Measure Of Predictive Accuracy Research Articles

Fibrinolysis shutdown and elevated D-dimer levels have high prognostic capacity for postoperative thromboembolic complications in patients with bone tumors.

Surgical resection of malignant bone tumors is associated with a high risk of venous thromboembolism (VTE). The purpose of this study was to evaluate the association between rotational thromboelastometry (ROTEM) parameters and VTE following oncologic resections, and to evaluate their prognostic capacity for this complication. A prospective observational study was conducted including 113 patients who underwent surgical resection of malignant bone tumors. ROTEM analysis and conventional coagulation studies were performed preoperatively and on the 2nd postoperative day, while patients were followed for the development of VTE. Logistic regression was used to assess the association between ROTEM parameters and occurrence of VTE. The area under the receiver operating characteristic curve (AUC), sensitivity and specificity were calculated as measures of discrimination and predictive accuracy. Fourteen patients (12.4%) developed symptomatic VTE. Development of VTE was associated with shortened INTEM CFT (Odds Ratio [OR] 0.90, 95% Confidence Interval [CI] 0.84 - 0.96, p = 0.004), higher INTEM A10 (OR 1.21, 95% CI 1.07 - 1.36, p = 0.002), higher INTEM MCF (OR 1.22, 95% CI 1.08 - 1.37, p = 0.001) and higher INTEM LI60 (OR 2.10, 95% CI 1.38 - 3.21, p = 0.001). An INTEM LI60 value indicative of fibrinolysis shutdown (≥ 98%) had the best predictive accuracy for VTE (AUC = 0.887, 95% CI 0.824 - 0.951, sensitivity = 100%, specificity = 67.0%), higher than that of D-dimer levels (p = 0.028). ROTEM parameters were promising predictors of symptomatic VTE. Fibrinolysis shutdown as reflected by ROTEM LI60 and high D-dimer levels can aid the identification of high-risk patients. Future studies should evaluate whether the addition of ROTEM findings to an expanded risk-assessing model can improve the predictive capacity and provide better guidance in thromboprophylaxis.

Outcome class imbalance and rare events: An underappreciated complication for overdose risk prediction modeling.

Low outcome prevalence, often observed with opioid-related outcomes, poses an underappreciated challenge to accurate predictive modeling. Outcome class imbalance, where non-events (i.e. negative class observations) outnumber events (i.e. positive class observations) by a moderate to extreme degree, can distort measures of predictive accuracy in misleading ways, and make the overall predictive accuracy and the discriminatory ability of a predictive model appear spuriously high. We conducted a simulation study to measure the impact of outcome class imbalance on predictive performance of a simple SuperLearner ensemble model and suggest strategies for reducing that impact. Using a Monte Carlo design with 250 repetitions, we trained and evaluated these models on four simulated data sets with 100 000 observations each: one with perfect balance between events and non-events, and three where non-events outnumbered events by an approximate factor of 10:1, 100:1, and 1000:1, respectively. We evaluated the performance of these models using a comprehensive suite of measures, including measures that are more appropriate for imbalanced data. Increasing imbalance tended to spuriously improve overall accuracy (using a high threshold to classify events vs non-events, overall accuracy improved from 0.45 with perfect balance to 0.99 with the most severe outcome class imbalance), but diminished predictive performance was evident using other metrics (corresponding positive predictive value decreased from 0.99 to 0.14). Increasing reliance on algorithmic risk scores in consequential decision-making processes raises critical fairness and ethical concerns. This paper provides broad guidance for analytic strategies that clinical investigators can use to remedy the impacts of outcome class imbalance on risk prediction tools.

Examining the use of decision trees in population health surveillance research: an application to youth mental health survey data in the COMPASS study.

