Machine learning approaches for prediction of early death among lung cancer patients with bone metastases using routine clinical characteristics: An analysis of 19,887 patients

Establishment and validation of an interactive artificial intelligence platform to predict postoperative ambulatory status for patients with metastatic spinal disease: a multicenter analysis

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.

Machine Learning Prediction of Tongue Pressure in Elderly Patients with Head and Neck Tumor: A Cross-Sectional Study

Background: This investigation sought to cross validate the predictors of tongue pressure recovery in elderly patients' post-treatment for head and neck tumors, leveraging advanced machine learning techniques. Methods: By employing logistic regression, support vector regression, random forest, and extreme gradient boosting, the study analyzed an array of variables including patient demographics, surgery types, dental health status, and age, drawn from comprehensive medical records and direct tongue pressure assessments. Results: Among the models, logistic regression emerged as the most effective, demonstrating an accuracy of 0.630 [95% confidence interval (CI): 0.370-0.778], F1 score of 0.688 [95% confidence interval (CI): 0.435-0.853], precision of 0.611 [95% confidence interval (CI): 0.313-0.801], recall of 0.786 [95% confidence interval (CI): 0.413-0.938] and an area under the receiver operating characteristic curve of 0.626 [95% confidence interval (CI): 0.409-0.806]. This model distinctly highlighted the significance of glossectomy (p = 0.039), the presence of functional teeth (p = 0.043), and the patient's age (p = 0.044) as pivotal factors influencing tongue pressure, setting the threshold for statistical significance at p < 0.05. Conclusions: The analysis underscored the critical role of glossectomy, the presence of functional natural teeth, and age as determinants of tongue pressure in logistics regression, with the presence of natural teeth and the tumor site located in the tongue consistently emerging as the key predictors across all computational models employed in this study.

Development and validation of an artificial intelligence mobile application for predicting 30-day mortality in critically ill patients with orthopaedic trauma

BACKGROUND

Given the intricate and grave nature of trauma-related injuries in ICU settings, it is imperative to develop and deploy reliable predictive tools that can aid in the early identification of high-risk patients who are at risk of early death. The objective of this study is to create and validate an artificial intelligence (AI) model that can accurately predict early mortality among critical fracture patients.

METHODS

A total of 2662 critically ill patients with orthopaedic trauma were included from the MIMIC III database. Early mortality was defined as death within 30 days in this study. The patients were randomly divided into a model training cohort and a model validation cohort. Various algorithms, including logistic regression (LR), extreme gradient boosting machine (eXGBM), decision tree (DT), support vector machine (SVM), random forest (RF), and neural network (NN), were employed. Evaluation metrics, including discrimination and calibration, were used to develop a comprehensive scoring system ranging from 0 to 60, with higher scores indicating better prediction performance. Furthermore, external validation was carried out using 131 patients. The optimal model was deployed as an internet-based AI tool.

RESULTS

Among all models, the eXGBM demonstrated the highest area under the curve (AUC) value (0.974, 95%CI: 0.959-0.983), followed by the RF model (0.951, 95%CI: 0.935-0.967) and the NN model (0.922, 95%CI: 0.905-0.941). Additionally, the eXGBM model outperformed other models in terms of accuracy (0.915), precision (0.906), recall (0.926), F1 score (0.916), Brier score (0.062), log loss (0.210), and discrimination slope (0.767). Based on the scoring system, the eXGBM model achieved the highest score (53), followed by RF (42) and NN (39). The LR, DT, and SVM models obtained scores of 28, 18, and 32, respectively. Decision curve analysis further confirmed the superior clinical net benefits of the eXGBM model. External validation of the model achieved an AUC value of 0.913 (95%CI: 0.878-0.948). Consequently, the model was deployed on the Internet at https://30-daymortalityincriticallyillpatients-fnfsynbpbp6rgineaspuim.streamlit.app/, allowing users to input patient features and obtain predicted risks of early mortality among critical fracture patients. Furthermore, the AI model successfully stratified patients into low or high risk of early mortality based on a predefined threshold and provided recommendations for appropriate therapeutic interventions.

