P–016 Using artificial intelligence to predict semen upgrading after microsurgical varicocele repair

2021 ◽  
Vol 36 (Supplement_1) ◽  
Author(s):  
J Ory ◽  
M Tradewell ◽  
T Lima ◽  
U Blankstein ◽  
V Madhusoodanan ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Random Forest ◽  
External Validation ◽  
Sperm Concentration ◽  
Random Forest Model ◽  
Forest Model ◽  
Intelligence Models ◽  
Artificial Intelligence Models ◽  
Clinically Significant ◽  
Varicocele Repair

Abstract Study question Can we use artificial intelligence models to predict semen upgrading after microsurgical varicocele repair? Summary answer A machine learning model performed well in predicting clinically meaningful post-varicocelectomy semen upgrade using pre-operative hormonal, clinical, and semen analysis data. What is known already Varicocele repair is recommended in the presence of a clinical varicocele together with at least one abnormal semen parameter, and male infertility. Unfortunately, up to 50% of men who meet criteria for repair will not see meaningful benefit in outcomes despite successful surgery. Nomograms exist to help predict success, but these are based out of single-center databases, do not incorporate hormonal data, and are rarely designed to predict pre-defined, clinically meaningful improvements in semen parameters. Study design, size, duration Data were collected from an international, multi-center retrospective cohort. A total of 240 men were identified. Data from 160 men from Miami, USA and 80 men from Toronto, Canada were included. Data was collected from 2006 to 2020. Participants/materials, setting, methods We collected pre and postoperative clinical data following varicocele surgery. Clinical upgrading was defined as an increase in sperm concentration that would allow a couple to access new reproductive technologies/techniques. The tiers used for upgrading were 0–1million/cc (Intracytoplasmic Sperm Injection), 1–5 million (In Vitro Fertilization), 5–15 million (Intrauterine Insemination), and >15 million (Natural conception). Artificial intelligence models were trained and tested using R to predict which patients upgraded after surgery. Main results and the role of chance 51% of men underwent bilateral varicocele repair. The majority of men had grade 2 varicocele on the left, and (when present) a grade 1 varicocele on the right. Overall, 47% of men experienced an upgrade following varicocele surgery, 47% did not change, and 6% downgraded. The data from Miami were used to create a random forest model for predicting clinically significant upgrade in sperm concentration. The most informative model parameters were preoperative FSH, sperm concentration, and surgical laterality. The model identified three clinical categories: men with unfavorable, intermediate, and favorable features to predict varicocele upgrade. On external validation using data from Toronto, the model accurately predicted upgrade in 87% of men with favorable features, and in 49% and 36% of men with intermediate and unfavorable features, respectively. Overall, the model performed well on external validation with an AUC of 0.72 and good calibration. Calibration plots, using cross-validation, define how well the predicted probabilities match the actual probability of sperm concentration upgrade. The random forest model was run twelve times. All model characteristics are the mean of ten model runs with the highest and lowest performing runs removed. The model was translated to an online calculator that can be used by clinicians. Limitations, reasons for caution One limitation to our study is that we were not able to predict total motile sperm count (TMSC), which has been shown to perform slightly better than concentration at predicting assisted reproduction outcomes. By focusing on clinically significant upgrading, this difference should be minimized. Wider implications of the findings: Predicting the chances of clinically significant semen upgrading after varicocele repair is essential for patients and clinicians to understand. Several men undergo surgery with no subsequent benefit, which may lead to a delay in definitive treatment with IVF/IUI. Understanding their chances will help couples make better informed decisions moving forward. Trial registration number Not applicable

scholarly journals Machine Learning Approach Using Routine Immediate Postoperative Laboratory Values for Predicting Postoperative Mortality

2021 ◽  
Vol 11 (12) ◽  
pp. 1271
Author(s):  
Jaehyeong Cho ◽  
Jimyung Park ◽  
Eugene Jeong ◽  
Jihye Shin ◽  
Sangjeong Ahn ◽  
...  
Keyword(s):  
Machine Learning ◽  
Random Forest ◽  
Prediction Models ◽  
External Validation ◽  
Model Development ◽  
Postoperative Mortality ◽  
Random Forest Model ◽  
Forest Model ◽  
Laboratory Values ◽  
Increased Risk

Background: Several prediction models have been proposed for preoperative risk stratification for mortality. However, few studies have investigated postoperative risk factors, which have a significant influence on survival after surgery. This study aimed to develop prediction models using routine immediate postoperative laboratory values for predicting postoperative mortality. Methods: Two tertiary hospital databases were used in this research: one for model development and another for external validation of the resulting models. The following algorithms were utilized for model development: LASSO logistic regression, random forest, deep neural network, and XGBoost. We built the models on the lab values from immediate postoperative blood tests and compared them with the SASA scoring system to demonstrate their efficacy. Results: There were 3817 patients who had immediate postoperative blood test values. All models trained on immediate postoperative lab values outperformed the SASA model. Furthermore, the developed random forest model had the best AUROC of 0.82 and AUPRC of 0.13, and the phosphorus level contributed the most to the random forest model. Conclusions: Machine learning models trained on routine immediate postoperative laboratory values outperformed previously published approaches in predicting 30-day postoperative mortality, indicating that they may be beneficial in identifying patients at increased risk of postoperative death.