In population health surveillance research, survey data are commonly analyzed using regression methods; however, these methods have limited ability to examine complex relationships. In contrast, decision tree models are ideally suited for segmenting populations and examining complex interactions among factors, and their use within health research is growing. This article provides a methodological overview of decision trees and their application to youth mental health survey data. The performance of two popular decision tree techniques, the classification and regression tree (CART) and conditional inference tree (CTREE) techniques, is compared to traditional linear and logistic regression models through an application to youth mental health outcomes in the COMPASS study. Data were collected from 74 501 students across 136 schools in Canada. Anxiety, depression and psychosocial well-being outcomes were measured along with 23 sociodemographic and health behaviour predictors. Model performance was assessed using measures of prediction accuracy, parsimony and relative variable importance. Decision tree and regression models consistently identified the same sets of most important predictors for each outcome, indicating a general level of agreement between methods. Tree models had lower prediction accuracy but were more parsimonious and placed greater relative importance on key differentiating factors. Decision trees provide a means of identifying high-risk subgroups to whom prevention and intervention efforts can be targeted, making them a useful tool to address research questions that cannot be answered by traditional regression methods.

A Comparison of Artificial Neural Network and Time Series Models for Timber Price Forecasting

The majority of the existing studies on timber price forecasting are based on ARIMA/SARIMA autoregressive moving average models, while vector autoregressive (VAR) and exponential smoothing (ETS) models have been employed less often. To date, timber prices in primary timber markets have not been forecasted with ANN methodology. This methodology was used only for forecasting lumber futures. Low-labor-intensive and relatively simple solutions that can be used in practice as a tool supporting decisions of timber market participants were sought. The present work sets out to compare RBF and MLP artificial neural networks with the Prophet procedure and with classical models (i.e., ARIMA, ETS, BATS, and TBATS) in terms of their suitability for forecasting timber prices in Poland. The study material consisted of quarterly time series of net nominal prices of roundwood (W0) for the years 2005–2021. MLP was found to be far superior to other models in terms of forecasting price changes and levels. ANN models exhibited a better fit to minimum and maximum values as compared to the classical models, which had a tendency to smooth price trends and produce forecasts biased toward average values. The Prophet procedure led to the lowest quality of projections. Ex-post error-based measures of prediction accuracy revealed a complex picture. The best forecasts for alder wood were obtained using the ETS model (with RMSE and MAE values of approx. 0.38 € m−3). ETS also performed well with respect to beech timber, although in this case BATS was just as good in terms of RMSE, while the difference between ETS and neural models amounted to as little as 0.64 € m−3. Birch timber prices were most accurately predicted with BATS and TBATS models (MAE 0.86 € m−3, RMSE 1.04 € m−3). The prices of the most popular roundwood types in Poland, i.e., Scots pine, Norway spruce, and oaks, were best forecasted using ANNs, and especially MLP models. Among the neural models for oak (MAE 4.74 € m−3, RMSE 8.09 € m−3), pine (MAE 2.21 € m−3, RMSE 2.83 € m−3), beech (MAE 2.31 € m−3, RMSE 2.70 € m−3), alder (MAE 1.88 € m−3, RMSE 2.40 € m−3), and spruce (MAE 2.44 € m−3, RMSE 2.58 € m−3), the MLP model was the best (the RBF model for birch). Of the seven models used to forecast the prices of six types of wood, the worst results were obtained for oak wood, while the best results were obtained for alder.

Total value of claims in the motor multiperil portfolio

In this article, we consider a motor portfolio of policies in which a single policy covers several perils. One of the metrics that can be used to manage claims in such a portfolio is the TVC (the total value of claims) for a settlement period (usually a calendar year). At a given point in the period, some claims have already occurred and are observed and some are not yet observed. Thus, the problem of predicting the TVC variable in the unobservable part arises. We propose to use the Tweedie-HGLM statistical model, which takes into account the multiperil structure of the portfolio. A plug-in predictor is used and prediction accuracy measures are estimated using a bootstrap procedure. Not only is the mean squared error calculated, but also the error based on the quantile of the bootstrap distribution of the model residuals. The application of the proposed model in practice is shown by the analysis of AUTOSEG data from Brazilian market.

