Development Of Predictive Models Research Articles

RNA mis-splicing in children with congenital myotonic dystrophy is associated with physical function.

Dysregulated RNA alternative splicing is the hallmark of myotonic dystrophy type 1 (DM1). However, the association between RNA mis-splicing and physical function in children with the most severe form of disease, congenital myotonic dystrophy (CDM), is unknown. Eighty-two participants (42 adults with DM1 and 40 children with CDM) with muscle biopsies and measures of myotonia, motor function, and strength were combined from five observational studies. Data were normalized and correlated with an aggregate measure of alternative splicing dysregulation, [MBNL]inferred, in skeletal muscle biopsies. Multiple linear regression analysis was performed to predict [MBNL]inferred using clinical outcome measures alone. Similar analyses were performed to predict 12-month physical function using baseline metrics. Myotonia (measured via vHOT) was significantly correlated with RNA mis-splicing in our cross-sectional population of all DM1 individuals; CDM participants alone displayed no myotonia despite a similar range of RNA mis-splicing. Measures of motor performance and muscle strength were significantly associated with [MBNL]inferred in our cohort of all DM1 individuals and when assessing children with CDMindependently. Multiple linear regression analyses yielded two models capable of predicting [MBNL]inferred from select clinical outcome assessments alone in all subjects(adjusted R2 = 0.6723) or exclusively in children with CDM (adjusted R2 = 0.5875). Our findings establish significant correlations between skeletal muscle performance and a composite measure of alternative splicing dysregulation, [MBNL]inferred, in DM1. The strength of these correlations and the development of predictive models will assist in designing efficacious clinical trials for individuals with DM1, particularly CDM.

Development of an AI-Based Suicide Ideation Prediction Model for People with Disabilities

South Korea has one of the highest suicide rates among countries in the Organisation for Economic Co-Operation and Development, and the suicide rate among people with disabilities is more than twice that of the general population. This study aimed to develop an artificial intelligence-based suicide ideation prediction model for people with disabilities in order to provide a proactive approach for managing high-risk groups and offer evidence for establishing suicide prevention policies. The support vector machine, adaptive boost (AdaBoost), and bidirectional long short-term memory (Bi-LSTM) models were used in this study. Data from the Disability and Life Dynamics Panel for 2018–2021 were used. The performance of the models was evaluated based on the accuracy, sensitivity, specificity, and area under the receiver operating characteristic curve (AUC). All the prediction models demonstrated excellent performance, with AUC > 0.80 (0.83–0.87). The best-performing models were AdaBoost (0.87) for accuracy, Bi-LSTM (0.90) for sensitivity, and AdaBoost (0.90) for specificity. This study is the first to develop an artificial intelligence-based suicide ideation prediction model for disabled people and is significant in that it suggests ways to pre-emptively manage groups at high risk for suicide, providing evidence for the establishment of suicide prevention policies.

Targeted Development and Validation of Clinical Prediction Models in Secondary Care Settings: Opportunities and Challenges for Electronic Health Record Data.

Before deploying a clinical prediction model (CPM) in clinical practice, its performance needs to be demonstrated in the population of intended use. This is also called "targeted validation." Many CPMs developed in tertiary settings may be most useful in secondary care, where the patient case mix is broad and practitioners need to triage patients efficiently. However, since structured or rich datasets of sufficient quality from secondary to assess the performance of a CPM are scarce, a validation gap exists that hampers the implementation of CPMs in secondary care settings. In this viewpoint, we highlight the importance of targeted validation and the use of CPMs in secondary care settings and discuss the potential and challenges of using electronic health record (EHR) data to overcome the existing validation gap. The introduction of software applications for text mining of EHRs allows the generation of structured "big" datasets, but the imperfection of EHRs as a research database requires careful validation of data quality. When using EHR data for the development and validation of CPMs, in addition to widely accepted checklists, we propose considering three additional practical steps: (1) involve a local EHR expert (clinician or nurse) in the data extraction process, (2) perform validity checks on the generated datasets, and (3) provide metadata on how variables were constructed from EHRs. These steps help to generate EHR datasets that are statistically powerful, of sufficient quality and replicable, and enable targeted development and validation of CPMs in secondary care settings. This approach can fill a major gap in prediction modeling research and appropriately advance CPMs into clinical practice.

Iodine-Based Dual-Energy Computed Tomography After Mechanical Thrombectomy Predicts Secondary Neurologic Decline from Cerebral Edema After Severe Stroke.