scholarly journals Artificial Intelligence Prediction Model for the Cost and Mortality of Renal Replacement Therapy in Aged and Super-Aged Populations in Taiwan

2019 ◽  
Vol 8 (7) ◽  
pp. 995 ◽  
Author(s):  
Shih-Yi Lin ◽  
Meng-Hsuen Hsieh ◽  
Cheng-Li Lin ◽  
Meng-Ju Hsieh ◽  
Wu-Huei Hsu ◽  
...  
Keyword(s):  
Neural Network ◽  
Artificial Intelligence ◽  
Artificial Neural Network ◽  
Random Forest ◽  
Prediction Model ◽  
Random Forest Model ◽  
Forest Model ◽  
Artificial Neural ◽  
One Year ◽  
The Cost

Background: Prognosis of the aged population requiring maintenance dialysis has been reportedly poor. We aimed to develop prediction models for one-year cost and one-year mortality in aged individuals requiring dialysis to assist decision-making for deciding whether aged people should receive dialysis or not. Methods: We used data from the National Health Insurance Research Database (NHIRD). We identified patients first enrolled in the NHIRD from 2000–2011 for end-stage renal disease (ESRD) who underwent regular dialysis. A total of 48,153 Patients with ESRD aged ≥65 years with complete age and sex information were included in the ESRD cohort. The total medical cost per patient (measured in US dollars) within one year after ESRD diagnosis was our study’s main outcome variable. We were also concerned with mortality as another outcome. In this study, we compared the performance of the random forest prediction model and of the artificial neural network prediction model for predicting patient cost and mortality. Results: In the cost regression model, the random forest model outperforms the artificial neural network according to the mean squared error and mean absolute error. In the mortality classification model, the receiver operating characteristic (ROC) curves of both models were significantly better than the null hypothesis area of 0.5, and random forest model outperformed the artificial neural network. Random forest model outperforms the artificial neural network models achieved similar performance in the test set across all data. Conclusions: Applying artificial intelligence modeling could help to provide reliable information about one-year outcomes following dialysis in the aged and super-aged populations; those with cancer, alcohol-related disease, stroke, chronic obstructive pulmonary disease (COPD), previous hip fracture, osteoporosis, dementia, and previous respiratory failure had higher medical costs and a high mortality rate.

scholarly journals Computed-Tomography-Based Radiomics Model for Predicting the Malignant Potential of Gastrointestinal Stromal Tumors Preoperatively: A Multi-Classifier and Multicenter Study

2021 ◽  
Vol 11 ◽  
Author(s):  
Minhong Wang ◽  
Zhan Feng ◽  
Lixiang Zhou ◽  
Liang Zhang ◽  
Xiaojun Hao ◽  
...  
Keyword(s):  
Logistic Regression ◽  
Random Forest ◽  
Risk Stratification ◽  
Gastrointestinal Stromal Tumors ◽  
Validation Cohort ◽  
External Validation ◽  
Random Forest Model ◽  
Training Cohort ◽  
Stromal Tumors ◽  
Forest Model

Background: Our goal was to establish and verify a radiomics risk grading model for gastrointestinal stromal tumors (GISTs) and to identify the optimal algorithm for risk stratification.Methods: We conducted a retrospective analysis of 324 patients with GISTs, the presence of which was confirmed by surgical pathology. Patients were treated at three different hospitals. A training cohort of 180 patients was collected from the largest center, while an external validation cohort of 144 patients was collected from the other two centers. To extract radiomics features, regions of interest (ROIs) were outlined layer by layer along the edge of the tumor contour on CT images of the arterial and portal venous phases. The dimensionality of radiomic features was reduced, and the top 10 features with importance value above 5 were selected before modeling. The training cohort used three classifiers [logistic regression, support vector machine (SVM), and random forest] to establish three GIST risk stratification prediction models. The receiver operating characteristic curve (ROC) was used to compare model performance, which was validated by external data.Results: In the training cohort, the average area under the curve (AUC) was 0.84 ± 0.07 of the logistic regression, 0.88 ± 0.06 of the random forest, and 0.81 ± 0.08 of the SVM. In the external validation cohort, the AUC was 0.85 of the logistic regression, 0.90 of the random forest, and 0.80 of the SVM. The random forest model performed the best in both the training and the external validation cohorts and could be generalized.Conclusion: Based on CT radiomics, there are multiple machine-learning models that can predict the risk of GISTs. Among them, the random forest algorithm had the highest prediction efficiency and could be readily generalizable. Through external validation data, we assume that the random forest model may be used as an effective tool to guide preoperative clinical decision-making.

scholarly journals Clinical trial registries as Scientometric data: A novel solution for linking and deduplicating clinical trials from multiple registries

