Forest (RF), and Support Vector Machine (SVM), were used to develop prediction models. Model prediction performance was evaluated using area under the curve (AUC), recall, specificity, F1 score, Brier score, and log loss. A scoring system incorporating 10 evaluation metrics was developed to comprehensively evaluate the prediction performance. The incidence of massive intraoperative blood loss was 23.50% (47/200). The model features were comprised of five clinical variables, including tumor type, smoking status, Eastern Cooperative Oncology Group (ECOG) score, surgical process, and preoperative platelet level. The XGBM model performed the best in AUC (0.857 [95% CI: 0.827, 0.877]), accuracy (0.771), recall (0.854), F1 score (0.787), Brier score (0.150), and log loss (0.461), and the RF model ranked second in AUC (0.826 [95% CI: 0.793, 0.861]) and precise (0.705), whereas the AUC of the LR model was only 0.710 (95% CI: 0.665, 0.771), the accuracy was 0.627, the recall was 0.610, and the F1 score was 0.617. According to the scoring system, the XGBM model obtained the highest total score of 55, which signifies the best predictive performance among the evaluated models. External validation showed that the AUC of the XGBM model was also up to 0.809 (95% CI: 0.778, 0.860) and the accuracy was 0.733. The XGBM model, was further deployed online, and can be freely accessed at https://starxueshu-massivebloodloss-main-iudy71.streamlit.app/. The XGBM model may be a useful AI tool to assess the risk of intraoperative blood loss in patients with metastatic spinal disease undergoing decompressive surgery.

Purpose: Bone is one of the most common sites for the spread of malignant tumors. Patients with bone metastases whose prognosis was shorter than 3 months (early death) were considered as surgical contraindications. However, the information currently available in the literature limits our capacity to assess the risk likelihood of 3 month mortality. As a result, the study's objective is to create an accurate prediction model utilizing machine-learning techniques to predict 3 month mortality specifically among lung cancer patients with bone metastases according to easily available clinical data.Methods: This study enrolled 19,887 lung cancer patients with bone metastases between 2010 and 2018 from a large oncologic database in the United States. According to a ratio of 8:2, the entire patient cohort was randomly assigned to a training (n = 15881, 80%) and validation (n = 4,006, 20%) group. In the training group, prediction models were trained and optimized using six approaches, including logistic regression, XGBoosting machine, random forest, neural network, gradient boosting machine, and decision tree. There were 13 metrics, including the Brier score, calibration slope, intercept-in-large, area under the curve (AUC), and sensitivity, used to assess the model's prediction performance in the validation group. In each metric, the best prediction effectiveness was assigned six points, while the worst was given one point. The model with the highest sum score of the 13 measures was optimal. The model's explainability was performed using the local interpretable model-agnostic explanation (LIME) according to the optimal model. Predictor importance was assessed using H₂O automatic machine learning. Risk stratification was also evaluated based on the optimal threshold.Results: Among all recruited patients, the 3 month mortality was 48.5%. Twelve variables, including age, primary site, histology, race, sex, tumor (T) stage, node (N) stage, brain metastasis, liver metastasis, cancer-directed surgery, radiation, and chemotherapy, were significantly associated with 3 month mortality based on multivariate analysis, and these variables were included for developing prediction models. With the highest sum score of all the measurements, the gradient boosting machine approach outperformed all the other models (62 points), followed by the XGBooting machine approach (59 points) and logistic regression (53). The area under the curve (AUC) was 0.820 (95% confident interval [CI]: 0.807–0.833), 0.820 (95% CI: 0.807–0.833), and 0.815 (95% CI: 0.801–0.828), respectively, calibration slope was 0.97, 0.95, and 0.96, respectively, and accuracy was all 0.772. Explainability of models was conducted to rank the predictors and visualize their contributions to an individual's mortality outcome. The top four important predictors in the population according to H₂O automatic machine learning were chemotherapy, followed by liver metastasis, radiation, and brain metastasis. Compared to patients in the low-risk group, patients in the high-risk group were more than three times the odds of dying within 3 months (P < 0.001).Conclusions: Using machine learning techniques, this study offers a number of models, and the optimal model is found after thoroughly assessing and contrasting the prediction performance of each model. The optimal model can be a pragmatic risk prediction tool and is capable of identifying lung cancer patients with bone metastases who are at high risk for 3 month mortality, informing risk counseling, and aiding clinical treatment decision-making. It is better advised for patients in the high-risk group to have radiotherapy alone, the best supportive care, or minimally invasive procedures like cementoplasty.

