Final Prediction Model Research Articles

Development and validation of a simple and practical model for early detection of diabetic macular edema in patients with type 2 diabetes mellitus using easily accessible systemic variables

ObjectiveDiabetic macular edema (DME) is the leading cause of visual impairment in patients with diabetes mellitus (DM). The goal of early detection has not yet achieved due to a lack of fast and convenient methods. Therefore, we aim to develop and validate a prediction model to identify DME in patients with type 2 diabetes mellitus (T2DM) using easily accessible systemic variables, which can be applied to an ophthalmologist-independent scenario.MethodsIn this four-center, observational study, a total of 1994 T2DM patients who underwent routine diabetic retinopathy screening were enrolled, and their information on ophthalmic and systemic conditions was collected. Forward stepwise multivariable logistic regression was performed to identify risk factors of DME. Machine learning and MLR (multivariable logistic regression) were both used to establish prediction models. The prediction models were trained with 1300 patients and prospectively validated with 104 patients from Guangdong Provincial People’s Hospital (GDPH). A total of 175 patients from Zhujiang Hospital (ZJH), 115 patients from the First Affiliated Hospital of Kunming Medical University (FAHKMU), and 100 patients from People’s Hospital of JiangMen (PHJM) were used as external validation sets. Area under the receiver operating characteristic curve (AUC), accuracy (ACC), sensitivity, and specificity were used to evaluate the performance in DME prediction.ResultsThe risk of DME was significantly associated with duration of DM, diastolic blood pressure, hematocrit, glycosylated hemoglobin, and urine albumin-to-creatinine ratio stage. The MLR model using these five risk factors was selected as the final prediction model due to its better performance than the machine learning models using all variables. The AUC, ACC, sensitivity, and specificity were 0.80, 0.69, 0.80, and 0.67 in the internal validation, and 0.82, 0.54, 1.00, and 0.48 in prospective validation, respectively. In external validation, the AUC, ACC, sensitivity and specificity were 0.84, 0.68, 0.90 and 0.60 in ZJH, 0.89, 0.77, 1.00 and 0.72 in FAHKMU, and 0.80, 0.67, 0.75, and 0.65 in PHJM, respectively.ConclusionThe MLR model is a simple, rapid, and reliable tool for early detection of DME in individuals with T2DM without the needs of specialized ophthalmologic examinations.

Prediction of Amyloid Positivity in Patients with Subcortical Vascular Cognitive Impairment.

Amyloid-β (Aβ) commonly coexists and impacts prognosis in subcortical vascular cognitive impairment (SVCI). This study aimed to examine the differences in clinical and neuroimaging variables between Aβ-positive and Aβ-negative SVCI and to propose a prediction model for Aβ positivity in clinically diagnosed SVCI patients. A total of 130 patients with SVCI were included in model development, and a separate cohort of 70 SVCI patients was used in external validation. The variables for the prediction model were selected by comparing the characteristics of the Aβ-negative and Aβ-positive SVCI groups. The final model was determined using a stepwise method. The model performance was evaluated using the receiver operating characteristic (ROC) curve and a calibration curve. A nomogram was used for visualization. Among 130 SVCI patients, 70 (53.8%) were Aβ-positive. The Aβ-positive SVCI group was characterized by older age, tendency to be in the dementia stage, a higher prevalence of APOEɛ4, a lower prevalence of lacune, and more severe medial temporal atrophy (MTA). The final prediction model, which excluded MTA grade following the stepwise method for variable selection, demonstrated good accuracy in distinguishing between Aβ-positive and Aβ-negative SVCI, with an area under the curve (AUC) of 0.80. The external validation demonstrated an AUC of 0.71. The findings suggest that older age, dementia stage, APOEɛ4 carrier, and absence of lacunes may be predictive of Aβ positivity in clinically diagnosed SVCI patients.

Proof-of-concept for an automatable mortality prediction scoring in hospitalised older adults

IntroductionIt is challenging to prognosticate hospitalised older adults. Delayed recognition of end-of-life leads to failure in delivering appropriate palliative care and increases healthcare utilisation. Most mortality prediction tools specific for older adults require additional manual input, resulting in poor uptake. By leveraging on electronic health records, we aim to create an automatable mortality prediction tool for hospitalised older adults.MethodsWe retrospectively reviewed electronic records of general medicine patients ≥75 years at a tertiary hospital between April–September 2021. Demographics, comorbidities, ICD-codes, age-adjusted Charlson Comorbidity Index (CCI), Hospital Frailty Risk Score, mortality and resource utilization were collected. We defined early deaths, late deaths and survivors as patients who died within 30 days, 1 year, and lived beyond 1 year of admission, respectively. Multivariate logistic regression analyses were adjusted for age, gender, race, frailty, and CCI. The final prediction model was created using a stepwise logistic regression.ResultsOf 1,224 patients, 168 (13.7%) died early and 370 (30.2%) died late. From adjusted multivariate regression, risk of early death was significantly associated with ≥85 years, intermediate or high frail risk, CCI > 6, cardiovascular risk factors, AMI and pneumonia. For late death, risk factors included ≥85 years, intermediate frail risk, CCI >6, delirium, diabetes, AMI and pneumonia. Our mortality prediction tool which scores 1 point each for age, pneumonia and AMI had an AUC of 0.752 for early death and 0.691 for late death.ConclusionOur mortality prediction model is a proof-of-concept demonstrating the potential for automated medical alerts to guide physicians towards personalised care for hospitalised older adults.