Patients with severe stroke are at high risk of secondary neurologic decline (ND) from the development of malignant cerebral edema (MCE). However, early infarcts are hard to diagnose on conventional head computed tomography (CT). We hypothesize that high-energy (190keV) virtual monochromatic imaging (VMI) from dual-energy CT (DECT) imaging enables earlier detection of ND from MCE. Consecutive patients with severe stroke with National Institute of Health Stroke Scale (NIHSS) scores > 15 and DECT within 10h of mechanical thrombectomy from May 2020 to March 2022 were included. We excluded patients with parenchymal hematoma type 2 transformation. Retrospective analysis of clinical and novel variables included the VMI Alberta Stroke Program Early CT Score (ASPECTS), total iodine content, and VMI infarct volume. The primary outcome was secondary ND, defined using a composite outcome variable of clinical worsening (increase in NIHSS score ≥ 4 or decrease in Glasgow Coma Scale score > 2) or malignant radiographical edema (midline shift ≥ 5mm at the level of the septum pellucidum). Fisher's exact test and Wilcoxon's test were used for univariate analysis. Logistic regression was used to develop prediction models for categorical outcomes. Eighty-four patients with severe stroke with a median age of 67.5 (interquartile range [IQR] 57-78) years and an NIHSS score of 22 (IQR 18-25) were included. Twenty-nine patients had ND. The VMI ASPECTS, total iodine content, and VMI infarct volume were associated with ND. The VMI ASPECTS, VMI infarct volume, and total iodine content were predictors of ND after adjusting for age, sex, initial NIHSS score, and tissue plasminogen activator administration, with areas under the receiver operating characteristic curve (AUROC) of 0.691 (95% confidence interval [CI] 0.572-0.810), 0.877 (95% CI 0.800-0.954), and 0.845 (95% CI 0.750-0.940). By including all three predictors, the model achieved an AUROC of 0.903 (95% CI 0.84-0.97) and was cross-validated by the leave one out method, with an AUROC of 0.827. The VMI ASPECTS and VMI infarct volume from DECT are superior to the conventional CT ASPECTS and are novel predictors for secondary ND due to MCE after severe stroke. Clinical trial registration ClinicalTrials.gov identifier: NCT04189471.

Nomogram Predictive Model for Vaginal Birth after One Prior Cesarean Section: A Retrospective Study

Background: Repeat cesareans pose significant maternal risks, whereas vaginal birth after cesarean (VBAC) offers better outcomes, with a complication rate of 2.4% compared with 3.6% for elective repeat cesareans and 14.1% for failed trial of labor after cesarean (TOLAC). TOLAC rates are low in China, and success rates vary between 60% and 80%. This study aims to develop a nomogram-based predictive model for VBAC in China and improve existing, less rigorous scoring models. Methods: This retrospective cohort study was conducted at Hangzhou Women's Hospital from February 2015 to March 2020, and included 159 parturient attempts at labor after one prior low transverse cesarean section. The participants were divided into two groups based on their mode of delivery for comparison: the VBAC and the TOLAC failure group. Univariate and multivariate logistic regression analyses were conducted to identify independent predictors for VBAC and develop a nomogram predictive model to estimate the success rate of TOLAC. The bootstrap method was used for internal validation of the models. Three different VBAC prediction models were evaluated by plotting receiver operating characteristic (ROC) curves, calibration curves, and decision curves. Results: A total of 127 women had VBAC and 32 women failed TOLAC, with a success rate of 79.9%. Three independent factors affecting the VBAC were identified: gestational age at delivery, Bishop score and newborn birth weight. A predictive nomogram model for the VBAC was constructed that incorporates these three factors. The model showed a good fit (χ2 = 11.94, p = 0.154) with an overall prediction accuracy of 81.1%. The area under the ROC curve was 0.83 (95% CI (confidence interval), 0.76–0.90) (p < 0.001) and the optimal cut-off value was 83.4%. The bootstrap internal validation showed that our predictive model maintained high overall accuracy and specificity, but exhibited low sensitivity and a low Kappa coefficient. Compared to the Grobman model and Jiaming Rao et al. model, our developed prediction model possesses the strongest discriminatory ability and the highest net benefit, followed by the model by Jiaming Rao et al. All three models demonstrate a high degree of fit. Conclusions: Shorter gestational age at delivery, lower newborn birth weight and higher cervical Bishop score are favorable factors for VBAC. The predictive nomogram model for the VBAC after a single cesarean section, constructed with these three factors, has good predictive efficacy. The model is simple to calculate and has practical value in the clinical selection of suitable candidates for TOLAC after a single cesarean section.