Background: Identification of patients with high-risk of experiencing inability to walk after surgery is important for surgeons to make therapeutic strategies for patients with metastatic spinal disease. However, there is a lack of clinical tool to assess postoperative ambulatory status for those patients. The emergence of artificial intelligence (AI) brings a promising opportunity to develop accurate prediction models. Methods: This study collected 455 patients with metastatic spinal disease who underwent posterior decompressive surgery at three tertiary medical institutions. Of these, 220 patients were collected from one medical institution to form the model derivation cohort, while 89 and 146 patients were collected from two other medical institutions to form the external validation cohorts 1 and 2, respectively. Patients in the model derivation cohort were used to develop and internally validate models. To establish the interactive AI platform, machine learning techniques were used to develop prediction models, including logistic regression (LR), decision tree (DT), random forest (RF), extreme gradient boosting machine (eXGBM), support vector machine (SVM), and neural network (NN). Furthermore, to enhance the resilience of the study’s model, an ensemble machine learning approach was employed using a soft-voting method by combining the results of the above six algorithms. A scoring system incorporating 10 evaluation metrics was used to comprehensively assess the prediction performance of the developed models. The scoring system had a total score of 0 to 60, with higher scores denoting better prediction performance. An interactive AI platform was further deployed via Streamlit. The prediction performance was compared between medical experts and the AI platform in assessing the risk of experiencing postoperative inability to walk among patients with metastatic spinal disease. Results: Among all developed models, the ensemble model outperformed the six other models with the highest score of 57, followed by the eXGBM model (54), SVM model (50), and NN model (50). The ensemble model had the best performance in accuracy and calibration slope, and the second-best performance in precise, recall, specificity, area under the curve (AUC), Brier score, and log loss. The scores of the LR model, RF model, and DT model were 39, 46, and 26, respectively. External validation demonstrated that the ensemble model had an AUC value of 0.873 (95% CI: 0.809–0.936) in the external validation cohort 1 and 0.924 (95% CI: 0.890–0.959) in the external validation cohort 2. In the new ensemble machine learning model excluding the feature of the number of comorbidities, the AUC value was still as high as 0.916 (95% CI: 0.863–0.969). In addition, the AUC values of the new model were 0.880 (95% CI: 0.819–0.940) in the external validation cohort 1 and 0.922 (95% CI: 0.887–0.958) in the external validation cohort 2, indicating favorable generalization of the model. The interactive AI platform was further deployed online based on the final machine learning model, and it was available at https://postoperativeambulatory-izpdr6gsxxwhitr8fubutd.streamlit.app/. By using the AI platform, researchers were able to obtain the individual predicted risk of postoperative inability to walk, gain insights into the key factors influencing the outcome, and find the stratified therapeutic recommendations. The AUC value obtained from the AI platform was significantly higher than the average AUC value achieved by the medical experts (P<0.001), denoting that the AI platform obviously outperformed the individual medical experts. Conclusions: The study successfully develops and validates an interactive AI platform for evaluating the risk of postoperative loss of ambulatory ability in patients with metastatic spinal disease. This AI platform has the potential to serve as a valuable model for guiding healthcare professionals in implementing surgical plans and ultimately enhancing patient outcomes.

Background: Individualized therapeutic strategies can be carried out under the guidance of expected lifespan, hence survival prediction is important. Nonetheless, reliable survival estimation in individuals with bone metastases from cancer of unknown primary (CUP) is still scarce. The objective of the study is to construct a model as well as a web-based calculator to predict three-month mortality among bone metastasis patients with CUP using machine learning-based techniques.Methods: This study enrolled 1010 patients from a large oncological database, the Surveillance, Epidemiology, and End Results (SEER) database, in the United States between 2010 and 2018. The entire patient population was classified into two cohorts at random: a training cohort (n=600, 60%) and a validation cohort (410, 40%). Patients from the validation cohort were used to validate models after they had been developed using the four machine learning approaches of random forest, gradient boosting machine, decision tree, and eXGBoosting machine on patients from the training cohort. In addition, 101 patients from two large teaching hospital were served as an external validation cohort. To evaluate each model’s ability to predict the outcome, prediction measures such as area under the receiver operating characteristic (AUROC) curves, accuracy, and Youden index were generated. The study’s risk stratification was done using the best cut-off value. The Streamlit software was used to establish a web-based calculator.Results: The three-month mortality was 72.38% (731/1010) in the entire cohort. The multivariate analysis revealed that older age (P=0.031), lung metastasis (P=0.012), and liver metastasis (P=0.008) were risk contributors for three-month mortality, while radiation (P=0.002) and chemotherapy (P<0.001) were protective factors. The random forest model showed the highest area under curve (AUC) value (0.796, 95% CI: 0.746-0.847), the second-highest precision (0.876) and accuracy (0.778), and the highest Youden index (1.486), in comparison to the other three machine learning approaches. The AUC value was 0.748 (95% CI: 0.653-0.843) and the accuracy was 0.745, according to the external validation cohort. Based on the random forest model, a web calculator was established: https://starxueshu-codeok-main-8jv2ws.streamlitapp.com/. When compared to patients in the low-risk groups, patients in the high-risk groups had a 1.99 times higher chance of dying within three months in the internal validation cohort and a 2.37 times higher chance in the external validation cohort (Both P<0.001).Conclusions: The random forest model has promising performance with favorable discrimination and calibration. This study suggests a web-based calculator based on the random forest model to estimate the three-month mortality among bone metastases from CUP, and it may be a helpful tool to direct clinical decision-making, inform patients about their prognosis, and facilitate therapeutic communication between patients and physicians.

