Dataset Information

Artificial Intelligence-Based Prognostic Model for Urologic Cancers: A SEER-Based Study.

ABSTRACT:

Background

Prognostication is essential to determine the risk profile of patients with urologic cancers.

Methods

We utilized the SEER national cancer registry database with approximately 2 million patients diagnosed with urologic cancers (penile, testicular, prostate, bladder, ureter, and kidney). The cohort was randomly divided into the development set (90%) and the out-held test set (10%). Modeling algorithms and clinically relevant parameters were utilized for cancer-specific mortality prognosis. The model fitness for the survival estimation was assessed using the differences between the predicted and observed Kaplan-Meier estimates on the out-held test set. The overall concordance index (c-index) score estimated the discriminative accuracy of the survival model on the test set. A simulation study assessed the estimated minimum follow-up duration and time points with the risk stability.

Results

We achieved a well-calibrated prognostic model with an overall c-index score of 0.800 (95% CI: 0.795-0.805) on the representative out-held test set. The simulation study revealed that the suggestions for the follow-up duration covered the minimum duration and differed by the tumor dissemination stages and affected organs. Time points with a high likelihood for risk stability were identifiable.

Conclusions

A personalized temporal survival estimation is feasible using artificial intelligence and has potential application in clinical settings, including surveillance management.

SUBMITTER: Eminaga O

PROVIDER: S-EPMC9264864 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:Introduction: Prognostic scores are important tools in oncology to facilitate clinical decision-making based on patient characteristics. To date, classic survival analysis using Cox proportional hazards regression has been employed in the development of these prognostic scores. With the advance of analytical models, this study aimed to determine if more complex machine-learning algorithms could outperform classical survival analysis methods. Methods: In this benchmarking study, two datasets were used to develop and compare different prognostic models for overall survival in pan-cancer populations: a nationwide EHR-derived de-identified database for training and in-sample testing and the OAK (phase III clinical trial) dataset for out-of-sample testing. A real-world database comprised 136K first-line treated cancer patients across multiple cancer types and was split into a 90% training and 10% testing dataset, respectively. The OAK dataset comprised 1,187 patients diagnosed with non-small cell lung cancer. To assess the effect of the covariate number on prognostic performance, we formed three feature sets with 27, 44 and 88 covariates. In terms of methods, we benchmarked ROPRO, a prognostic score based on the Cox model, against eight complex machine-learning models: regularized Cox, Random Survival Forests (RSF), Gradient Boosting (GB), DeepSurv (DS), Autoencoder (AE) and Super Learner (SL). The C-index was used as the performance metric to compare different models. Results: For in-sample testing on the real-world database the resulting C-index [95% CI] values for RSF 0.720 [0.716, 0.725], GB 0.722 [0.718, 0.727], DS 0.721 [0.717, 0.726] and lastly, SL 0.723 [0.718, 0.728] showed significantly better performance as compared to ROPRO 0.701 [0.696, 0.706]. Similar results were derived across all feature sets. However, for the out-of-sample validation on OAK, the stronger performance of the more complex models was not apparent anymore. Consistently, the increase in the number of prognostic covariates did not lead to an increase in model performance. Discussion: The stronger performance of the more complex models did not generalize when applied to an out-of-sample dataset. We hypothesize that future research may benefit by adding multimodal data to exploit advantages of more complex models.