73 Predictors of neurodevelopmental impairment in extreme preterm infants with unremarkable cranial ultrasound: A Canadian population-based cohort

Abstract Background Extreme preterm infants are at high-risk of brain injury and neurodevelopmental impairment (NDI). Previous studies reported significant NDI (sNDI) in preterm infants with no abnormalities on routine cranial ultrasound screening (CUS), traditionally perceived to have favorable outcomes. Recent data from population-based outlining clinical predictors of sNDI in those infants are lacking. Objectives (1) to describe the incidence, perinatal and neonatal characteristics of NDI and sNDI in a large population-based cohort of extreme preterm infants with unremarkable CUS; (2) to develop a prediction model of sNDI (any of: CP ≥ GMFCS stage 3, Bayley III < 70 in any domain, deafness requiring aids, or bilateral blindness) in those infants. Design/Methods A retrospective review of a national cohort of preterm infants born at <29 weeks’ gestation between April 2009 and December 2018. We included surviving infants with unremarkable routine CUS (no hemorrhage, periventricular leukomalacia or ventricular dilatation) who had neurodevelopmental assessment at 18-24 month corrected age at one of participating centres in the Canadian Neonatal Follow Up Network. We compared the baseline characteristics between infants with no NDI and those with any NDI and sNDI. The population sample was then randomly split into training and testing datasets in 70:30 ratio for prediction model’s development and validation, respectively. Multivariate logistic regression with GEE accounting for clustering within site was used, adjusted for variables with p-value<0.1 using backward selection procedure. The AUC and the diagnostic properties of the model developed using training dataset was then validated in the testing dataset. Results Out of 7463 eligible infants, 4327 (58%) were included. Of those, 2501 (59%) had no NDI and 1736 (41%) had NDI. sNDI accounted for 14% of the cohort and one third of those with NDI. Perinatal and neonatal characteristics of the three groups are shown in Table 1. On internal validation, maternal hypertension, maternal level of education, gestational age, male sex, ROP≥ stage 3 and systemic steroids were predictive of sNDI (Table 2). The prediction model had Sensitivity 0.91, NPV 0.90, and AUC 0.69 (95% CI 0.64-0.73). Conclusion In this national cohort, 2 out of 5 extreme preterm infants with unremarkable CUS had NDI and 1 in 7 had sNDI. The developed prediction model had high sensitivity and NPV, but poor discrimination. The findings of this study can help clinicians to identify at-risk infants who may benefit from early targeted interventions.

Development of Predictive Statistical Model for Gaining Valuable Insights in Pharmaceutical Product Recalls.

The rapid progress in artificial intelligence (AI) has revolutionized problem-solving across various domains. The global challenge of pharmaceutical product recalls imposes the development of effective tools to control and reduce shortage of pharmaceutical products and help avoid such recalls. This study employs AI, specifically machine learning (MI), to analyze critical factors influencing formulation, manufacturing, and formulation complexity which could offer promising avenue for optimizing drug development processes. Utilizing FDAZilla and SafeRX tools, an open database model was constructed, and predictive statistical models were developed using Multivariate Analysis and the Least Absolute Shrinkage and Selection Operator (LASSO) Approach. The study focuses on key descriptors such as delivery route, dosage form, dose, BCS classification, solid-state and physicochemical properties, release type, half-life, and manufacturing complexity. Through statistical analysis, a data simplification process identifies critical descriptors, assigning risk numbers and computing a cumulative risk number to assess product complexity and recall likelihood. Partial Least Square Regression and the LASSO approach established quantitative relationships between key descriptors and cumulative risk numbers. Results have identified key descriptors; BCS Class I, dose number, release profile, and drug half-life influencing product recall risk. The LASSO model further confirms these identified descriptors with 71% accuracy. In conclusion, the study presents a holistic AI and machine learning approach for evaluating and forecasting pharmaceutical product recalls, underscoring the importance of descriptors, formulation complexity, and manufacturing processes in mitigating risks associated with product quality.

Development and validation of a risk prediction model for feeding intolerance in neurocritical patients with enteral nutrition.