Development and validation of a nomogram for predicting heterotopic ossification following spinal cord injury

ObjectiveHeterotopic ossification (HO) following spinal cord injury (SCI) can severely compromise patient mobility and quality of life. Precise identification of SCI patients at an elevated risk for HO is crucial for implementing early clinical interventions. While the literature presents diverse correlations between HO onset and purported risk factors, the development of a predictive model to quantify these risks is likely to bolster preventive approaches. This study is designed to develop and validate a nomogram-based predictive model that estimates the likelihood of HO in SCI patients, utilizing recognized risk factors to expedite clinical decision-making processes. MethodsWe recruited a total of 145 patients with SCI and presenting with HO who were hospitalized at the China Rehabilitation Research Center, Beijing Boai Hospital, from June 2016 to December 2022. Additionally, 337 patients with SCI without HO were included as controls. Comprehensive data were collected for all study participants, and subsequently, the dataset was randomly partitioned into training and validation groups. Using Least Absolute Shrinkage and Selection Operator regression, variables were meticulously screened during the pretreatment phase to formulate the predictive model. The efficacy of the model was then assessed using metrics including receiver-operating characteristic (ROC) analysis, calibration assessment, and decision curve analysis. ResultsThe final prediction model incorporated age, sex, complete spinal cord injury status, spasm occurrence, and presence of deep vein thrombosis (DVT). Notably, the model exhibited commendable performance in both the training and validation groups, as evidenced by areas under the ROC curve (AUCs) of 0.756 and 0.738, respectively. These values surpassed the AUCs obtained for single variables, namely age (0.636), sex (0.589), complete spinal cord injury (0.681), spasm occurrence (0.563), and DVT presence (0.590). Furthermore, the calibration curve illustrated a congruence between the predicted and actual outcomes, indicating the high accuracy of the model. The decision curve analysis indicated substantial net benefits associated with the application of the model, thereby underscoring its practical utility. ConclusionsHO following SCI correlates with several identifiable risk factors, including male gender, youthful age, complete SCI, spasm occurrence and DVT. Our predictive model effectively estimates the likelihood of HO development by leveraging these factors, assisting physicians in identifying patients at high risk. Subsequently, correct positioning to prevent spasm-related deformities and educating healthcare providers on safe lower limb mobilization techniques are crucial to minimize muscle injury risks from rapid iliopsoas muscle extension. Additionally, the importance of early DVT prevention through routine screening and anticoagulation is emphasized to further reduce the incidence of HO.

Upper limb muscle strength and exercise endurance as predictors of successful extubation in mechanically ventilated patients

BackgroundFailed extubation increases the intensive care unit (ICU) length of stay, hospital length of stay, and financial costs and it reduces the patient’s functional ability. Avoiding failed extubation is of utmost importance, therefore predictors for successful extubation are paramount.ObjectiveTo determine if successful extubation in mechanically ventilated patients can be predicted by physiotherapists using upper limb muscle strength and exercise endurance.MethodsFifty-seven patients from the medical and trauma ICUs of a large academic hospital were eligible for testing. Muscle strength was evaluated using the Oxford grading scale, Medical Research Council score (MRC score), handgrip dynamometer, and maximum inspiratory pressure (MIP). Exercise endurance was tested while the patient was actively riding the MOTOmed® letto2 cycle ergometer for six minutes with the upper limbs.ResultsExercise endurance (time the patient rode actively) (P = 0.005), MRC-score (P = 0.007), and number of days ventilated (P = 0.005) were associated with successful extubation. The handgrip strength (P = 0.061), MIP (P = 0.095), and muscle strength of the sternocleidomastoid (P = 0.053) and trapezius muscles (P = 0.075) were marginally associated with successful extubation. Due to multicollinearity when developing the prediction equation, the final multivariable logistic regression prediction model included only exercise endurance and the number of days ventilated. The newly developed prediction equation conferred a sensitivity of 81.82% and a specificity of 77.14% to predict successful extubation.ConclusionSuccessful extubation of mechanically ventilated patients can be predicted by physiotherapists using the newly developed prediction equation consisting of exercise endurance and number of days ventilated.