To investigate the epidemiology of cement leaks and further develop an algorithm to detect the high risk of cement leaks among advanced cancer patients with metastatic spinal disease treated with percutaneous vertebroplasty. This study retrospectively analyzed 309 patients with metastatic spinal disease treated with percutaneous vertebroplasty. Patients were randomly divided into a training group and a validation group. In the training group, 13 potential characteristics were analyzed for their abilities to predict cement leaks. Discal cement leakage and paravertebral cement leakage were excluded from the analysis. Those characteristics identified as having significant predictive value were used to develop a predictive algorithm. Internal validation of the algorithm was performed based on discrimination and calibration qualities. Overall, cement leaks occurred in 61.17% (189/309) patients. Among the 13 characteristics analyzed, younger age (P = 0.03), extravertebral bone metastases (P = 0.02), increased number of treated vertebrae levels (P < 0.01), and cortical osteolytic destruction in the posterior wall (P = 0.01) were included in the algorithm. This algorithm generates a score between 0 and 16 points, with higher scores indicating a higher risk of cement leakage. The area under the receiver operating characteristic curve (AUROC) value for the algorithm was 0.75 in the training group and 0.69 in the validation group. The mean correct classification rates for the training and validation groups were 73.5% and 64.9%, respectively, and the corresponding P-values of the goodness-of-fit test were 0.70 and 0.50. Cement leaks are common in patients with metastatic spinal disease treated with percutaneous vertebroplasty. The present study proposed and internally validated an algorithm that can be used to screen patients at high risk of cement leakage.

Background: Treatment of metastatic spinal disease often involves surgical intervention; however, surgical site infections (SSIs) pose a great challenge for spine surgeons. At present, there is an absence of reliable clinical tools for predicting SSI, which can adversely affect treatment decisions and overall patient management. This study aims to construct and validate an application to stratify the patients at high risk of SSI among those with metastatic spinal disease using an artificial intelligence (AI) approach. Methods: A total of 667 patients diagnosed with metastatic spinal disease were enrolled in this study to train and validate models. Patients in the model-derivation cohort ( n = 485) from two tertiary medical institutions were randomly divided into two groups at a ratio of 8:2, with the most patients belonging to the model-training group and the remaining patients classified into the model-validation group. External validation was conducted among patients ( n = 182) from another tertiary medical institution. Logistic Regression and five machine learning algorithms, including support vector machine, gradient boosting machine (GBM), K-nearest neighbor (KNN), neural network (NN), and decision tree, were used to train and optimize models. The predictive performance of the models was assessed through both discrimination and calibration. The model demonstrating the best prediction accuracy was selected as the AI platform for assessing the risk of SSI in patients with metastatic spinal disease. To evaluate the clinical utility of our AI model, we conducted a comparative study involving 100 patients undergoing surgery for metastatic spinal disease at one tertiary medical institution. Results: The incidence of SSI in spinal metastasis surgeries was 6.4% in the model derivation cohort and 7.7% in the external validation cohort. Among all models, the GBM model had the highest area under the curve (AUC) value (0.986, 95% confidence interval [CI]: 0.972–1.000), followed by the KNN model (0.962, 95% CI: 0.933–0.991), and the NN model (0.944, 95% CI: 0.914–0.974). The GBM model also had the best prediction performance in terms of accuracy, precision, recall, F1 score, Brier score, and log loss. The calibration curve revealed the GBM model had favorable calibration ability, and decision curve analysis showed the GBM model had significant net clinical benefits in various risk thresholds. External validation generated an AUC value of the model of 0.848 (95% CI: 0.806–0.890). Surgery time, tumor type, and number of comorbidities were identified as the most three influential factors for postoperative SSI. The AI application achieved significantly higher accuracy than clinician assessments (AUC: 0.986 vs. 0.572–0.627, P < 0.001). Sensitivity analysis confirmed robustness across subgroups (e.g. diabetes, visceral metastases). Conclusions: This study develops and validates an AI tool with strong predictive performance in identifying patients at a high risk for SSI. By facilitating personalized treatment based on risk classification, this advancement has the potential to significantly enhance surgical care for patients with metastatic spinal disease. Future research should focus on integrating this predictive tool into clinical practice and exploring its applicability across diverse patient populations.