This study collects and analyzes clinical data on enteral nutrition therapy in neurocritical patients, develops and validates a feeding intolerance (FI) risk prediction model, and provides a theoretical basis for screening patients with high risk of feeding intolerance (FI) and delivering personalized care. A convenience sampling method was employed to select 300 patients who were admitted to a tertiary hospital in China for early enteral nutrition therapy in the neurointensive care unit between April 2022 and December 2022. Independent risk factors for FI were identified using univariate and logistic regression analyses. A prediction model was established, and the goodness of fit and discriminant validity of the model were evaluated. The incidence of FI in neurocritical patients receiving enteral nutrition was 71%. Logistic regression analysis identified age, Glasgow Coma Scale (GCS) scores, Acute Physiology and Chronic Health Evaluation II (APACHE II) scores, mechanical ventilation, feeding via the nasogastric tube route, hyperglycemia, and low serum albumin as independent risk factors for the development of FI (p < 0.05). The predictive formula for FI risk was established as follows: Logit p = -14.737 + 1.184 × mechanical ventilation +2.309 × feeding route +1.650 × age + 1.336 × GCS tertile (6-8 points) + 1.696 × GCS tertile (3-5 points) + 1.753 × APACHE II score + 1.683 × blood glucose value +1.954 × serum albumin concentration. The Hosmer-Lemeshow test showed χ2 = 9.622, p = 0.293, and the area under the ROC curve was 0.941 (95% confidence interval: 0.912-0.970, p < 0.001). The optimal critical value was 0.767, with a sensitivity of 85.9%, a specificity of 90.8%, and a Youden index of 0.715. The early enteral nutrition FI risk prediction model developed in this study demonstrated good predictive ability. This model can serve as a valuable reference for effectively assessing the risk of FI in neurocritical patients, thereby enhancing clinical outcomes.

Development and assessment of a machine learning tool for predicting emergency admission in Scotland

Emergency admissions (EA), where a patient requires urgent in-hospital care, are a major challenge for healthcare systems. The development of risk prediction models can partly alleviate this problem by supporting primary care interventions and public health planning. Here, we introduce SPARRAv4, a predictive score for EA risk that will be deployed nationwide in Scotland. SPARRAv4 was derived using supervised and unsupervised machine-learning methods applied to routinely collected electronic health records from approximately 4.8M Scottish residents (2013-18). We demonstrate improvements in discrimination and calibration with respect to previous scores deployed in Scotland, as well as stability over a 3-year timeframe. Our analysis also provides insights about the epidemiology of EA risk in Scotland, by studying predictive performance across different population sub-groups and reasons for admission, as well as by quantifying the effect of individual input features. Finally, we discuss broader challenges including reproducibility and how to safely update risk prediction models that are already deployed at population level.

A novel daily runoff forecasting model based on global features and enhanced local feature interpretation

The development of artificial intelligence has introduced new perspectives to the field of hydrological forecasting. However, there is still a lack of research on efficiently identifying the physical characteristics of runoff sequences and developing prediction models that consider global and local sequence features. This study proposes a parallel computing prediction model called IMCAEN (Integrated Multi-Feature Causal Dilated Convolutional Attention Encoder Network) to address these issues. Unlike existing models, this model can monitor fluctuations and anomalies in time series. Incorporating the CDC-AA (Causal Dilated Convolutional Network with Aggregation Attention) and encoder structure captures both local sequence variations and global abrupt anomalies, allowing for comprehensive attention to sequence features. When predicting runoff data from three different hydrological conditions, the IMCAEN model achieved NSEC (Nash-Sutcliffe Efficiency Coefficient) values of 0.98, 0.97, and 0.88, respectively, and outperformed benchmark models in other evaluation indicators as well. Given the opacity of the feature distribution process in AI models, SHAP (SHapleyAdditive exPlanations) analysis and spatial expression of feature distribution are used to assess the contribution of each feature variable to the long-term trend of runoff and to verify the distribution of features trained in each module. The proposed IMCAEN model efficiently captures local and global information in the runoff evolution process through parallel computing and shared features, enabling accurate runoff forecasting and providing critical references for timely warnings and predictions.

Development and validation of a cardiovascular risk prediction model for Sri Lankans using machine learning.