A transdiagnostic evaluation of contrast avoidance across generalized anxiety disorder, major depressive disorder, and social anxiety disorder

BackgroundThe contrast avoidance model (CAM) proposes that persons with generalized anxiety disorder (GAD) are sensitive to sharp increases in negative emotion or decreases in positive emotion (i.e., negative emotional contrasts; NEC) and use worry to avoid NEC. Sensitivity to and avoidance of NEC could also be a shared feature of major depressive disorder (MDD) and social anxiety disorder (SAD). MethodsIn a large college sample (N = 1409), we used receiver operating characteristics analysis to examine the accuracy of a measure of emotional contrast avoidance in detecting probable GAD, MDD, and SAD. ResultsParticipants with probable GAD, MDD, and SAD all reported higher levels of contrast avoidance than participants without the disorder (Cohen’s d = 1.32, 1.62 and 1.53, respectively). Area under the curve, a measure of predictive accuracy, was .81, .87, and .83 for predicting probable GAD, MDD, and SAD, respectively. A cutoff score of 48.5 optimized predictive accuracy for probable GAD and SAD, and 50.5 optimized accuracy for probable MDD. ConclusionA measure of emotional contrast avoidance demonstrated excellent ability to predict probable GAD, MDD, and SAD. Sensitivity to and avoidance of NEC appears to be a transdiagnostic feature of these disorders.

Prediction of response to anti-TNF treatment using laboratory biomarkers in patients with rheumatoid arthritis: a systematic review

ObjectivesIn this systematic review, we aim to identify laboratory biomarkers that predict response to tumour necrosis factor inhibitors (TNFi) in patients with rheumatoid arthritis (RA).MethodsEMBASE, PubMed and Cochrane Library (CENTRAL)...

Evaluating the Predictive Performance of Positive- Unlabelled Classifiers

Positive-Unlabelled (PU) learning is a growing area of machine learning that aims to learn classifiers from data consisting of labelled positive and unlabelled instances. Whilst much work has been done proposing methods for PU learning, little has been written on the subject of evaluating these methods. Many popular standard classification metrics cannot be precisely calculated due to the absence of fully labelled data, so alternative approaches must be taken. This short commentary paper critically reviews the main PU learning evaluation approaches and the choice of predictive accuracy measures in 51 articles proposing PU classifiers and provides practical recommendations for improvements in this area.

Does the combination of models with different explanatory variables improve tourism demand forecasting performance?

The aim of this study is to assess whether combining econometric models with different explanatory variables can contribute to better tourism demand forecasts. Inbound tourism demand to the UK from seven leading markets is forecast, respectively, based on quarterly data using both individual and combination models. Causal econometric models that serve as constituents in combination take two specifications which are different in identified influencing factors. The empirical results show that generally including different explanatory variables in combination can produce better predictions according to both predictive accuracy measures and statistical tests. It suggests that the combination forecasting approach is superior to the individual one, and diversified information embedded in different explanatory variables should be integrated to improve tourism demand forecasting performance.

Modified Brier score for evaluating prediction accuracy for binary outcomes.

The Brier score has been a popular measure of prediction accuracy for binary outcomes. However, it is not straightforward to interpret the Brier score for a prediction model since its value depends on the outcome prevalence. We decompose the Brier score into two components, the mean squares between the estimated and true underlying binary probabilities, and the variance of the binary outcome that is not reflective of the model performance. We then propose to modify the Brier score by removing the variance of the binary outcome, estimated via a general sliding window approach. We show that the new proposed measure is more sensitive for comparing different models through simulation. A standardized performance improvement measure is also proposed based on the new criterion to quantify the improvement of prediction performance. We apply the new measures to the data from the Breast Cancer Surveillance Consortium and compare the performance of predicting breast cancer risk using the models with and without its most important predictor.

