Enhanced prognostic accuracy in severe TBI: a comprehensive nomogram analysis.

OBJECTIVE: This study aims to enhance prognostic accuracy in severe traumatic brain injury (STBI) by developing a novel nomogram that integrates clinical and paraclinical data. METHODS: Data from 263 STBI patients were analyzed, focusing on critical variables such as age, Glasgow Coma Scale scores, pupil responsiveness, CT findings, and blood markers. A rigorous regression analysis was conducted to identify significant predictors. The nomogram underwent internal and external validation, and its predictive performance was compared with existing models through a meta-analysis. RESULTS: The novel nomogram demonstrated superior predictive accuracy for STBI outcomes compared to traditional models. Key predictors, including age, Glasgow Coma Scale scores, pupil responsiveness, CT findings, and specific blood markers, were harmonized to provide a more precise prognostic tool. Validation processes confirmed the robustness and reliability of the nomogram. CONCLUSION: The developed nomogram represents a significant advancement in STBI prognosis, offering clinicians a powerful tool to improve patient care strategies. By integrating CT imaging and blood parameters, the nomogram enhances the precision of outcome predictions, facilitating better-informed clinical decisions.

Harnessing the power of child development records to detect early neurodevelopmental disorders using Bayesian analysis.

AIM: This study aims to analyse the developmental data from public health nurses (PHNs) to identify early indicators of neurodevelopmental disorders (NDDs) in young children using Bayesian network (BN) analysis to determine factor combinations that improve diagnosis accuracy. METHODS: The study cohort was 501 children who underwent health checkups at 18 and 36-month. Data included demographics, pregnancy, delivery, neonatal factors, maternal interviews, and physical and neurological findings. Diagnoses were made by paediatricians and child psychiatrists using standardised tools. Predictive accuracy was assessed by the receiver operating characteristic (ROC) curve analysis. RESULTS: We identified several infant/toddler factors significantly associated with NDD diagnoses. Predictive factors included meconium-stained amniotic fluid, 1 min Apgar score, and early developmental milestones. ROC curve analysis showed varying predictive accuracies based on evaluation timing. The 10-month checkup was valid for screening but less reliable for excluding low-risk cases. The 18-month evaluation accurately identified children at NDD risk. CONCLUSION: The study demonstrates the potential of using developmental records for early NDD detection, emphasising early monitoring and intervention for at-risk children. These findings could guide future infant mental health initiatives in the community.

Comparison of Four Severity Assessment Scoring Systems in Critically Ill Patients for Predicting Patient Outcomes: A Prospective Observational Study From a Single Tertiary Center in Central India.

Background and aim A variety of scoring systems are employed in intensive care units (ICUs) with the objective of predicting patient morbidity and mortality. The present study aimed to compare four different severity assessment scoring systems, namely, Acute Physiology and Chronic Health Evaluation II (APACHE II), Rapid Emergency Medicine Score (REMS), Sequential Organ Failure Assessment (SOFA), and Simplified Acute Physiologic Score II (SAPS II) to predict prognosis of all patients admitted to a mixed medical ICU of a tertiary care teaching hospital in central India. Methods The prospective observational study included 1136 patients aged 18 years or more, admitted to the mixed medical ICU. All patients underwent severity assessment using the four scoring systems, namely APACHE II, SOFA, REMS, and SAPS II, after admission. Predicted mortality was calculated from each of the scores and actual patient outcomes were noted. Receiver operating curve analysis was undertaken to identify the cut-off value of individual scoring systems for predicting mortality with optimum sensitivity and specificity. Calibration and discrimination were employed to ascertain the validity of each scoring model. Bivariate and multivariable logistic regression analyses among the study participants were conducted to identify the best scoring system, after adjusting for potential confounders. Results Final analysis was done on 957 study participants (mean (±SD) age-58.4 (±12.9) years; males-62.2%). The mortality rate was 14.7%. APACHE II, SOFA, SAPS II, and REMS scores were significantly higher among the non-survivors as compared to the survivors (p<0.05). SAPS II was found to have the highest AUC of 0.981 (p<0.001). SAPS II score >58 had 93.6% sensitivity, 94.1% specificity, 73.3% PPV, 98.8% NPV, and 94.0% diagnostic accuracy in predicting mortality. This scoring system also had the best calibration. Binary logistic regression showed that all four scoring systems were significantly associated with ICU mortality. After adjusting for each other, only SAPS II remained significantly associated with ICU mortality. Conclusion Both SAPS II and APACHE II were observed to have good calibration and discriminatory power; however, SAPS II had the best prediction power suggesting that it may be a useful tool for clinicians and researchers in assessing the severity of illness and mortality risk in critically ill patients.