Sri Lankans do not have a specific cardiovascular (CV) risk prediction model and therefore, World Health Organization(WHO) risk charts developed for the Southeast Asia Region are being used. We aimed to develop a CV risk prediction model specific for Sri Lankans using machine learning (ML) of data of a population-based, randomly selected cohort of Sri Lankans followed up for 10 years and to validate it in an external cohort. The cohort consisted of 2596 individuals between 40-65 years of age in 2007, who were followed up for 10 years. Of them, 179 developed hard CV diseases (CVD) by 2017. We developed three CV risk prediction models named model 1, 2 and 3 using ML. We compared predictive performances between models and the WHO risk charts using receiver operating characteristic curves (ROC). The most predictive and practical model for use in primary care, model 3 was named "SLCVD score" which used age, sex, smoking status, systolic blood pressure, history of diabetes, and total cholesterol level in the calculation. We developed an online platform to calculate the SLCVD score. Predictions of SLCVD score were validated in an external hospital-based cohort. Model 1, 2, SLCVD score and the WHO risk charts predicted 173, 162, 169 and 10 of 179 observed events and the area under the ROC (AUC) were 0.98, 0.98, 0.98 and 0.52 respectively. During external validation, the SLCVD score and WHO risk charts predicted 56 and 18 respectively of 119 total events and AUCs were 0.64 and 0.54 respectively. SLCVD score is the first and only CV risk prediction model specific for Sri Lankans. It predicts the 10-year risk of developing a hard CVD in Sri Lankans. SLCVD score was more effective in predicting Sri Lankans at high CV risk than WHO risk charts.

Predictive model development for premature infant extubation outcomes: development and analysis.

Given the knowledge of the damage caused by prolonged invasive mechanical ventilation in premature newborns, withdrawing this support as quickly as possible is important to minimize morbidity. The aim of this study was to analyze the variables associated with extubation outcomes and to develop a predictive model for successful extubation in premature newborns. Data were obtained from a multicenter study involving six public maternity hospitals. The variables with the highest correlation to the extubation outcome were used to construct the predictive model through data analysis and machine learning methods, followed by training and testing of algorithms. Data were collected from 405 premature newborns. The predictive model with the best metrics was trained and tested using the variables of gestational age, birth weight, weight at extubation, congenital infections, and time on invasive mechanical ventilation, based on 393 samples according to the extubation outcome (12 were discarded due to irretrievable missing data in important attributes). The model exhibited an accuracy of 77.78%, sensitivity of 79.41%, and specificity of 60%. These variables generated a predictive model capable of estimating the probability of successful extubation in premature newborns. Prolonged use of invasive mechanical ventilation in preterm newborns increases morbidity/mortality rates, emphasizing the importance of early withdrawal from invasive ventilatory support. However, the decision to extubate lacks tools with higher extubation outcome precision. The use of artificial intelligence through the construction of a predictive model can assist in the decision-making process for extubating preterm newborns based on real-world data. The implementation of this tool can optimize the decision to extubate preterm newborns, promoting successful extubation and reducing preterm newborns exposure to adverse events associated with extubation failure.

Development and construction of a cataract risk prediction model based on biochemical indices: the National Health and Nutrition Examination Survey, 2005-2008.

The aim of this study is to develop and validate a novel multivariable prediction model capable of accurately estimating the probability of cataract development, utilizing parameters such as blood biochemical markers and age. This population-based cross-sectional study comprised 9,566 participants drawn from the National Health and Nutrition Examination Survey (NHANES) across the 2005-2008 cycles. Demographic information and laboratory test results from the patients were collected and analyzed using LASSO regression and multivariate logistic regression to accurately capture the influence of biochemical indicators on the outcomes. The SHAP (Shapley Additive Explanations) scale was employed to assess the importance of each clinical feature, excluding age. A multivariate logistic regression model was then developed and visualized as a nomogram. To assess the model's performance, its discrimination, calibration, and clinical utility were evaluated using receiver operating characteristic (ROC) curves, 10-fold cross-validation, Hosmer-Lemeshow calibration curves, and decision curve analysis (DCA), respectively. Logistic regression analysis identified age, erythrocyte folate (nmol/L), blood glucose (mmol/L), and blood urea nitrogen (mmol/L) as independent risk factors for cataract, and these variables were incorporated into a multivariate logistic regression-based nomogram for cataract risk prediction. The area under the receiver operating characteristic (ROC) curve (AUC) for cataract risk prediction was 0.917 (95% CI: 0.9067-0.9273) in the training cohort, and 0.9148 (95% CI: 0.8979-0.9316) in the validation cohort. The Hosmer-Lemeshow calibration curve demonstrated a good fit, indicating strong model calibration. Ten-fold cross-validation confirmed the logistic regression model's robust predictive performance and stability during internal validation. Decision curve analysis (DCA) demonstrated that the nomogram prediction model provided greater clinical benefit for predicting cataract risk when the patient's threshold probability ranged from 0.10 to 0.90. This study identified blood urea nitrogen (mmol/L), serum glucose (mmol/L), and erythrocyte folate (mmol/L) as significant risk factors for cataract. A risk prediction model was developed, demonstrating strong predictive accuracy and clinical utility, offering clinicians a reliable tool for early and effective diagnosis. Cataract development may be delayed by reducing levels of blood urea nitrogen, serum glucose, and erythrocyte folate through lifestyle improvements and dietary modifications.