Using some Statistical methods and artificial intelligence to predict the amount of oil exports in Iraq

Building predictive models that aid in the creation of economic growth plans involves the use of statistical techniques and artificial intelligence. Based on data for the time, the study sought to compare the ARIMA, artificial neural networks, and the hybrid technique to predict the volume of oil shipments from Iraq (January 2018- December 2021). It has been determined by comparing these models using the MAE, RMSE, MSE, and MAPE prediction accuracy measures that artificial neural networks are superior to ARIMA because they provide the lowest value of errors in accordance with the earlier measures. The use of the hybrid method also assisted in lowering the error value where it has been relied upon to determine the amount of oil exports from Iraq until June 2022.

A preoperative tool for estimating the risk of blood transfusion over an ovarian cancer debulking surgery (113)

<b>Objectives:</b> To develop a preoperative tool for estimating the risk for packed red blood cell transfusion during primary debulking surgery (PDS) for ovarian cancer and in the postoperative setting. This will help physicians identify a subgroup of patients that will benefit from surgical planning and blood-saving techniques. <b>Methods:</b> We conducted a single-center ovarian cancer database review of women undergoing PDS between 2001-2019. Exclusion criteria included patients with preoperative hemoglobin <10.0g/dl. Associations between the criteria and PDS outcomes were tested using the Wilcoxon Rank-Sum test for continuous variables and Fisher's exact test for categorical variables. A receiver operating characteristics (ROC) curve was generated to build a model predictive of transfusion; AUC was used as a measure of predictive accuracy. A multivariable regression model was developed to evaluate the odds of transfusion. These criteria were then assigned a risk of transfusion—a "BLood transfusion Over an Ovarian cancer Debulking Surgery (BLOODS)" score—according to their multivariate odds ratios (ORs). The total score of all patients in the cohort was subsequently calculated, and the odds of receiving a transfusion corresponding to each total score were determined. <b>Results:</b> A total of 1289 patients met the eligibility criteria. Median estimated blood loss was 650cc (range: 10-8150cc), with 375 patients experiencing a blood loss ≥1000cc (29%). A total of 1087 (84%) underwent optimal PDS (≤1cm of residual disease), 654 (51%) had complete gross resection. The presence of upper abdominal disease ≥1cm was most heavily associated with the need for transfusion intraoperatively and/or postoperatively (OR: 3.11, 95% CI: 2.47-3.91), followed Table by the presence of ascites (OR: 3.07, 2.44-3.87), albumin ≤3.5 (OR: 2.51, 1.76-3.59), carcinomatosis (OR: 2.27, 1.76-2.93), and CA-125 ≥600 (OR: 2.46, 1.95-3.10). On multivariable analysis, seven criteria were associated with blood transfusion: ASA ≥3 (1.05, 1.00-1.10), albumin ≤3.5 (1.26, 1.19-1.34), ascites (1.06, 0.98-1.15), CA-125 ≥600 (OR: 1.10, 1.04-1.16), carcinomatosis (1.01, 0.93-1.10), creatinine >0.90 (1.14, 1.07-1.22), upper abdominal disease ≥1cm (1.16, 1.07-1.25). A predictive (BLOODS) score was assigned to each of the seven criteria based on their multivariable ORs. A BLOODS score of ≥3 is projected to identify a rate of 85% of primary ovarian cancer cytoreductive cases requiring an intraoperative blood transfusion, 78% requiring a postoperative blood transfusion, and 80% overall. <b>Conclusions:</b> The BLOODS score can be used as a universal preoperative scoring system for patients with ovarian cancer undergoing PDS. The model estimates the risk of requiring a blood transfusion, which is directly proportional to ASA, albumin, ascites, CA-125, carcinomatosis, creatinine, and the presence of upper abdominal disease. This will help physicians with surgical planning and can benefit patient outcomes.