Utility of saturation trends to predict successful weaning of nasal CPAP in very preterm neonates - A prospective study.

BACKGROUND: There is no objective criteria to wean CPAP in preterm neonates. We aimed to assess the accuracy of 'saturation trends' to predict successful CPAP discontinuation. METHODS: We included very preterm neonates who required CPAP. Index tests were 'saturation trends'. Outcome was successful CPAP discontinuation, defined as baby stable in room air for 72 h. RESULTS: We had 120 neonates with mean±SD gestation 28.6±1.8 weeks. 96 (80%) neonates had successful discontinuation and 24 (20%) failed. Neonates with successful discontinuation had significantly greater 'saturation trends' during 24 h before discontinuing CPAP compared to those who failed [64.3 (48.1-83.7) vs. 47.3 (23.0-65.0), p = 0.001]. Saturations > 95% while on CPAP with 21% FiO2 for > 60% time had 63% sensitivity and 70% specificity to predict successful CPAP discontinuation. CONCLUSION: 'Saturation trends' is a readily available objective parameter that can be used to guide weaning CPAP in preterm neonates.

Establishment of a nomogram model for predicting distant metastasis in pancreatic ductal adenocarcinoma: a comparative analysis of different lymph node staging systems based on the SEER database.

The purpose of this study was to compare the predictive value of different lymph node staging systems and to develop an optimal prognostic nomogram for predicting distant metastasis in pancreatic ductal adenocarcinoma (PDAC). Our study involved 6364 patients selected from the Surveillance, Epidemiology, and End Results (SEER) database and 126 patients from China. Independent risk factors for distant metastasis were screened by univariate and multivariate logistic regression analyses, and a model-based comparison of different lymph node staging systems was conducted. Furthermore, we developed a nomogram for predicting distant metastasis using the optimal performance lymph node staging system. The lymph node ratio (LNR), log odds of positive lymph nodes (LODDS), age, primary site, grade, tumor size, American Joint Committee on Cancer (AJCC) 7th Edition T stage, and radiotherapy recipient status were significant predictors of distant metastasis in PDAC patients. The model with the LODDS was a better fit than the model with the LNR. We developed a nomogram model based on LODDS and six clinical parameters. The area under the curve (AUC) and concordance index (C-index) of 0.753 indicated that this model satisfied the discrimination criteria. Kaplan-Meier curves indicate a significant difference in OS among patients with different metastasis risks. LODDS seems to have a superior ability to predict distant metastasis in PDAC patients compared with the AJCC 8th Edition N stage, PLN and LNR staging systems. Moreover, we developed a nomogram model for predicting distant metastasis. Clinicians can use the model to detect patients at high risk of distant metastasis and to make further clinical decisions.

Accurate prediction of spatial distribution of soil potentially toxic elements using machine learning and associated key influencing factors identification: A case study in mining and smelting area in southwestern China.

Accurate prediction of spatial distribution of potentially toxic elements (PTEs) is crucial for soil pollution prevention and risk control. Achieving accurate prediction of spatial distribution of soil PTEs at a large scale using conventional methods presents significant challenges. In this study, machine learning (ML) models, specially artificial neural network (ANN), random forest (RF), and extreme gradient boosting (XGB), were used to predict spatial distribution of soil PTEs and identify associated key factors in mining and smelting area located in Yunnan Province, China, under the three scenarios: (1) natural + socioeconomic + spatial datasets (NS), (2) NS + irrigation pollution index (IPI) datasets, (3) NS + IPI + deposition (DEPO) datasets. The results highlighted the combination of NS+IPI+DEPO yielded the highest predictive accuracy across ML models. Particularly, XGB exhibited the highest performance for As (R2 =0.7939), Cd (R2 =0.6679), Cu (R2 =0.8519), Pb (R2 =0.8317), and Zn (R2 =0.7669), whereas RF performed the best for Ni (R2 =0.7146). The feature importance and Shapley additive explanation (SHAP) analysis revealed that DEPO and IPI were the pivotal factors influencing the distribution of soil PTEs. Our findings highlighted the important role of DEPO in spatial distribution prediction of soil PTEs, which has often been ignored in previous studies.