2021 ◽  
Author(s):  
Christian Thiele ◽  
Gerrit Hirschfeld ◽  
Ruth von Brachel
Keyword(s):  
Clinical Trials ◽  
Random Forest ◽  
Random Forest Model ◽  
Scientometric Analysis ◽  
Data Set ◽  
The Public ◽  
Forest Model ◽  
Clinical Trial Registries ◽  
Multiple Primary ◽  
Clinical Trials Registry

AbstractRegistries of clinical trials are a potential source for scientometric analysis of medical research and serve important functions for the research community and the public at large. Clinical trials that recruit patients in Germany are usually registered in the German Clinical Trials Register (DRKS) or in international registries such as ClinicalTrials.gov. Furthermore, the International Clinical Trials Registry Platform (ICTRP) aggregates trials from multiple primary registries. We queried the DRKS, ClinicalTrials.gov, and the ICTRP for trials with a recruiting location in Germany. Trials that were registered in multiple registries were linked using the primary and secondary identifiers and a Random Forest model based on various similarity metrics. We identified 35,912 trials that were conducted in Germany. The majority of the trials was registered in multiple databases. 32,106 trials were linked using primary IDs, 26 were linked using a Random Forest model, and 10,537 internal duplicates on ICTRP were identified using the Random Forest model after finding pairs with matching primary or secondary IDs. In cross-validation, the Random Forest increased the F1-score from 96.4% to 97.1% compared to a linkage based solely on secondary IDs on a manually labelled data set. 28% of all trials were registered in the German DRKS. 54% of the trials on ClinicalTrials.gov, 43% of the trials on the DRKS and 56% of the trials on the ICTRP were pre-registered. The ratio of pre-registered studies and the ratio of studies that are registered in the DRKS increased over time.

scholarly journals Multi-Scenario Prediction of Intra-Urban Land Use Change Using a Cellular Automata-Random Forest Model

2021 ◽  
Vol 10 (8) ◽  
pp. 503
Author(s):  
Hang Liu ◽  
Riken Homma ◽  
Qiang Liu ◽  
Congying Fang
Keyword(s):  
Land Use ◽  
Random Forest ◽  
Cellular Automata ◽  
Land Use Change ◽  
Urban Land ◽  
Urban Land Use ◽  
Random Forest Model ◽  
Growth Trend ◽  
Related Factors ◽  
Forest Model

The simulation of future land use can provide decision support for urban planners and decision makers, which is important for sustainable urban development. Using a cellular automata-random forest model, we considered two scenarios to predict intra-land use changes in Kumamoto City from 2018 to 2030: an unconstrained development scenario, and a planning-constrained development scenario that considers disaster-related factors. The random forest was used to calculate the transition probabilities and the importance of driving factors, and cellular automata were used for future land use prediction. The results show that disaster-related factors greatly influence land vacancy, while urban planning factors are more important for medium high-rise residential, commercial, and public facilities. Under the unconstrained development scenario, urban land use tends towards spatially disordered growth in the total amount of steady growth, with the largest increase in low-rise residential areas. Under the planning-constrained development scenario that considers disaster-related factors, the urban land area will continue to grow, albeit slowly and with a compact growth trend. This study provides planners with information on the relevant trends in different scenarios of land use change in Kumamoto City. Furthermore, it provides a reference for Kumamoto City’s future post-disaster recovery and reconstruction planning.

scholarly journals Estimates of daily ground-level NO2 concentrations in China based on Random Forest model integrated K-means

2021 ◽  
pp. 100017
Author(s):  
Xinyu Dou ◽  
Cuijuan Liao ◽  
Hengqi Wang ◽  
Ying Huang ◽  
Ying Tu ◽  
...  
Keyword(s):  
Random Forest ◽  
Ground Level ◽  
Random Forest Model ◽  
Forest Model

scholarly journals Stress testing reveals gaps in clinic readiness of image-based diagnostic artificial intelligence models

2021 ◽  
Vol 4 (1) ◽  
Author(s):  
Albert T. Young ◽  
Kristen Fernandez ◽  
Jacob Pfau ◽  
Rasika Reddy ◽  
Nhat Anh Cao ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Real World ◽  
Stress Testing ◽  
Operating Characteristic ◽  
Characteristic Curve ◽  
Skin Lesions ◽  
Stress Tests ◽  
Performance Metric ◽  
Intelligence Models ◽  
Artificial Intelligence Models

AbstractArtificial intelligence models match or exceed dermatologists in melanoma image classification. Less is known about their robustness against real-world variations, and clinicians may incorrectly assume that a model with an acceptable area under the receiver operating characteristic curve or related performance metric is ready for clinical use. Here, we systematically assessed the performance of dermatologist-level convolutional neural networks (CNNs) on real-world non-curated images by applying computational “stress tests”. Our goal was to create a proxy environment in which to comprehensively test the generalizability of off-the-shelf CNNs developed without training or evaluation protocols specific to individual clinics. We found inconsistent predictions on images captured repeatedly in the same setting or subjected to simple transformations (e.g., rotation). Such transformations resulted in false positive or negative predictions for 6.5–22% of skin lesions across test datasets. Our findings indicate that models meeting conventionally reported metrics need further validation with computational stress tests to assess clinic readiness.

Sign in / Sign up

Export Citation Format

Share Document