Development of prediction models of spontaneous ureteral stone passage through machine learning: Comparison with conventional statistical analysis.
Ontology highlight
ABSTRACT: Objectives
To develop a prediction model of spontaneous ureteral stone passage (SSP) using machine learning and logistic regression and compare the performance of the two models. Indications for management of ureteral stones are unclear, and the clinician determines whether to wait for SSP or perform active treatment, especially in well-controlled patients, to avoid unwanted complications. Therefore, suggesting the possibility of SSP would help make a clinical decision regarding ureteral stones.Methods
Patients diagnosed with unilateral ureteral stones at our emergency department between August 2014 and September 2018 were included and underwent non-contrast-enhanced computed tomography 4 weeks from the first stone episode. Predictors of SSP were applied to build and validate the prediction model using multilayer perceptron (MLP) with the Keras framework.Results
Of 833 patients, SSP was observed in 606 (72.7%). SSP rates were 68.2% and 75.6% for stone sizes 5-10 mm and <5 mm, respectively. Stone opacity, location, and whether it was the first ureteral stone episode were significant predictors of SSP. Areas under the curve (AUCs) for receiver operating characteristic (ROC) curves for MLP, and logistic regression were 0.859 and 0.847, respectively, for stones <5 mm, and 0.881 and 0.817, respectively, for 5-10 mm stones.Conclusion
SSP prediction models were developed in patients with well-controlled unilateral ureteral stones; the performance of the models was good, especially in identifying SSP for 5-10-mm ureteral stones without definite treatment guidelines. To further improve the performance of these models, future studies should focus on using machine learning techniques in image analysis.
SUBMITTER: Park JS
PROVIDER: S-EPMC8635399 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:A 48-year-old man with a history of cerebral infarction presented with gross hematuria. The patient's limping accompanies twisting trunk on his walking. The diagnosis was right upper ureteral stone. Prior to Extracorporeal shockwave lithotripsy (ESWL) ureteral stent was inserted. After the second ESWL ureteral stent was displaced upwardly without patient's unknown. Retrograde intrarenal surgery (RIRS) was performed for both removal of ureteral stent and fragmentation of residual stone. Spontaneously, post RIRS ureteral stent was migrated upwardly to the same position. Ureteral stent migration is uncommon. Twisting walk may cause the position of ureteral stent upwardly.
| S-EPMC6562287 | biostudies-literature
Project description:AimsThis study aimed to review the performance of machine learning (ML) methods compared with conventional statistical models (CSMs) for predicting readmission and mortality in patients with heart failure (HF) and to present an approach to formally evaluate the quality of studies using ML algorithms for prediction modelling.Methods and resultsFollowing Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines, we performed a systematic literature search using MEDLINE, EPUB, Cochrane CENTRAL, EMBASE, INSPEC, ACM Library, and Web of Science. Eligible studies included primary research articles published between January 2000 and July 2020 comparing ML and CSMs in mortality and readmission prognosis of initially hospitalized HF patients. Data were extracted and analysed by two independent reviewers. A modified CHARMS checklist was developed in consultation with ML and biostatistics experts for quality assessment and was utilized to evaluate studies for risk of bias. Of 4322 articles identified and screened by two independent reviewers, 172 were deemed eligible for a full-text review. The final set comprised 20 articles and 686 842 patients. ML methods included random forests (n = 11), decision trees (n = 5), regression trees (n = 3), support vector machines (n = 9), neural networks (n = 12), and Bayesian techniques (n = 3). CSMs included logistic regression (n = 16), Cox regression (n = 3), or Poisson regression (n = 3). In 15 studies, readmission was examined at multiple time points ranging from 30 to 180 day readmission, with the majority of studies (n = 12) presenting prediction models for 30 day readmission outcomes. Of a total of 21 time-point comparisons, ML-derived c-indices were higher than CSM-derived c-indices in 16 of the 21 comparisons. In seven studies, mortality was examined at 9 time points ranging from in-hospital mortality to 1 year survival; of these nine, seven reported higher c-indices using ML. Two of these seven studies reported survival analyses utilizing random survival forests in their ML prediction models. Both reported higher c-indices when using ML compared with CSMs. A limitation of studies using ML techniques was that the majority were not externally validated, and calibration was rarely assessed. In the only study that was externally validated in a separate dataset, ML was superior to CSMs (c-indices 0.913 vs. 0.835).ConclusionsML algorithms had better discrimination than CSMs in most studies aiming to predict risk of readmission and mortality in HF patients. Based on our review, there is a need for external validation of ML-based studies of prediction modelling. We suggest that ML-based studies should also be evaluated using clinical quality standards for prognosis research. Registration: PROSPERO CRD42020134867.