CONCLUSION

This study successfully develops and validates an AI model, with the eXGBM algorithm demonstrating the highest predictive performance for early mortality in critical fracture patients. By deploying the model as a web-based AI application, healthcare professionals can easily access the tool, enabling them to predict 30-day mortality and aiding in the identification and management of high-risk patients among those critically ill with orthopedic trauma.

Efficacy of stereotactic body radiotherapy and response prediction using artificial intelligence in oligometastatic gynaecologic cancer

PURPOSE

We present a large real-world multicentric dataset of ovarian, uterine and cervical oligometastatic lesions treated with SBRT exploring efficacy and clinical outcomes. In addition, an exploratory machine learning analysis was performed.

METHODS

A pooled analysis of gynecological oligometastases in terms of efficacy and clinical outcomes as well an exploratory machine learning model to predict the CR to SBRT were carried out. The CR rate following radiotherapy (RT) was the study main endpoint. The secondary endpoints included the 2-year actuarial LC, DMFS, PFS, and OS.

RESULTS

501 patients from 21 radiation oncology institutions with 846 gynecological metastases were analyzed, mainly ovarian (53.1%) and uterine metastases(32.1%).Multiple fraction radiotherapy was used in 762 metastases(90.1%).The most frequent schedule was 24 Gy in 3 fractions(13.4%). CR was observed in 538(63.7%) lesions. The Machine learning analysis showed a poor ability to find covariates strong enough to predict CR in the whole series. Analyzing them separately, in uterine cancer, if RT dose≥78.3Gy, the CR probability was 75.4%; if volume was <13.7 cc, the CR probability became 85.1%. In ovarian cancer, if the lesion was a lymph node, the CR probability was 71.4%; if volume was <17 cc, the CR probability rose to 78.4%. No covariate predicted the CR for cervical lesions. The overall 2-year actuarial LC was 79.2%, however it was 91.5% for CR and 52.5% for not CR lesions(p < 0.001). The overall 2-year DMFS, PFS and OS rate were 27.3%, 24.8% and 71.0%, with significant differences between CR and not CR.

CONCLUSIONS

CR was substantially associated to patient outcomes in our series of gynecological cancer oligometastatic lesions. The ability to predict a CR through artificial intelligence could also drive treatment choices in the context of personalized oncology.

Development and validation of a web-based artificial intelligence prediction model to assess massive intraoperative blood loss for metastatic spinal disease using machine learning techniques

BACKGROUND CONTEXT

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.

PURPOSE

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.

STUDY DESIGN/SETTING

An observational cohort study.

PATIENT SAMPLE

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.

OUTCOME MEASURES

The primary outcome was massive intraoperative blood loss defined as an estimated blood loss of 2,500 cc or more.

METHODS

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.

RESULTS

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/.

CONCLUSIONS

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.

The impact of indirect notification of a cancer diagnosis and a risk model based on it to predict the prognosis of postoperative stage T3 esophageal cancer patients