Ambient Mass Spectrometry and Machine Learning-Based Diagnosis System for Acute Coronary Syndrome.

Aims: The purpose of this study is to establish a novel diagnosis system in early acute coronary syndrome (ACS) using probe electrospray ionization-mass spectrometry (PESI-MS) and machine learning (ML) and to validate the diagnostic accuracy. Methods: A total of 32 serum samples derived from 16 ACS patients and 16 control patients were analyzed by PESI-MS. The acquired mass spectrum dataset was subsequently analyzed by partial least squares (PLS) regression to find the relationship between the two groups. A support vector machine, an ML method, was applied to the dataset to construct the diagnostic algorithm. Results: Control and ACS groups were separated into the two clusters in the PLS plot, indicating ACS patients differed from the control in the profile of serum composition obtained by PESI-MS. The sensitivity, specificity, and accuracy of our diagnostic system were all 93.8%, and the area under the receiver operating characteristic curve showed 0.965 (95% CI: 0.84-1). Conclusion: The PESI-MS and ML-based diagnosis system are likely an optimal solution to assist physicians in ACS diagnosis with its remarkably predictive accuracy.

The relationship between weight-adjusted-waist index and suicidal ideation: evidence from NHANES.

BACKGROUND: Amidst growing evidence of the intricate link between physical and mental health, this study aims to dissect the relationship between the waist-to-weight index (WWI) and suicidal ideation within a representative sample of the US population, proposing WWI as a novel metric for suicide risk assessment. METHODS: The study engaged a sample of 9500 participants in a cross-sectional design. It employed multivariate logistic and linear regression analyses to probe the association between WWI and suicidal ideation. It further examined potential nonlinear dynamics using a weighted generalized additive model alongside stratified analyses to test the relationship's consistency across diverse demographic and health variables. RESULTS: Our analysis revealed a significant positive correlation between increased WWI and heightened suicidal ideation, characterized by a nonlinear relationship that persisted in the adjusted model. Subgroup analysis sustained the association's uniformity across varied population segments. CONCLUSIONS: The study elucidates WWI's effectiveness as a predictive tool for suicidal ideation, underscoring its relevance in mental health evaluations. By highlighting the predictive value of WWI, our findings advocate for the integration of body composition considerations into mental health risk assessments, thereby broadening the scope of suicide prevention strategies.

A prospective cohort study evaluating the TRISS and TRISS-SpO2 scoring systems for assessing mortality risk in trauma study participants in India.

Background: Globally, trauma cases have significant morbidity and mortality. Hence, various scoring systems have been designed to improve the prognosis in trauma cases. Trauma and Injury Severity Score (TRISS) is one of the widely used models to predict mortality; however, it has certain limitation. We have aimed to evaluate the survival prediction of new model TRISS-oxygen saturation (SpO2) and to compare with original TRISS score in trauma study participants. Methods: This was a prospective cohort study conducted on 380 trauma study participants admitted to the surgery department from January 20, 2021, to November 28, 2021. The proposed model includes TRISS-SpO2 which replaces pulse SpO2 instead of revised trauma score in the original TRISS score. Probability of survival (Ps) was calculated for both models using coefficients derived from Walker-Duncan regression analysis analyzed from the Major Trauma Outcome Study. Receiver operating characteristic curve analysis was used to predict model performance and the accuracy was calculated. Results: The mortality rate in the present study was 30 (7.9%). The predictive accuracy of original TRISS score which calculated Ps based on respiratory rate was 97.11%, and for the proposed model of TRISS score which calculated Ps based on SpO2 was found 97.11%, and thus there is no significant difference in the performance. Conclusions: The new proposed model TRISS-SpO2 showed a good accuracy which is similar to original TRISS score. However, the new tool TRISS-SpO2 might be easier to use for robust performance in the clinical setting.