| S-EPMC7835549 | biostudies-literature
Project description:The STONE score is a clinical decision rule that classifies patients with suspected nephrolithiasis into low-, moderate-, and high-score groups, with corresponding probabilities of ureteral stone. We evaluate the STONE score in a multi-institutional cohort compared with physician gestalt and hypothesize that it has a sufficiently high specificity to allow clinicians to defer computed tomography (CT) scan in patients with suspected nephrolithiasis.We assessed the STONE score with data from a randomized trial for participants with suspected nephrolithiasis who enrolled at 9 emergency departments between October 2011 and February 2013. In accordance with STONE predictors, we categorized participants into low-, moderate-, or high-score groups. We determined the performance of the STONE score and physician gestalt for ureteral stone.Eight hundred forty-five participants were included for analysis; 331 (39%) had a ureteral stone. The global performance of the STONE score was superior to physician gestalt (area under the receiver operating characteristic curve=0.78 [95% confidence interval {CI} 0.74 to 0.81] versus 0.68 [95% CI 0.64 to 0.71]). The prevalence of ureteral stone on CT scan ranged from 14% (95% CI 9% to 19%) to 73% (95% CI 67% to 78%) in the low-, moderate-, and high-score groups. The sensitivity and specificity of a high score were 53% (95% CI 48% to 59%) and 87% (95% CI 84% to 90%), respectively.The STONE score can successfully aggregate patients into low-, medium-, and high-risk groups and predicts ureteral stone with a higher specificity than physician gestalt. However, in its present form, the STONE score lacks sufficient accuracy to allow clinicians to defer CT scan for suspected ureteral stone.
| S-EPMC4808407 | biostudies-literature
Project description:ObjectivesTo develop a nomogram that could predict spontaneous stone passage (SSP) in patients presenting with acute ureteric colic who are suitable for conservative management.Subject/patientsA 2517 patient dataset was utilised from an international multi-centre cohort study (MIMIC, A Multi-centre Cohort Study Evaluating the role of Inflammatory Markers In Patients Presenting with Acute Ureteric Colic) of patients presenting with acute ureteric colic across 71 secondary care hospitals in the United Kingdom, Ireland, Australia, and New Zealand. Inclusion criteria mandated a non-contrast CT-KUB.MethodsSSP was defined as the 'absence of the need for intervention'. The model was developed using logistic regression and backwards selection (to achieve lowest AIC) in a subset from 2009-2015 (n=1728) and temporally validated on a subset from 2016-2017 (n=789).ResultsOf the 2517 patients, 1874 had SSP (74.5%). Mean age (±[SD]) was 47 (±14.7) years and 1892 were male (75.2%). At the end of the modelling process, gender: male (OR 0.8, 95%CI 0.64-1.01, p=0.07), neutrophil count (OR 1.03, 95%CI 1.00-1.06, p = 0.08), hydronephrosis (OR 0.79, 95%CI 0.59-1.05, p=0.1), hydroureter (OR 1.3, 95%CI 0.97-1.75, p =0.08), stone size >5-7mm (OR 0.2, 95%CI 0.16-0.25, p<0.0001), stone size >7mm (OR 0.11, 95%CI 0.08-0.15, p<0.001), middle ureter stone position (OR 0.59, 95%CI 0.43-0.81, p=0.001), upper ureter stone position (OR 0.31, 95%CI 0.25-0.39, p<0.001) ), medical expulsive therapy use (OR 1.36, 95%CI 1.1 - 1.67, p = 0.001), oral NSAID use (OR 1.3, 95%CI 0.99 - 1.71, p=0.06), and rectal NSAID use (OR1.17, 95%CI 0.9 - 1.53, p=0.24) remained. Concordance-statistic (C-statistic) was 0.77 (95%CI 0.75 - 0.80) and a nomogram was developed based on these.ConclusionThe presented nomogram is available to use as an online calculator via www.BURSTurology.com and could allow clinicians and patients to make a more informed decision on pursuing conservative management versus early intervention.