A comparison of survival models for prediction of eight-year revision risk following total knee and hip arthroplasty

BackgroundThere is increasing interest in the development and use of clinical prediction models, but a lack of evidence-supported guidance on the merits of different modelling approaches. This is especially true for time-to-event outcomes, where limited studies have compared the vast number of modelling approaches available. This study compares prediction accuracy and variable importance measures for four modelling approaches in prediction of time-to-revision surgery following total knee arthroplasty (TKA) and total hip arthroplasty (THA).MethodsThe study included 321,945 TKA and 151,113 THA procedures performed between 1 January 2003 and 31 December 2017. Accuracy of the Cox model, Weibull parametric model, flexible parametric model, and random survival forest were compared, with patient age, sex, comorbidities, and prosthesis characteristics considered as predictors. Prediction accuracy was assessed using the Index of Prediction Accuracy (IPA), c-index, and smoothed calibration curves. Variable importance rankings from the Cox model and random survival forest were also compared.ResultsOverall, the Cox and flexible parametric survival models performed best for prediction of both TKA (integrated IPA 0.056 (95% CI [0.054, 0.057]) compared to 0.054 (95% CI [0.053, 0.056]) for the Weibull parametric model), and THA revision. (0.029 95% CI [0.027, 0.030] compared to 0.027 (95% CI [0.025, 0.028]) for the random survival forest). The c-index showed broadly similar discrimination between all modelling approaches. Models were generally well calibrated, but random survival forest underfitted the predicted risk of TKA revision compared to regression approaches. The most important predictors of revision were similar in the Cox model and random survival forest for TKA (age, opioid use, and patella resurfacing) and THA (femoral cement, depression, and opioid use).ConclusionThe Cox and flexible parametric models had superior overall performance, although all approaches performed similarly. Notably, this study showed no benefit of a tuned random survival forest over regression models in this setting.

Evaluating the Inaccuracy of the National Surgical Quality Improvement Project Surgical Risk Calculator in Plastic Surgery: A Meta-analysis of Short-Term Predicted Complications.

Preoperative surgical risk assessment is a major component of clinical decision making. The ability to provide accurate, individualized risk estimates has become critical because of growing emphasis on quality metrics benchmarks. The American College of Surgeons National Surgical Quality Improvement Project (NSQIP) Surgical Risk Calculator (SRC) was designed to quantify patient-specific risk across various surgeries. Its applicability to plastic surgery is unclear, however, with multiple studies reporting inaccuracies among certain patient populations. This study uses meta-analysis to evaluate the NSQIP SRC's ability to predict complications among patients having plastic surgery. OVID MEDLINE and PubMed were searched for all studies evaluating the predictive accuracy of the NSQIP SRC in plastic surgery, including oncologic reconstruction, ventral hernia repair, and body contouring. Only studies directly comparing SCR predicted to observed complication rates were included. The primary measure of SRC prediction accuracy, area under the curve (AUC), was assessed for each complication via DerSimonian and Laird random-effects analytic model. The I2 statistic, indicating heterogeneity, was judged low (I2 < 50%) or borderline/unacceptably high (I2 > 50%). All analyses were conducted in StataSE 16.1 (StataCorp LP, College Station, Tex). Ten of the 296 studies screened met criteria for inclusion (2416 patients). Studies were classified as follows: (head and neck: n = 5, breast: n = 1, extremity: n = 1), open ventral hernia repair (n = 2), and panniculectomy (n = 1). Predictive accuracy was poor for medical and surgical complications (medical: pulmonary AUC = 0.67 [0.48-0.87], cardiac AUC = 0.66 [0.20-0.99], venous thromboembolism AUC = 0.55 [0.47-0.63]), (surgical: surgical site infection AUC = 0.55 [0.46-0.63], reoperation AUC = 0.54 [0.49-0.58], serious complication AUC = 0.58 [0.43-0.73], and any complication AUC = 0.60 [0.57-0.64]). Although mortality was accurately predicted in 2 studies (AUC = 0.87 [0.54-0.99]), heterogeneity was high with I2 = 68%. Otherwise, heterogeneity was minimal (I2 = 0%) or acceptably low (I2 < 50%) for all other outcomes. The NSQIP Universal SRC, aimed at offering individualized quantifiable risk estimates for surgical complications, consistently demonstrated poor risk discrimination in this plastic surgery-focused meta-analysis. The limitations of the SRC are perhaps most pronounced where complex, multidisciplinary reconstructions are needed. Future efforts should identify targets for improving SRC reliability to better counsel patients in the perioperative setting and guide appropriate healthcare resource allocation.