Chinese doctors are required to inform patients' direct relatives of a cancer diagnosis rather than the patients themselves. The disease may be hidden from patients by their family members, which could result in severe outcomes. We selected postoperative T3 esophageal cancer (EsC) patients hospitalized from June 2015 to December 2019 as research subjects. The patients were divided into a direct-notification group and an indirect-notification group. Several variables were used to evaluate both groups' 36-month progress-free survival (PFS). A risk prediction model of prognosis based on the risk score was established, which was assessed using the area under the curve (AUC) of the receiver operating characteristic curve. One hundred and thirteen patients were enrolled in the training group and forty-eight in the validation group. Cox multivariate regression analysis revealed that males, late stage, poor pathological differentiation, and indirect notification were independent worse risk factors for postoperative T3 stage EsC patients at 36-month PFS (hazard ratio (HR) = 0.454, 95% confidence interval (CI): 0.254-0.812, P = .008; HR = 1.560, 95% CI: 1.006-2.420, P = .047; HR = 0.595, 95% CI: 0.378-0.936, P = .025; HR = 2.686, 95% CI: 1.679-4.297, P < 0.001, respectively). The type of notification was the best correlation factor. The risk score was calculated as follows: risk score = 0.988 × cancer notification (indirect = 1, direct = 0)-0.790 × sex (female = 1, Male = 0) + 0.445 × stage (IIIB = 1, IIA + IIB = 0)-0.519 × pathological differentiation (moderately + well = 1, poorly = 0). The model had a sensitivity of 64.8% and specificity of 81.8%, with the AUC at 0.717 (95% CI: 0.614-0.810) in internal verification, and a sensitivity of 56.8% and specificity of 100%, with the AUC at 0.705 (95% CI: 0.651-0.849) in external validation. The model had good internal and external stability. The model showed a Brier score of 0.18. Indirect notification of a cancer diagnosis was an important negative predictor of postoperative EsC patients' PFS. The model displayed good accuracy and stability in the prediction of risk for cancer progression.

Integrative analysis reveals a four-gene signature for predicting survival and immunotherapy response in colon cancer patients using bulk and single-cell RNA-seq data

Background

Colon cancer (CC) ranks as one of the leading causes of cancer-related mortality globally. Single-cell transcriptome sequencing (scRNA-seq) offers precise gene expression data for distinct cell types. This study aimed to utilize scRNA-seq and bulk transcriptome sequencing (bulk RNA-seq) data from CC samples to develop a novel prognostic model.

Methods

scRNA-seq data was downloaded from the GSE161277 database. R packages including "Seurat", "Harmony", and "singleR" were employed to categorize eight major cell types within normal and tumor tissues. By comparing tumor and normal samples, differentially expressed genes (DEGs) across these major cell types were identified. Gene Ontology (GO) enrichment analyses of DEGs for each cell type were conducted using "Metascape". DEGs-based signature construction involved Cox regression and least absolute shrinkage operator (LASSO) analyses, performed on The Cancer Genome Atlas (TCGA) training cohort. Validation occurred in the GSE39582 and GSE33382 datasets. The expression pattern of prognostic genes was verified using spatial transcriptome sequencing (ST-seq) data. Ultimately, an established prognostic nomogram based on the gene signature and age was established and calibrated. Sensitivity to chemotherapeutic drugs was predicted with the "oncoPredict" R package.

Results

Using scRNA-Seq data, we examined 33,213 cells, categorizing them into eight cell types within normal and tumor samples. GO enrichment analysis revealed various cancer-related pathways across DEGs in these cell types. Among the 55 DEGs identified via univariate Cox regression, four independent prognostic genes emerged: PTPN6, CXCL13, SPINK4, and NPDC1. Expression validation through ST-seq confirmed PTPN6 and CXCL13 predominance in immune cells, while SPINK4 and NPDC1 were relatively epithelial cell-specific. Creating a four-gene prognostic signature, Kaplan-Meier survival analyses emphasized higher risk scores correlating with unfavorable prognoses, confirmed across training and validation cohorts. The risk score emerged as an independent prognostic factor, supported by a reliable nomogram. Intriguingly, drug sensitivity analysis unveiled contrasting anti-cancer drug responses in the two risk groups, suggesting significant clinical implications.

Conclusion

We developed a novel prognostic four-gene risk model, and these genes may act as potential therapeutic targets for CC.

A Web-Based Calculator to Predict Early Death Among Patients With Bone Metastasis Using Machine Learning Techniques: Development and Validation Study

BACKGROUND

Patients with bone metastasis often experience a significantly limited survival time, and a life expectancy of <3 months is generally regarded as a contraindication for extensive invasive surgeries. In this context, the accurate prediction of survival becomes very important since it serves as a crucial guide in making clinical decisions.