| S-EPMC9796920 | biostudies-literature
Project description:Background:Statistically derived cardiovascular risk calculators (CVRC) that use conventional risk factors, generally underestimate or overestimate the risk of cardiovascular disease (CVD) or stroke events primarily due to lack of integration of plaque burden. This study investigates the role of machine learning (ML)-based CVD/stroke risk calculators (CVRCML) and compares against statistically derived CVRC (CVRCStat) based on (I) conventional factors or (II) combined conventional with plaque burden (integrated factors). Methods:The proposed study is divided into 3 parts: (I) statistical calculator: initially, the 10-year CVD/stroke risk was computed using 13 types of CVRCStat (without and with plaque burden) and binary risk stratification of the patients was performed using the predefined thresholds and risk classes; (II) ML calculator: using the same risk factors (without and with plaque burden), as adopted in 13 different CVRCStat, the patients were again risk-stratified using CVRCML based on support vector machine (SVM) and finally; (III) both types of calculators were evaluated using AUC based on ROC analysis, which was computed using combination of predicted class and endpoint equivalent to CVD/stroke events. Results:An Institutional Review Board approved 202 patients (156 males and 46 females) of Japanese ethnicity were recruited for this study with a mean age of 69±11 years. The AUC for 13 different types of CVRCStat calculators were: AECRS2.0 (AUC 0.83, P<0.001), QRISK3 (AUC 0.72, P<0.001), WHO (AUC 0.70, P<0.001), ASCVD (AUC 0.67, P<0.001), FRScardio (AUC 0.67, P<0.01), FRSstroke (AUC 0.64, P<0.001), MSRC (AUC 0.63, P=0.03), UKPDS56 (AUC 0.63, P<0.001), NIPPON (AUC 0.63, P<0.001), PROCAM (AUC 0.59, P<0.001), RRS (AUC 0.57, P<0.001), UKPDS60 (AUC 0.53, P<0.001), and SCORE (AUC 0.45, P<0.001), while the AUC for the CVRCML with integrated risk factors (AUC 0.88, P<0.001), a 42% increase in performance. The overall risk-stratification accuracy for the CVRCML with integrated risk factors was 92.52% which was higher compared all the other CVRCStat. Conclusions:ML-based CVD/stroke risk calculator provided a higher predictive ability of 10-year CVD/stroke compared to the 13 different types of statistically derived risk calculators including integrated model AECRS 2.0.
| S-EPMC7487379 | biostudies-literature
Project description:BackgroundUreteral injury (UI) is a rare but devastating complication during colorectal surgery. Ureteral stents may reduce UI but carry risks themselves. Risk predictors for UI could help target the use of stents, but previous efforts have relied on logistic regression (LR), shown moderate accuracy, and used intraoperative variables. We sought to use an emerging approach in predictive analytics, machine learning, to create a model for UI.MethodsPatients who underwent colorectal surgery were identified in the National Surgical Quality Improvement Program (NSQIP) database. Patients were split into training, validation, and test sets. The primary outcome was UI. Three machine learning approaches were tested including random forest (RF), gradient boosting (XGB), and neural networks (NN), and compared with traditional LR. Model performance was assessed using area under the curve (AUROC).ResultsThe data set included 262,923 patients, of whom 1519 (.578%) experienced UI. Of the modeling techniques, XGB performed the best, with an AUROC score of .774 (95% CI .742-.807) compared with .698 (95% CI .664-.733) for LR. Random forest and NN performed similarly with scores of .738 and .763, respectively. Type of procedure, work RVUs, indication for surgery, and mechanical bowel prep showed the strongest influence on model predictions.ConclusionsMachine learning-based models significantly outperformed LR and previous models and showed high accuracy in predicting UI during colorectal surgery. With proper validation, they could be used to support decision making regarding the placement of ureteral stents preoperatively.
| S-EPMC10622328 | biostudies-literature
Project description:ObjectiveTo derive and validate an objective clinical prediction rule for the presence of uncomplicated ureteral stones in patients eligible for computed tomography (CT). We hypothesized that patients with a high probability of ureteral stones would have a low probability of acutely important alternative findings.DesignRetrospective observational derivation cohort; prospective observational validation cohort.SettingUrban tertiary care emergency department and suburban freestanding community emergency department.ParticipantsAdults undergoing non-contrast CT for suspected uncomplicated kidney stone. The derivation cohort comprised a random selection of patients undergoing CT between April 2005 and November 2010 (1040 patients); the validation cohort included consecutive prospectively enrolled patients from May 2011 to January 2013 (491 patients).Main outcome measuresIn the derivation phase a priori factors potentially related to symptomatic ureteral stone were derived from the medical record blinded to the dictated CT report, which was separately categorized by diagnosis. Multivariate logistic regression was used to determine the top five factors associated with ureteral stone and these were assigned integer points to create a scoring system that was stratified into low, moderate, and high probability of ureteral stone. In the prospective phase this score was observationally derived blinded to CT results and compared with the prevalence of ureteral stone and important alternative causes of symptoms.ResultsThe derivation sample included 1040 records, with five factors found to be most predictive of ureteral stone: male sex, short duration of pain, non-black race, presence of nausea or vomiting, and microscopic hematuria, yielding a score of 0-13 (the STONE score). Prospective validation was performed on 491 participants. In the derivation and validation cohorts ureteral stone was present in, respectively, 8.3% and 9.2% of the low probability (score 0-5) group, 51.6% and 51.3% of the moderate probability (score 6-9) group, and 89.6% and 88.6% of the high probability (score 10-13) group. In the high score group, acutely important alternative findings were present in 0.3% of the derivation cohort and 1.6% of the validation cohort.ConclusionsThe STONE score reliably predicts the presence of uncomplicated ureteral stone and lower likelihood of acutely important alternative findings. Incorporation in future investigations may help to limit exposure to radiation and over-utilization of imaging.Trial registrationwww.clinicaltrials.gov NCT01352676.