Stuttering Disfluency Detection Using Machine Learning Approaches

Stuttering is a neurodevelopmental speech disorder wherein people suffer from disfluency in speech generation. Recent research has applied machine learning and deep learning approaches to stuttering disfluency recognition and classification. However, these studies have focussed on small datasets, generated by a limited number of speakers and within specific tasks, such as reading. This paper rigorously investigates the effective use of eight well-known machine learning classifiers, on two publicly available datasets (FluencyBank and SEP-28k) to automatically detect stuttering disfluency using multiple objective metrics, i.e. prediction accuracy, recall, precision, F1-score, and AUC measures. Our experimental results on the two datasets show that the Random Forest classifier achieves the best performance, with an accuracy of 50.3% and 50.35%, a recall of 50% and 42%, a precision of 42% and 46%, and an F1 score of 42% and 34%, against the FluencyBank and SEP-28K datasets, respectively. Moreover, we show that the machine learning-based approaches may not be effective in accurate stuttering disfluency evaluation, due to diverse variations in speech rate, and differences in vocal tracts between children and adults. We argue that the use of deep learning approaches and Automatic Speech Recognition (ASR) with language models may improve outcomes, specifically for large scale and imbalanced datasets.

Combining Predictions of Auto Insurance Claims

This paper aims to better predict highly skewed auto insurance claims by combining candidate predictions. We analyze a version of the Kangaroo Auto Insurance company data and study the effects of combining different methods using five measures of prediction accuracy. The results show the following. First, when there is an outstanding (in terms of Gini Index) prediction among the candidates, the “forecast combination puzzle” phenomenon disappears. The simple average method performs much worse than the more sophisticated model combination methods, indicating that combining different methods could help us avoid performance degradation. Second, the choice of the prediction accuracy measure is crucial in defining the best candidate prediction for “low frequency and high severity” (LFHS) data. For example, mean square error (MSE) does not distinguish well between model combination methods, as the values are close. Third, the performances of different model combination methods can differ drastically. We propose using a new model combination method, named ARM-Tweedie, for such LFHS data; it benefits from an optimal rate of convergence and exhibits a desirable performance in several measures for the Kangaroo data. Fourth, overall, model combination methods improve the prediction accuracy for auto insurance claim costs. In particular, Adaptive Regression by Mixing (ARM), ARM-Tweedie, and constrained Linear Regression can improve forecast performance when there are only weak learners or when no dominant learner exists.

A simulation analysis to explore when using a calibration function is preferred over a scalar factor for calibrating safety performance functions

The Highway Safety Manual (HSM) recommends calibrating Safety Performance Functions using a scalar calibration factor. Recently, a few studies explored the merits of estimating a calibration function instead of a calibration factor. Although it seems a promising approach, it is not clear when a calibration function should be preferred over a scalar calibration factor. On the one hand estimating a scalar factor is easier than estimating a calibration function; on the other hand, the calibration results may improve using a calibration function. This study performs a simulation study to compare the two calibration strategies for different ranges of data characteristics (i.e.: sample mean and variance) as well as the sample size. A measure of prediction accuracy is used to compare the two methods. The results show that as the sample size increases, or variation of data decreases, the calibration function performs better than the scalar calibration factor. If the analyst can collect a sample of at least 150 locations, calibration function is recommended over the scalar factor. If the HSM recommendation of 30-50 locations is used and the analyst desires a better accuracy, calibration function is recommended only if the coefficient of variation of data is less than 2. Otherwise, calibration factor yields better results.