OBJECTIVE

This study aimed to develop a machine learning-based web calculator that can provide an accurate assessment of the likelihood of early death among patients with bone metastasis.

METHODS

This study analyzed a large cohort of 118,227 patients diagnosed with bone metastasis between 2010 and 2019 using the data obtained from a national cancer database. The entire cohort of patients was randomly split 9:1 into a training group (n=106,492) and a validation group (n=11,735). Six approaches-logistic regression, extreme gradient boosting machine, decision tree, random forest, neural network, and gradient boosting machine-were implemented in this study. The performance of these approaches was evaluated using 11 measures, and each approach was ranked based on its performance in each measure. Patients (n=332) from a teaching hospital were used as the external validation group, and external validation was performed using the optimal model.

RESULTS

In the entire cohort, a substantial proportion of patients (43,305/118,227, 36.63%) experienced early death. Among the different approaches evaluated, the gradient boosting machine exhibited the highest score of prediction performance (54 points), followed by the neural network (52 points) and extreme gradient boosting machine (50 points). The gradient boosting machine demonstrated a favorable discrimination ability, with an area under the curve of 0.858 (95% CI 0.851-0.865). In addition, the calibration slope was 1.02, and the intercept-in-large value was -0.02, indicating good calibration of the model. Patients were divided into 2 risk groups using a threshold of 37% based on the gradient boosting machine. Patients in the high-risk group (3105/4315, 71.96%) were found to be 4.5 times more likely to experience early death compared with those in the low-risk group (1159/7420, 15.62%). External validation of the model demonstrated a high area under the curve of 0.847 (95% CI 0.798-0.895), indicating its robust performance. The model developed by the gradient boosting machine has been deployed on the internet as a calculator.

CONCLUSIONS

This study develops a machine learning-based calculator to assess the probability of early death among patients with bone metastasis. The calculator has the potential to guide clinical decision-making and improve the care of patients with bone metastasis by identifying those at a higher risk of early death.

Prediction of postoperative health-related quality of life among patients with metastatic spinal cord compression secondary to lung cancer

Background

Health-related quality of life (HRQoL) is a critical aspect of overall well-being for patients with lung cancer, particularly those with metastatic spinal cord compression (MSCC). However, there is currently a lack of universal evaluation of HRQoL in this specific patient population. The aim of this study was to develop a nomogram that can accurately predict HRQoL outcomes in patients with lung cancer-related MSCC.

Methods

A total of 119 patients diagnosed with MSCC secondary to lung cancer were prospectively collected for analysis in the study. The least absolute shrinkage and selection operator (LASSO) regression analysis, along with 10-fold cross-validation, was employed to select the most significant variables for inclusion in the nomogram. Discriminative and calibration abilities were assessed using the concordance index (C-index), discrimination slope, calibration plots, and goodness-of-fit tests. Net reclassification index (NRI) and integrated discrimination improvement (IDI) analyses were conducted to compare the nomogram's performance with and without the consideration of comorbidities.

Results

Four variables were selected to construct the final nomogram, including the Eastern Cooperative Oncology Group (ECOG) score, targeted therapy, anxiety scale, and number of comorbidities. The C-index was 0.87, with a discrimination slope of 0.47, indicating a favorable discriminative ability. Calibration plots and goodness-of-fit tests revealed a high level of consistency between the predicted and observed probabilities of poor HRQoL. The NRI (0.404, 95% CI: 0.074-0.734, p = 0.016) and the IDI (0.035, 95% CI: 0.004-0.066, p = 0.027) confirmed the superior performance of the nomogram with the consideration of comorbidities.

Conclusions

This study develops a prediction nomogram that can assist clinicians in evaluating postoperative HRQoL in patients with lung cancer-related MSCC. This nomogram provides a valuable tool for risk stratification and personalized treatment planning in this specific patient population.