Clinical ocular prediction model of postoperative ametropic amblyopia in patients with congenital ectopia lentis.

Despite prompt and appropriate surgical management, a considerable proportion of patients with congenital ectopia lentis (CEL) suffer from postoperative ametropic amblyopia. To predict and identify at-risk patients early, and ensure timely amblyopia treatment, we conducted a thorough investigation into the onset and progression patterns of postoperative amblyopia in patients with CEL. Moreover, an ocular prediction model was constructed for amblyopia. In this prospective cohort study, amblyopia analysis was conducted to reveal the prevalence of postoperative amblyopia at different time points of follow-up. Comparative analysis and logistic regression analysis were performed for the development of an amblyopia prediction model. Receiver Operating Characteristic (ROC) analysis, calibration plots, and decision curve analysis (DCA) were used to evaluate the performance of the model. A nomogram was created to determine the probability of postoperative amblyopia. Amblyopia was diagnosed according to the most recent edition of the Amblyopia Preferred Practice Pattern. A total of 889 eyes from 677 patients operated for CEL were enrolled in this study. In the pediatric cohort, the prevalence of amblyopia showed a decreasing trend with follow-up time from 1 month to 3.5 years. A prediction model based on preoperative best-corrected visual acuity (BCVA) and cardiac phenotype was established to predict postoperative amblyopia. For effective individual prediction, a nomogram was created. With great calibration, discrimination, and clinical usefulness, the prediction model demonstrated good performance. The findings underscore that the prevalence of ametropic amblyopia in pediatric CEL patients who underwent lens surgery exhibited a marked decline over time. The prediction model established with preoperative BCVA and cardiac phenotype can provide accurate and individualized predictions of postoperative amblyopia, and it has the potential to assist ophthalmologists in rapidly identifying high-risk patients.

Predicting chlorophyll-a dynamics in the Ashtamudi estuary using ANN and ANFIS techniques

Excessive nutrients and associated high chlorophyll-a concentration are of growing concern to the public health due to the occurrence of eutrophication in aquatic bodies. Continuous monitoring of chlorophyll-a has limitations, thereby necessitating the development of prediction models. Even though chlorophyll-a prediction models are numerous, they rarely fit into estuarine conditions, which is encountered with dynamic mixing of freshwater and sea water. Thus, the present study identifies the most appropriate driving factors that are relevant for estuarine conditions through chlorophyll-a prediction models developed using Artificial Neural Network and Adaptive Neuro Fuzzy Inference System (ANFIS) approaches in the Ashtamudi estuary, India. Salinity, which is an indirect measure of the estuarine mixing intensity, has been used to replicate the dynamic mixing in the estuary. The results indicate that the model incorporating salinity along with total nitrogen, total phosphorous and turbidity well-predicted chlorophyll-a concentration with a coefficient of determination ranging from 0.73 to 0.99. General Regression Neural Network (GRNN) and ANFIS models outperformed Back Propagation Neural Network (BPNN) and Recurrent Neural Network (RNN) models. Of the various ANFIS models, the ones that used Gaussian and Generalized Bell membership functions were most appropriate for the prediction of chlorophyll-a than the models with triangular and trapezoidal membership functions. The study identified that the models that considered salinity were less sensitive and can be used for modelling chlorophyll-a. The chlorophyll-a was observed to have a direct influence of salinity at salinity values greater than 5‰. The study highlighted that estuarine mixing further enhances the primary productivity through increased penetration of light leading to higher chlorophyll-a concentration. Further the study emplasized that the predictive models are important tools fitting well within estuarine environments due to its replicability.