An Hour-Ahead PV Power Forecasting Method Based on an RNN-LSTM Model for Three Different PV Plants

Incorporating solar energy into a grid necessitates an accurate power production forecast for photovoltaic (PV) facilities. In this research, output PV power was predicted at an hour ahead on yearly basis for three different PV plants based on polycrystalline (p-si), monocrystalline (m-si), and thin-film (a-si) technologies over a four-year period. Wind speed, module temperature, ambiance, and solar irradiation were among the input characteristics taken into account. Each PV plant power output was the output parameter. A deep learning method (RNN-LSTM) was developed and evaluated against existing techniques to forecast the PV output power of the selected PV plant. The proposed technique was compared with regression (GPR, GPR (PCA)), hybrid ANFIS (grid partitioning, subtractive clustering and FCM) and machine learning (ANN, SVR, SVR (PCA)) methods. Furthermore, different LSTM structures were also investigated, with recurrent neural networks (RNN) based on 2019 data to determine the best structure. The following parameters of prediction accuracy measure were considered: RMSE, MSE, MAE, correlation (r) and determination (R2) coefficients. In comparison to all other approaches, RNN-LSTM had higher prediction accuracy on the basis of minimum (RMSE and MSE) and maximum (r and R2). The p-si, m-si and a-si PV plants showed the lowest RMSE values of 26.85 W/m2, 19.78 W/m2 and 39.2 W/m2 respectively. Moreover, the proposed method was found to be robust and flexible in forecasting the output power of the three considered different photovoltaic plants.

Using an adaptive network‐based fuzzy inference system model to predict the loss ratio of petroleum insurance in Egypt

AbstractInsurance companies and those interested in developing insurance services seek to use modern mathematical and statistical methods to study further and analyze all the company's corporate internal and external performance indicators. Loss ratio is a vital indicator used to measure performance and predict future losses in insurance companies. Many pivotal processors, such as underwriting and pricing depending on it. Therefore, accurate predictions assist insurance companies in making decisions properly. Thus, this paper aims to use the adaptive network‐based fuzzy inference system (ANFIS) and autoregressive integrated moving average (ARIMA) models in forecasting the loss ratio of petroleum insurance in Misr Insurance Holding Company from 1995 to 2019. We applied many ANFIS models according to ANFIS properties and used the first 21 years (1995–2015), making up the training data set, which represents 85% of the data, as well as the past 4 years (2016–2019). Which are used for the testing stage and represent 15% of the data. Our finding concluded that ANFIS models give more accurate results than ARIMA models in predicting the loss ratio during the investigation by comparing results using predictive accuracy measures.

Screening tools for predicting posttraumatic stress disorder in acutely injured adult trauma patients: A systematic review.

Adult trauma patients are at risk of developing posttraumatic stress disorder (PTSD). Early intervention reduces the development of PTSD, but few trauma patients seek and obtain care. Valid and reliable screening tools are needed to identify patients at risk of developing PTSD. The objective of this review is to identify existing screening tools and evaluate their accuracy for predicting PTSD outcomes. PubMed, PsychInfo, and ClinicalTrials.gov were searched for studies evaluating the predictive accuracy of PTSD screening tools among traumatically injured adult civilians. Eligible studies assessed patients during acute hospitalization and at least 1 month following injury to measure PTSD outcome. Eligible outcomes included measures of predictive accuracy, such as sensitivity and specificity. The Quality Assessment of Diagnostic Accuracy Studies 2 tool was used to assess the risk of bias of each study, and the strength of evidence was assessed following the Agency for Healthcare Research and Quality guidelines. Forty-nine studies were included evaluating the predictive accuracy of 38 screening tools. Most tools were assessed in a single study. Questionnaire-style tools had more favorable predictive ability than diagnostic interview assessments. The Injured Trauma Survivor Screen, Posttraumatic Adjustment Screen, the PTSD Checklist for DSM-5, and the Richmond et al. tool demonstrated the most favorable predictive accuracy, with high sensitivity (75-100%) and specificity (67-94%). Common sources of bias were selection bias due to high attrition rate and using nondiagnostic tools to assess PTSD symptoms at follow-up. Although sensitivity and specificity of PTSD predictive tools varied widely, several emerged with favorable predictive accuracy. Further research is needed to define the ability of screening and intervention to prevent PTSD in injured trauma survivors. The results of this review can inform screening tool options for screening programs and future intervention studies. Systematic review, level III.