Machine learning was used to predict risk factors for distant metastasis of pancreatic cancer and prognosis analysis

BACKGROUND

The mechanisms of distant metastasis in pancreatic cancer (PC) have not been elucidated, and this study aimed to explore the risk factors affecting the metastasis and prognosis of metastatic patients and to develop a predictive model.

METHOD

Clinical data from patients meeting criteria from 1990 to 2019 were obtained from the Surveillance, Epidemiology, and End Results (SEER) database, and two machine learning methods, random forest and support vector machine, combined with logistic regression, were used to explore risk factors influencing distant metastasis and to create nomograms. The performance of the model was validated using calibration curves and ROC curves based on the Shaanxi Provincial People's Hospital cohort. LASSO regression and Cox regression models were used to explore the independent risk factors affecting the prognosis of patients with distant PC metastases.

RESULTS

We found that independent risk factors affecting PC distant metastasis were: age, radiotherapy, chemotherapy, T and N; the independent risk factors for patient prognosis were: age, grade, bone metastasis, brain metastasis, lung metastasis, radiotherapy and chemotherapy.

CONCLUSION

Together, our study provides a method for risk factors and prognostic assessment for patients with distant PC metastases. The nomogram we developed can be used as a convenient individualized tool to facilitate aid in clinical decision making.

Prediction of Medical Disputes Between Health Care Workers and Patients in Terms of Hospital Legal Construction Using Machine Learning Techniques: Externally Validated Cross-Sectional Study

BACKGROUND

Medical disputes are a global public health issue that is receiving increasing attention. However, studies investigating the relationship between hospital legal construction and medical disputes are scarce. The development of a multicenter model incorporating machine learning (ML) techniques for the individualized prediction of medical disputes would be beneficial for medical workers.

OBJECTIVE

This study aimed to identify predictors related to medical disputes from the perspective of hospital legal construction and the use of ML techniques to build models for predicting the risk of medical disputes.

METHODS

This study enrolled 38,053 medical workers from 130 tertiary hospitals in Hunan province, China. The participants were randomly divided into a training cohort (34,286/38,053, 90.1%) and an internal validation cohort (3767/38,053, 9.9%). Medical workers from 87 tertiary hospitals in Beijing were included in an external validation cohort (26,285/26,285, 100%). This study used logistic regression and 5 ML techniques: decision tree, random forest, support vector machine, gradient boosting decision tree (GBDT), and deep neural network. In total, 12 metrics, including discrimination and calibration, were used for performance evaluation. A scoring system was developed to select the optimal model. Shapley additive explanations was used to generate the importance coefficients for characteristics. To promote the clinical practice of our proposed optimal model, reclassification of patients was performed, and a web-based app for medical dispute prediction was created, which can be easily accessed by the public.

RESULTS

Medical disputes occurred among 46.06% (17,527/38,053) of the medical workers in Hunan province, China. Among the 26 clinical characteristics, multivariate analysis demonstrated that 18 characteristics were significantly associated with medical disputes, and these characteristics were used for ML model development. Among the ML techniques, GBDT was identified as the optimal model, demonstrating the lowest Brier score (0.205), highest area under the receiver operating characteristic curve (0.738, 95% CI 0.722-0.754), and the largest discrimination slope (0.172) and Youden index (1.355). In addition, it achieved the highest metrics score (63 points), followed by deep neural network (46 points) and random forest (45 points), in the internal validation set. In the external validation set, GBDT still performed comparably, achieving the second highest metrics score (52 points). The high-risk group had more than twice the odds of experiencing medical disputes compared with the low-risk group.

CONCLUSIONS

We established a prediction model to stratify medical workers into different risk groups for encountering medical disputes. Among the 5 ML models, GBDT demonstrated the optimal comprehensive performance and was used to construct the web-based app. Our proposed model can serve as a useful tool for identifying medical workers at high risk of medical disputes. We believe that preventive strategies should be implemented for the high-risk group.

Development of a web-based calculator to predict three-month mortality among patients with bone metastases from cancer of unknown primary: An internally and externally validated study using machine-learning techniques

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.