A Comprehensive Study on the Diagnostic Value of Multi-Slice Computed Tomography for Peripancreatic Infection in Elderly With Severe Acute Pancreatitis.

Background: This study investigated the diagnostic efficacy of multi-slice spiral computed tomography (MSCT) perfusion imaging in evaluating peripancreatic infection in elderly patients with severe acute pancreatitis (SAP). Methods: A retrospective analysis was conducted on the clinical data of 110 elderly SAP patients treated at our hospital from March 2018 to August 2019. The study correlated MSCT perfusion imaging characteristics with peripancreatic infection in elderly SAP patients. Additionally, receiver operating characteristic (ROC) curves were constructed to assess the diagnostic performance of MSCT perfusion imaging parameters in evaluating peripancreatic infection in elderly SAP patients. Results: The results indicated that among all 110 elderly SAP patients, the incidence rate of peripancreatic infection was 20.91%, with a mortality rate of 0.91%. MSCT perfusion imaging revealed that after peripancreatic infection in elderly SAP patients, there was a decrease in pancreatic density, local enlargement of the pancreas, blurring of the pancreatic margins, and associated ascites. Compression/narrowing/occlusion of the splenic vein was observed in 22 patients, compression/narrowing/occlusion of the superior mesenteric vein in 17 patients, thickening/thrombosis of the portal vein in 19 patients, and collateral circulation in 21 patients. Compared to elderly SAP patients without peripancreatic infection, those with the infection showed prolonged peak times, reduced peak heights, and decreased blood flow. ROC analysis indicated that the combination of the three parameters (peak time, peak height, and blood flow) had higher specificity and area under the curve (AUC) than single parameters, with no significant difference in sensitivity between the combination and single parameters. Conclusions: In conclusion, combining the three key MSCT perfusion imaging parameters (peak time, peak height, and blood flow) can significantly enhance the predictive efficacy for the risk of peripancreatic infection in elderly SAP patients.

Identifying animal behaviours from accelerometers: Improving predictive accuracy of machine learning by refining the variables selected, data frequency, and sample duration.

Observing animals in the wild often poses extreme challenges, but animal-borne accelerometers are increasingly revealing unobservable behaviours. Automated machine learning streamlines behaviour identification from the substantial datasets generated during multi-animal, long-term studies; however, the accuracy of such models depends on the qualities of the training data. We examined how data processing influenced the predictive accuracy of random forest (RF) models, leveraging the easily observed domestic cat (Felis catus) as a model organism for terrestrial mammalian behaviours. Nine indoor domestic cats were equipped with collar-mounted tri-axial accelerometers, and behaviours were recorded alongside video footage. From this calibrated data, eight datasets were derived with (i) additional descriptive variables, (ii) altered frequencies of acceleration data (40 Hz vs. a mean over 1 s) and (iii) standardised durations of different behaviours. These training datasets were used to generate RF models that were validated against calibrated cat behaviours before identifying the behaviours of five free-ranging tag-equipped cats. These predictions were compared to those identified manually to validate the accuracy of the RF models for free-ranging animal behaviours. RF models accurately predicted the behaviours of indoor domestic cats (F-measure up to 0.96) with discernible improvements observed with post-data-collection processing. Additional variables, standardised durations of behaviours and higher recording frequencies improved model accuracy. However, prediction accuracy varied with different behaviours, where high-frequency models excelled in identifying fast-paced behaviours (e.g. locomotion), whereas lower-frequency models (1 Hz) more accurately identified slower, aperiodic behaviours such as grooming and feeding, particularly when examining free-ranging cat behaviours. While RF modelling offered a robust means of behaviour identification from accelerometer data, field validations were important to validate model accuracy for free-ranging individuals. Future studies may benefit from employing similar data processing methods that enhance RF behaviour identification accuracy, with extensive advantages for investigations into ecology, welfare and management of wild animals.

A new sample-size planning approach for person-specific VAR(1) studies: Predictive accuracy analysis.