Soil liquefaction manifestations at Hatay Airport after the February 2023 Türkiye earthquake sequence

Hatay Airport was shaken by the Mw 7.8 and Mw 7.5 Pazarcık and Ekinözü-Elbistan Kahramanmaraş earthquake sequence on February 6, 2023. Two weeks after these events, Mw 6.3 Yayladağı-Hatay earthquake shook the site again. This paper presents the results of the reconnaissance assessment of soil liquefaction at the site, focusing on mostly three aspects: (a) the seismic response of the Hatay Airport, particularly the surface manifestations of seismic soil liquefaction in the form of soil ejecta; (b) the findings of site investigation studies performed before and after the seismic events, and (c) assessments for soil liquefaction susceptibility. Among the soil ejecta samples collected, three out of five are classified as clayey sand and fall within or near the boundary of the “further studies required” region on the susceptibility charts. The remaining two ejecta samples, composed of low and high-plasticity clay soils with PI values of 31 and 36% fall within the “not susceptible” region. The deviation from the current state of knowledge might be attributed to liquefaction-induced seepage eroding clayey soils to the ground surface or limitations in the current liquefaction susceptibility assessment methods for fine-grained soils, which may not accurately delineate the boundaries between susceptible and not-susceptible zones. Determining the most likely explanation requires additional site investigation studies, including CPT soundings, extending beyond the scope of this reconnaissance study. The documented case history and assessment results are expected to enhance the understanding of seismic soil liquefaction in fine-grained soils and contribute to the development of predictive models based on case histories for assessing liquefaction susceptibility and triggering.

Artificial intelligence applied to development of predictive stability model for intracranial aneurysms

BackgroundWe aimed to develop multiple machine learning models to predict the risk of early intracranial aneurysms (IAs) rupture, evaluate and compare the performance of predictive models.MethodsInformation related to patients diagnosed with IA by CT angiography and clinicians in Central hospital of Dalian University of Technology from January 2010 to June 2022 was collected, including clinical characteristics, blood indicators and IA morphological parameters. IA with rupture or maximum growth ≥ 0.5 mm within 1 month of first diagnosis was considered unstable. The relevant factors affecting IA stability were screened and predictive models were developed based on the above three levels, including random forest (RF), support vector machine (SVM), and artificial neural network (ANN). Sensitivity, specificity, accuracy and area under curve (AUC) value were used to evaluate the predictive models.ResultsA total of 989 IA patients were included in the study, including 561 stable patients and 428 unstable patients. For RF models, the training set showed that sensitivity, specificity, accuracy and the AUC values were 72.8–83.7%, 76.9–86.9%, 75.1–84.1% and 0.748 (0.719–0.778)–0.839 (0.814–0.864), respectively; after test set validation, the results were 71.9–78.8%, 75.0–84.0%, 73.6–81.1% and 0.734 (0.688–0.781)–0.809 (0.768–0.850), respectively. For SVM models, the training set were 66.0–80.2%, 76.5–85.5%, 71.7–82.3%, 0.712 (0.682–0.743)–0.913 (0.884–0.924), respectively; the test set were 44.2–78.3%, 63.4–84.4%, 57.9–80.9%, 0.699 (0.651–0.747)–0.806 (0.765–0.848), respectively. For ANN models, the training set were 66.8–83.0%, 75.3–82.3%, 71.6–82.1%, 0.783 (0.757–0.808)–0.897 (0.879–0.914); the test set were 63.1–76.3%, 65.5–84.0%, 64.4–80.6%, 0.680 (0.593–0.694)–0.860 (0.821–0.899). The results of variable importance showed that age, white blood cell count (WBC) and uric acid (UA) played an important role in predicting the stability of IA.ConclusionsThe predictive stability models of IA based on three artificial intelligence methods shows good clinical application. Age, WBC and UA played an important role in predicting the IA stability, and were potentially important predictors.

Nationwide study on development and validation of a risk prediction model for CIN3+ and cervical cancer in Estonia

Transitioning to an individualized risk-based approach can significantly enhance cervical cancer screening programs. We aimed to derive and internally validate a prediction model for assessing the risk of cervical intraepithelial neoplasia grade 3 or higher (CIN3+) and cancer in women eligible for screening. This retrospective study utilized data from the Estonian electronic health records, including 517,884 women from the health insurance database and linked health registries. We employed Cox proportional hazard regression, incorporating reproductive and medical history variables (14 covariates), and utilized the least absolute shrinkage and selection operator (LASSO) for variable selection. A 10-fold cross-validation for internal validation of the model was used. The main outcomes were the performance of discrimination and calibration. Over the 8-year follow-up, we identified 1326 women with cervical cancer and 5929 with CIN3+, with absolute risks of 0.3% and 1.1%, respectively. The prediction model for CIN3 + and cervical cancer had good discriminative power and was well calibrated Harrell’s C of 0.74 (0.73–0.74) (calibration slope 1.00 (0.97–1.02) and 0.67 (0.66–0.69) (calibration slope 0.92 (0.84–1.00) respectively. A developed model based on nationwide electronic health data showed potential utility for risk stratification to supplement screening efforts. This work was supported through grants number PRG2218 from the Estonian Research Council, and EMP416 from the EEA (European Economic Area) and Norway Grants.