Project description:An increasing body of evidence supports the association of immune genes with tumorigenesis and prognosis of breast cancer (BC). This research aims at exploring potential regulatory mechanisms and identifying immunogenic prognostic markers for BC, which were used to construct a prognostic signature for disease-free survival (DFS) of BC based on artificial intelligence algorithms. Differentially expressed immune genes were identified between normal tissues and tumor tissues. Univariate Cox regression identified potential prognostic immune genes. Thirty-four transcription factors and 34 immune genes were used to develop an immune regulatory network. The artificial intelligence survival prediction system was developed based on three artificial intelligence algorithms. Multivariate Cox analyses determined 17 immune genes (ADAMTS8, IFNG, XG, APOA5, SIAH2, C2CD2, STAR, CAMP, CDH19, NTSR1, PCDHA1, AMELX, FREM1, CLEC10A, CD1B, CD6, and LTA) as prognostic biomarkers for BC. A prognostic nomogram was constructed on these prognostic genes. Concordance indexes were 0.782, 0.734, and 0.735 for 1-, 3-, and 5- year DFS. The DFS in high-risk group was significantly worse than that in low-risk group. Artificial intelligence survival prediction system provided three individual mortality risk predictive curves based on three artificial intelligence algorithms. In conclusion, comprehensive bioinformatics identified 17 immune genes as potential prognostic biomarkers, which might be potential candidates of immunotherapy targets in BC patients. The current study depicted regulatory network between transcription factors and immune genes, which was helpful to deepen the understanding of immune regulatory mechanisms for BC cancer. Two artificial intelligence survival predictive systems are available at https://zhangzhiqiao7.shinyapps.io/Smart_Cancer_Survival_Predictive_System_16_BC_C1005/ and https://zhangzhiqiao8.shinyapps.io/Gene_Survival_Subgroup_Analysis_16_BC_C1005/. These novel artificial intelligence survival predictive systems will be helpful to improve individualized treatment decision-making.

Project description:BackgroundSurgical site infection (SSI) is one of the most common types of health care-associated infections. It increases mortality, prolongs hospital length of stay, and raises health care costs. Many institutions developed risk assessment models for SSI to help surgeons preoperatively identify high-risk patients and guide clinical intervention. However, most of these models had low accuracies.ObjectiveWe aimed to provide a solution in the form of an Artificial intelligence-based Multimodal Risk Assessment Model for Surgical site infection (AMRAMS) for inpatients undergoing operations, using routinely collected clinical data. We internally and externally validated the discriminations of the models, which combined various machine learning and natural language processing techniques, and compared them with the National Nosocomial Infections Surveillance (NNIS) risk index.MethodsWe retrieved inpatient records between January 1, 2014, and June 30, 2019, from the electronic medical record (EMR) system of Rui Jin Hospital, Luwan Branch, Shanghai, China. We used data from before July 1, 2018, as the development set for internal validation and the remaining data as the test set for external validation. We included patient demographics, preoperative lab results, and free-text preoperative notes as our features. We used word-embedding techniques to encode text information, and we trained the LASSO (least absolute shrinkage and selection operator) model, random forest model, gradient boosting decision tree (GBDT) model, convolutional neural network (CNN) model, and self-attention network model using the combined data. Surgeons manually scored the NNIS risk index values.ResultsFor internal bootstrapping validation, CNN yielded the highest mean area under the receiver operating characteristic curve (AUROC) of 0.889 (95% CI 0.886-0.892), and the paired-sample t test revealed statistically significant advantages as compared with other models (P<.001). The self-attention network yielded the second-highest mean AUROC of 0.882 (95% CI 0.878-0.886), but the AUROC was only numerically higher than the AUROC of the third-best model, GBDT with text embeddings (mean AUROC 0.881, 95% CI 0.878-0.884, P=.47). The AUROCs of LASSO, random forest, and GBDT models using text embeddings were statistically higher than the AUROCs of models not using text embeddings (P<.001). For external validation, the self-attention network yielded the highest AUROC of 0.879. CNN was the second-best model (AUROC 0.878), and GBDT with text embeddings was the third-best model (AUROC 0.872). The NNIS risk index scored by surgeons had an AUROC of 0.651.ConclusionsOur AMRAMS based on EMR data and deep learning methods-CNN and self-attention network-had significant advantages in terms of accuracy compared with other conventional machine learning methods and the NNIS risk index. Moreover, the semantic embeddings of preoperative notes improved the model performance further. Our models could replace the NNIS risk index to provide personalized guidance for the preoperative intervention of SSIs. Through this case, we offered an easy-to-implement solution for building multimodal RAMs for other similar scenarios.