Researchers increasingly study short-term dynamic processes that evolve within single individuals using N = 1 studies. The processes of interest are typically captured by fitting a VAR(1) model to the resulting data. A crucial question is how to perform sample-size planning and thus decide on the number of measurement occasions that are needed. The most popular approach is to perform a power analysis, which focuses on detecting the effects of interest. We argue that performing sample-size planning based on out-of-sample predictive accuracy yields additional important information regarding potential overfitting of the model. Predictive accuracy quantifies how well the estimated VAR(1) model will allow predicting unseen data from the same individual. We propose a new simulation-based sample-size planning method called predictive accuracy analysis (PAA), and an associated Shiny app. This approach makes use of a novel predictive accuracy metric that accounts for the multivariate nature of the prediction problem. We showcase how the values of the different VAR(1) model parameters impact power and predictive accuracy-based sample-size recommendations using simulated data sets and real data applications. The range of recommended sample sizes is smaller for predictive accuracy analysis than for power analysis.

Accuracy of respiratory muscle assessments to predict weaning outcomes: a systematic review and comparative meta-analysis.

BACKGROUND: Several bedside assessments are used to evaluate respiratory muscle function and to predict weaning from mechanical ventilation in patients on the intensive care unit. It remains unclear which assessments perform best in predicting weaning success. The primary aim of this systematic review and meta-analysis was to summarize and compare the accuracy of the following assessments to predict weaning success: maximal inspiratory (PImax) and expiratory pressures, diaphragm thickening fraction and excursion (DTF and DE), end-expiratory (Tdiee) and end-inspiratory (Tdiei) diaphragm thickness, airway occlusion pressure (P0.1), electrical activity of respiratory muscles, and volitional and non-volitional assessments of transdiaphragmatic and airway opening pressures. METHODS: Medline (via Pubmed), EMBASE, Web of Science, Cochrane Library and CINAHL were comprehensively searched from inception to 04/05/2023. Studies including adult mechanically ventilated patients reporting data on predictive accuracy were included. Hierarchical summary receiver operating characteristic (HSROC) models were used to estimate the SROC curves of each assessment method. Meta-regression was used to compare SROC curves. Sensitivity analyses were conducted by excluding studies with high risk of bias, as assessed with QUADAS-2. Direct comparisons were performed using studies comparing each pair of assessments within the same sample of patients. RESULTS: Ninety-four studies were identified of which 88 studies (n = 6296) reporting on either PImax, DTF, DE, Tdiee, Tdiei and P0.1 were included in the meta-analyses. The sensitivity to predict weaning success was 63% (95% CI 47-77%) for PImax, 75% (95% CI 67-82%) for DE, 77% (95% CI 61-87%) for DTF, 74% (95% CI 40-93%) for P0.1, 69% (95% CI 13-97%) for Tdiei, 37% (95% CI 13-70%) for Tdiee, at fixed 80% specificity. Accuracy of DE and DTF to predict weaning success was significantly higher when compared to PImax (p = 0.04 and p < 0.01, respectively). Sensitivity and direct comparisons analyses showed that the accuracy of DTF to predict weaning success was significantly higher when compared to DE (p < 0.01). CONCLUSIONS: DTF and DE are superior to PImax and DTF seems to have the highest accuracy among all included respiratory muscle assessments for predicting weaning success. Further studies aiming at identifying the optimal threshold of DTF to predict weaning success are warranted. TRIAL REGISTRATION: PROSPERO CRD42020209295, October 15, 2020.

Oncotype DX in Breast Cancer Management: Insights and Outcomes From the United Arab Emirates.