Separating Risk Prediction: Myocardial Infarction vs. Ischemic Stroke in 6.2M Screenings.

Traditional cardiovascular disease risk prediction models generate a combined risk assessment for myocardial infarction (MI) and ischemic stroke (IS), which may inadequately reflect the distinct etiologies and disparate risk factors of MI and IS. We aim to develop prediction models that separately estimate the risks of MI and IS. Our analysis included 6,242,404 individuals over 40 years old who participated in a cardiovascular health screening examination in 2009. Potential predictors were selected based on a literature review and the available data. Cox proportional hazards models were used to construct 5-year risk prediction models for MI, and IS. Model performance was assessed through discrimination and calibration. During a follow-up of 39,322,434.39 person-years, 89,140 individuals were diagnosed with MI and 116,259 with IS. Both models included age, sex, body mass index, smoking, alcohol consumption, physical activity, diabetes, hypertension, dyslipidemia, chronic kidney disease, and family history. Statin use was factored into the classification of dyslipidemia. The c-indices for the prediction models were 0.709 (0.707-0.712) for MI, and 0.770 (0.768-0.772) for IS. Age and hypertension exhibited a more pronounced effect on IS risk prediction than MI, whereas smoking, body mass index, dyslipidemia, and chronic kidney disease showed the opposite effect. The models calibrated well for low-risk individuals. Our findings underscore the necessity of tailored risk assessments for MI and IS to facilitate the early detection and accurate identification of heterogeneous at-risk populations for atherosclerotic cardiovascular disease.

Iowa Brain-Behavior Modeling Toolkit: An Open-Source MATLAB Tool for Inferential and Predictive Modeling of Imaging-Behavior and Lesion-Deficit Relationships.

The traditional analytical framework taken by neuroimaging studies in general, and lesion-behavior studies in particular, has been inferential in nature and has focused on identifying and interpreting statistically significant effects within the sample under study. While this framework is well-suited for hypothesis testing approaches, achieving the modern goal of precision medicine requires a different framework that is predictive in nature and that focuses on maximizing the predictive power of models and evaluating their ability to generalize beyond the data that were used to train them. However, few tools exist to support the development and evaluation of predictive models in the context of neuroimaging or lesion-behavior research, creating an obstacle to the widespread adoption of predictive modeling approaches in the field. Further, existing tools for lesion-behavior analysis are often unable to accommodate categorical outcome variables and often impose restrictions on the predictor data. Researchers therefore often must use different software packages and analytical approaches depending on whether they are addressing a classification vs. regression problem and on whether their predictor data correspond to binary lesion images, continuous lesion-network images, connectivity matrices, or other data modalities. To address these limitations, we have developed a MATLAB software toolkit that supports both inferential and predictive modeling frameworks, accommodates both classification and regression problems, and does not impose restrictions on the modality of the predictor data. The toolkit features both a graphical user interface and scripting interface, includes implementations of multiple mass-univariate, multivariate, and machine learning models, features built-in and customizable routines for hyper-parameter optimization, cross-validation, model stacking, and significance testing, and automatically generates text-based descriptions of key methodological details and modeling results to improve reproducibility and minimize errors in the reporting of methods and results. Here, we provide an overview and discussion of the toolkit features and demonstrate its functionality by applying it to the question of how expressive and receptive language impairments relate to lesion location, structural disconnection, and functional network disruption in a large sample of patients with left hemispheric brain lesions. We find that impairments in expressive vs. receptive language are most strongly associated with left lateral prefrontal and left posterior temporal/parietal damage, respectively. We also find that impairments in expressive vs. receptive language are associated with partially overlapping patterns of fronto-temporal structural disconnection, and that the associated functional networks are also similar. Importantly, we find that lesion location and lesion-derived network measures are highly predictive of both types of impairment, with predictions from models trained on these measures explaining ~30-40% of the variance on average when applied to data from patients not used to train the models. We have made the toolkit publicly available, and we have included a comprehensive set of tutorial notebooks to support new users in applying the toolkit in their studies.