Project description:ObjectivesTo develop and validate a novel interpretable artificial intelligence (AI) model that integrates radiomic features, deep learning features, and imaging features at multiple semantic levels to predict the prognosis of intracerebral hemorrhage (ICH) patients at 6 months post-onset.Materials and methodsRetrospectively enrolled 222 patients with ICH for Non-contrast Computed Tomography (NCCT) images and clinical data, who were divided into a training cohort (n = 186, medical center 1) and an external testing cohort (n = 36, medical center 2). Following image preprocessing, the entire hematoma region was segmented by two radiologists as the volume of interest (VOI). Pyradiomics algorithm library was utilized to extract 1762 radiomics features, while a deep convolutional neural network (EfficientnetV2-L) was employed to extract 1000 deep learning features. Additionally, radiologists evaluated imaging features. Based on the three different modalities of features mentioned above, the Random Forest (RF) model was trained, resulting in three models (Radiomics Model, Radiomics-Clinical Model, and DL-Radiomics-Clinical Model). The performance and clinical utility of the models were assessed using the Area Under the Receiver Operating Characteristic Curve (AUC), calibration curve, and Decision Curve Analysis (DCA), with AUC compared using the DeLong test. Furthermore, this study employs three methods, Shapley Additive Explanations (SHAP), Grad-CAM, and Guided Grad-CAM, to conduct a multidimensional interpretability analysis of model decisions.ResultsThe Radiomics-Clinical Model and DL-Radiomics-Clinical Model exhibited relatively good predictive performance, with an AUC of 0.86 [95% Confidence Intervals (CI): 0.71, 0.95; P < 0.01] and 0.89 (95% CI: 0.74, 0.97; P < 0.01), respectively, in the external testing cohort.ConclusionThe multimodal explainable AI model proposed in this study can accurately predict the prognosis of ICH. Interpretability methods such as SHAP, Grad-CAM, and Guided Grad-Cam partially address the interpretability limitations of AI models. Integrating multimodal imaging features can effectively improve the performance of the model.Clinical relevance statementPredicting the prognosis of patients with ICH is a key objective in emergency care. Accurate and efficient prognostic tools can effectively prevent, manage, and monitor adverse events in ICH patients, maximizing treatment outcomes.

Project description:BackgroundArtificial intelligence (AI) has become a powerful tool and is attracting more attention in the field of medicine. There are a number of AI studies focusing on skin diseases, and there are many AI products that have been applied in dermatology. However, the attitudes of dermatologists, specifically those from China, towards AI, is not clear as few, if any studies have focused on this issue.MethodsA web-based questionnaire was designed by experts from the Chinese Skin Image Database (CSID) and published on the UMER Doctor platform (an online learning platform for dermatologists developed by the Shanghai Wheat Color Intelligent Technology Company, China). A total of 1,228 Chinese dermatologists were recruited and provided answers to the questionnaire online. The differences of dermatologists' attitudes towards AI among the different groups (stratified by age, gender, hospital level, education degree, professional title, and hospital ownership) were compared by using the Mann-Whitney U test and the Kruskal-Wallis H test. The correlations between stratified factors and dermatologists' attitudes towards AI were calculated by using the Spearman's rank correlation test. SPSS (version 22.0) was utilized for all analyses. A two-sided P value <0.05 was considered statistically significant in all analyses.ResultsA total of 1,228 Chinese dermatologists from 30 provinces, autonomous regions, municipalities, and other regions (including Hong Kong, Macau, and Taiwan) participated in this survey. The dermatologists who participated acquired AI-related information mainly through the Internet, meetings or forums, and 70.51% of participated dermatologists acquired AI-related information by two or more approaches. In total, 99.51% of participated dermatologists pay attention (general, passive-active, and active attention) to information pertaining to AI. Stratified analyses revealed statistically significant differences in their attention levels (unconcerned, general, passive-active, and active attention) to AI-related information by gender, hospital level, education degree, and professional title (P values ≤1.79E-02). In total, 95.36% of the participated dermatologists thought the role of AI to be in "assisting the daily diagnosis and treatment activities for dermatologists". Stratified analyses about the thought of AI roles (unconcerned, useless, assist, and replace) showed that there was no statistically significant difference except for the hospital level (P value =4.09E-03). The correlations between stratified factors with attention levels and the opinions of AI roles showed extremely weak correlations. Furthermore, 64.17% of participated dermatologists thought secondary hospitals in China are in most need of the application AI, and 91.78% of participated dermatologists thought the priority implementation of AI should be in skin tumors.ConclusionsThe majority of Chinese dermatologists are interested in AI information and acquired information about AI through a variety of approaches. Nearly all dermatologists are attentive to information on AI and think the role of AI is in "assisting the daily diagnosis and treatment activities for dermatologists". Future AI implementation should be primarily focused on skin tumors and utilized in in secondary hospitals.