Introduction Breast cancer remains the most significant cancer affecting women worldwide, with an increasing incidence, especially in developing regions. The introduction of genomic tests like Oncotype DX has revolutionized personalized treatment, allowing for more tailored approaches to therapy. This study focuses on the United Arab Emirates (UAE), where breast cancer is the leading cause of cancer-related deaths among women, aiming to assess the predictive accuracy of the Oncotype DX test in categorizing patients based on recurrence risk. Materials and methods A retrospective cohort study was conducted on 95 breast cancer patients diagnosed at Tawam Hospital between 2013 and 2017 who underwent Oncotype DX testing. Data on patient demographics, tumor characteristics, treatment details, and Oncotype DX scores were collected. Survival analysis was performed using the Kaplan-Meier method, with the chi-square goodness of fit test assessing the model's adequacy. Results The cohort's age range was 27-71 years, with a mean age of 50, indicating a significant concentration of cases in the early post-menopausal period. The Oncotype DX analysis classified 55 patients (57.9%) as low risk, 29 (30.5%) as medium risk, and 11 (11.6%) as high risk of recurrence. The majority, 73 patients (76.8%), did not receive chemotherapy, highlighting the test's impact on treatment decisions. The survival analysis revealed no statistically significant difference in recurrence rates across the Oncotype DX risk categories (p = 0.268231). Conclusion The Oncotype DX test provides a valuable genomic approach to categorizing breast cancer patients by recurrence risk in the UAE. While the test influences treatment decisions, particularly the use of chemotherapy, this study did not find a significant correlation between Oncotype DX risk categories and actual recurrence events. These findings underscore the need for further research to optimize the use of genomic testing in the UAE's diverse patient population and enhance personalized treatment strategies in breast cancer management.

Advanced hybrid LSTM-transformer architecture for real-time multi-task prediction in engineering systems.

In the field of engineering systems-particularly in underground drilling and green stormwater management-real-time predictions are vital for enhancing operational performance, ensuring safety, and increasing efficiency. Addressing this niche, our study introduces a novel LSTM-transformer hybrid architecture, uniquely specialized for multi-task real-time predictions. Building on advancements in attention mechanisms and sequence modeling, our model integrates the core strengths of LSTM and Transformer architectures, offering a superior alternative to traditional predictive models. Further enriched with online learning, our architecture dynamically adapts to variable operational conditions and continuously incorporates new field data. Utilizing knowledge distillation techniques, we efficiently transfer insights from larger, pretrained networks, thereby achieving high predictive accuracy without sacrificing computational resources. Rigorous experiments on sector-specific engineering datasets validate the robustness and effectiveness of our approach. Notably, our model exhibits clear advantages over existing methods in terms of predictive accuracy, real-time adaptability, and computational efficiency. This work contributes a pioneering predictive framework for targeted engineering applications, offering actionable insights into.

Genomic prediction using machine learning: a comparison of the performance of regularized regression, ensemble, instance-based and deep learning methods on synthetic and empirical data.

BACKGROUND: The accurate prediction of genomic breeding values is central to genomic selection in both plant and animal breeding studies. Genomic prediction involves the use of thousands of molecular markers spanning the entire genome and therefore requires methods able to efficiently handle high dimensional data. Not surprisingly, machine learning methods are becoming widely advocated for and used in genomic prediction studies. These methods encompass different groups of supervised and unsupervised learning methods. Although several studies have compared the predictive performances of individual methods, studies comparing the predictive performance of different groups of methods are rare. However, such studies are crucial for identifying (i) groups of methods with superior genomic predictive performance and assessing (ii) the merits and demerits of such groups of methods relative to each other and to the established classical methods. Here, we comparatively evaluate the genomic predictive performance and informally assess the computational cost of several groups of supervised machine learning methods, specifically, regularized regression methods, deep, ensemble and instance-based learning algorithms, using one simulated animal breeding dataset and three empirical maize breeding datasets obtained from a commercial breeding program. RESULTS: Our results show that the relative predictive performance and computational expense of the groups of machine learning methods depend upon both the data and target traits and that for classical regularized methods, increasing model complexity can incur huge computational costs but does not necessarily always improve predictive accuracy. Thus, despite their greater complexity and computational burden, neither the adaptive nor the group regularized methods clearly improved upon the results of their simple regularized counterparts. This rules out selection of one procedure among machine learning methods for routine use in genomic prediction. The results also show that, because of their competitive predictive performance, computational efficiency, simplicity and therefore relatively few tuning parameters, the classical linear mixed model and regularized regression methods are likely to remain strong contenders for genomic prediction. CONCLUSIONS: The dependence of predictive performance and computational burden on target datasets and traits call for increasing investments in enhancing the computational efficiency of machine learning algorithms and computing resources.