| S-EPMC3966515 | biostudies-literature
Project description:ObjectiveTo compare machine learning methods for predicting inpatient seizures risk and determine the feasibility of 1-h screening EEG to identify low-risk patients (<5% seizures risk in 48 h).MethodsThe Critical Care EEG Monitoring Research Consortium (CCEMRC) multicenter database contains 7716 continuous EEGs (cEEG). Neural networks (NN), elastic net logistic regression (EN), and sparse linear integer model (RiskSLIM) were trained to predict seizures. RiskSLIM was used previously to generate 2HELPS2B model of seizure predictions. Data were divided into training (60% for model fitting) and evaluation (40% for model evaluation) cohorts. Performance was measured using area under the receiver operating curve (AUC), mean risk calibration (CAL), and negative predictive value (NPV). A secondary analysis was performed using Monte Carlo simulation (MCS) to normalize all EEG recordings to 48 h and use only the first hour of EEG as a "screening EEG" to generate predictions.ResultsRiskSLIM recreated the 2HELPS2B model. All models had comparable AUC: evaluation cohort (NN: 0.85, EN: 0.84, 2HELPS2B: 0.83) and MCS (NN: 0.82, EN; 0.82, 2HELPS2B: 0.81) and NPV (absence of seizures in the group that the models predicted to be low risk): evaluation cohort (NN: 97%, EN: 97%, 2HELPS2B: 97%) and MCS (NN: 97%, EN: 99%, 2HELPS2B: 97%). 2HELPS2B model was able to identify the largest proportion of low-risk patients.InterpretationFor seizure risk stratification of hospitalized patients, the RiskSLIM generated 2HELPS2B model compares favorably to the complex NN and EN generated models. 2HELPS2B is able to accurately and quickly identify low-risk patients with only a 1-h screening EEG.
| S-EPMC6649418 | biostudies-literature
Project description:We compared the prediction performance of machine learning-based undiagnosed diabetes prediction models with that of traditional statistics-based prediction models. We used the 2014-2020 Korean National Health and Nutrition Examination Survey (KNHANES) (N = 32,827). The KNHANES 2014-2018 data were used as training and internal validation sets and the 2019-2020 data as external validation sets. The receiver operating characteristic curve area under the curve (AUC) was used to compare the prediction performance of the machine learning-based and the traditional statistics-based prediction models. Using sex, age, resting heart rate, and waist circumference as features, the machine learning-based model showed a higher AUC (0.788 vs. 0.740) than that of the traditional statistical-based prediction model. Using sex, age, waist circumference, family history of diabetes, hypertension, alcohol consumption, and smoking status as features, the machine learning-based prediction model showed a higher AUC (0.802 vs. 0.759) than the traditional statistical-based prediction model. The machine learning-based prediction model using features for maximum prediction performance showed a higher AUC (0.819 vs. 0.765) than the traditional statistical-based prediction model. Machine learning-based prediction models using anthropometric and lifestyle measurements may outperform the traditional statistics-based prediction models in predicting undiagnosed diabetes.
| S-EPMC10421881 | biostudies-literature
Project description:Criticism of the implementation of existing risk prediction models (RPMs) for cardiovascular diseases (CVDs) in new populations motivates researchers to develop regional models. The predominant usage of laboratory features in these RPMs is also causing reproducibility issues in low-middle-income countries (LMICs). Further, conventional logistic regression analysis (LRA) does not consider non-linear associations and interaction terms in developing these RPMs, which might oversimplify the phenomenon. This study aims to develop alternative machine learning (ML)-based RPMs that may perform better at predicting CVD status using nonlaboratory features in comparison to conventional RPMs. The data was based on a case-control study conducted at the Punjab Institute of Cardiology, Pakistan. Data from 460 subjects, aged between 30 and 76 years, with (1:1) gender-based matching, was collected. We tested various ML models to identify the best model/models considering LRA as a baseline RPM. An artificial neural network and a linear support vector machine outperformed the conventional RPM in the majority of performance matrices. The predictive accuracies of the best performed ML-based RPMs were between 80.86 and 81.09% and were found to be higher than 79.56% for the baseline RPM. The discriminating capabilities of the ML-based RPMs were also comparable to baseline RPMs. Further, ML-based RPMs identified substantially different orders of features as compared to baseline RPM. This study concludes that nonlaboratory feature-based RPMs can be a good choice for early risk assessment of CVDs in LMICs. ML-based RPMs can identify better order of features as compared to the conventional approach, which subsequently provided models with improved prognostic capabilities.
| S-EPMC8657087 | biostudies-literature