The Effect of Missing Item Data on the Relative Predictive Accuracy of Correctional Risk Assessment Tools.

Missing data are pervasive in risk assessment but their impact on predictive accuracy has largely been unexplored. Common techniques for handling missing risk data include summing available items or proration; however, multiple imputation is a more defensible approach that has not been methodically tested against these simpler techniques. We compared the validity of these three missing data techniques across six conditions using STABLE-2007 (N = 4,286) and SARA-V2 (N = 455) assessments from men on community supervision in Canada. Condition 1 was the observed data (low missingness), and Conditions 2 to 6 were generated missing data conditions, whereby 1% to 50% of items per case were randomly deleted in 10% increments. Relative predictive accuracy was unaffected by missing data, and simpler techniques performed just as well as multiple imputation, but summed totals underestimated absolute risk. The current study therefore provides empirical justification for using proration when data are missing within a sample.

Predicting Facial Attractiveness from Colour Cues: A New Analytic Framework.

Various facial colour cues were identified as valid predictors of facial attractiveness, yet the conventional univariate approach has simplified the complex nature of attractiveness judgement for real human faces. Predicting attractiveness from colour cues is difficult due to the high number of candidate variables and their inherent correlations. Using datasets from Chinese subjects, this study proposed a novel analytic framework for modelling attractiveness from various colour characteristics. One hundred images of real human faces were used in experiments and an extensive set of 65 colour features were extracted. Two separate attractiveness evaluation sets of data were collected through psychophysical experiments in the UK and China as training and testing datasets, respectively. Eight multivariate regression strategies were compared for their predictive accuracy and simplicity. The proposed methodology achieved a comprehensive assessment of diverse facial colour features and their role in attractiveness judgements of real faces; improved the predictive accuracy (the best-fit model achieved an out-of-sample accuracy of 0.66 on a 7-point scale) and significantly mitigated the issue of model overfitting; and effectively simplified the model and identified the most important colour features. It can serve as a useful and repeatable analytic tool for future research on facial impression modelling using high-dimensional datasets.

Dynamic Risk Scales Degrade Over Time: Evidence for Reassessments.

Risk tools containing dynamic (potentially changeable) factors are routinely used to evaluate the recidivism risk of justice-involved individuals. Although frequent reassessments are recommended, there is little research on how the predictive accuracy of dynamic risk assessments changes over time. This study examined the extent to which predictive accuracy decreases over time for the ACUTE-2007 and the STABLE-2007 sexual recidivism risk tools. We used two independent samples of men on community supervision (NStudy 1 = 795; NStudy 2 = 4,221). For all outcomes (sexual, violent, and any recidivism [including technical violations]), reassessments improved predictive accuracy, with the largest effects found for the most recent assessment (i.e., those closest in time prior to the recidivism event). Based on these results, we recommend that ACUTE-2007 assessments occur at least every 30 days and that the STABLE-2007 assessments occur every 6 months or after significant life changes (e.g., successful completion of treatment).

Time-dependent receiver operating characteristic curve estimator for correlated right-censored time-to-event data.

In clinical trials, evaluating the accuracy of risk scores (markers) derived from prognostic models for prediction of survival outcomes is of major concern. The time-dependent receiver operating characteristic curve and the corresponding area under the receiver operating characteristic curve are appealing measures to evaluate the predictive accuracy. Several estimation methods have been proposed in the context of classical right-censored data which assumes the event time of individuals are independent. In many applications, however, this may not hold true if, for example, individuals belong to clusters or experience recurrent events. Estimates may be biased if this correlated nature is not taken into account. This paper is then aimed to fill this knowledge gap to introduce a time-dependent receiver operating characteristic curve and the corresponding area under the receiver operating characteristic curve estimation method for right-censored data that take the correlated nature into account. In the proposed method, the unknown status of censored subjects is imputed using conditional survival functions given the marker and frailty of the subjects. An extensive simulation study is conducted to evaluate and demonstrate the finite sample performance of the proposed method. Finally, the proposed method is illustrated using two real-world examples of lung cancer and kidney disease.