Prediction of Cognitive Impairment Risk among Older Adults: A Machine Learning-Based Comparative Study and Model Development

Introduction: The prevalence of cognitive impairment and dementia in the older population is increasing, and thereby, early detection of cognitive decline is essential for effective intervention. Methods: This study included 2,288 participants with normal cognitive function from the Ma’anshan Healthy Aging Cohort Study. Forty-two potential predictors, including demographic characteristics, chronic diseases, lifestyle factors, anthropometric indices, physical function, and baseline cognitive function, were selected based on clinical importance and previous research. The dataset was partitioned into training, validation, and test sets in a proportion of 60% for training, 20% for validation, and 20% for testing, respectively. Recursive feature elimination was used for feature selection, followed by six machine learning algorithms that were employed for model development. The performance of the models was evaluated using area under the curve (AUC), specificity, sensitivity, and accuracy. Moreover, SHapley Additive exPlanations (SHAP) was conducted to access the interpretability of the final selected model and to gain insights into the impact of features on the prediction outcomes. SHAP force plots were established to vividly show the application of the prediction model at the individual level. Results: The final predictive model based on the Naive Bayes algorithm achieved an AUC of 0.820 (95% CI, 0.773–0.887) on the test set, outperforming other algorithms. The top ten influential features in the model included baseline Mini-Mental State Examination (MMSE), education, self-reported economic status, collective or social activities, Pittsburgh sleep quality index (PSQI), body mass index, systolic blood pressure, diastolic blood pressure, instrumental activities of daily living, and age. The model demonstrated the potential to identify individuals at a higher risk of cognitive impairment within 3 years from older adults. Conclusion: The predictive model developed in this study contributes to the early detection of cognitive impairment in older adults by primary healthcare staff in community settings.

Computational prediction of phosphorylation sites of SARS-CoV-2 infection using feature fusion and optimization strategies

SARS-CoV-2′s global spread has instigated a critical health and economic emergency, impacting countless individuals. Understanding the virus's phosphorylation sites is vital to unravel the molecular intricacies of the infection and subsequent changes in host cellular processes. Several computational methods have been proposed to identify phosphorylation sites, typically focusing on specific residue (S/T) or Y phosphorylation sites. Unfortunately, current predictive tools perform best on these specific residues and may not extend their efficacy to other residues, emphasizing the urgent need for enhanced methodologies. In this study, we developed a novel predictor that integrated all the residues (STY) phosphorylation sites information. We extracted ten different feature descriptors, primarily derived from composition, evolutionary, and position-specific information, and assessed their discriminative power through five classifiers. Our results indicated that Light Gradient Boosting (LGB) showed superior performance, and five descriptors displayed excellent discriminative capabilities. Subsequently, we identified the top two integrated features have high discriminative capability and trained with LGB to develop the final prediction model, LGB-IPs. The proposed approach shows an excellent performance on 10-fold cross-validation with an ACC, MCC, and AUC values of 0.831, 0.662, 0.907, respectively. Notably, these performances are replicated in the independent evaluation. Consequently, our approach may provide valuable insights into the phosphorylation mechanisms in SARS-CoV-2 infection for biomedical researchers.

New models for prediction of postoperative pulmonary complications in lung resection candidates.

In recent years, ventilatory efficiency (minute ventilation (V'E)/carbon dioxide production (V'CO2 ) slope) and partial pressure of end-tidal carbon dioxide (P ETCO2 ) have emerged as independent predictors of postoperative pulmonary complications (PPC). Single parameters may give only partial information regarding periprocedural hazards. Accordingly, our aim was to create prediction models with improved ability to stratify PPC risk in patients scheduled for elective lung resection surgery. This post hoc analysis was comprised of consecutive lung resection candidates from two prior prospective trials. All individuals completed pulmonary function tests and cardiopulmonary exercise testing (CPET). Logistic regression analyses were used for identification of risk factors for PPC that were entered into the final risk prediction models. Two risk models were developed; the first used rest P ETCO2 (for patients with no available CPET data), the second used V'E/ V'CO2 slope (for patients with available CPET data). Receiver operating characteristic analysis with the De-Long test and area under the curve (AUC) were used for comparison of models. The dataset from 423 patients was randomly split into the derivation (n=310) and validation (n=113) cohorts. Two final models were developed, both including sex, thoracotomy, "atypical" resection and forced expiratory volume in 1 s/forced vital capacity ratio as risk factors. In addition, the first model also included rest P ETCO2 , while the second model used V'E/V'CO2 slope from CPET. AUCs of risk scores were 0.795 (95% CI: 0.739-0.851) and 0.793 (95% CI: 0.737-0.849); both p<0.001. No differences in AUCs were found between the derivation and validation cohorts. We created two multicomponental models for PPC risk prediction, both having excellent predictive properties.

Predicting air quality index using attention hybrid deep learning and quantum-inspired particle swarm optimization

Air pollution poses a significant threat to the health of the environment and human well-being. The air quality index (AQI) is an important measure of air pollution that describes the degree of air pollution and its impact on health. Therefore, accurate and reliable prediction of the AQI is critical but challenging due to the non-linearity and stochastic nature of air particles. This research aims to propose an AQI prediction hybrid deep learning model based on the Attention Convolutional Neural Networks (ACNN), Autoregressive Integrated Moving Average (ARIMA), Quantum Particle Swarm Optimization (QPSO)-enhanced-Long Short-Term Memory (LSTM) and XGBoost modelling techniques. Daily air quality data were collected from the official Seoul Air registry for the period 2021 to 2022. The data were first preprocessed through the ARIMA model to capture and fit the linear part of the data and followed by a hybrid deep learning architecture developed in the pretraining–finetuning framework for the non-linear part of the data. This hybrid model first used convolution to extract the deep features of the original air quality data, and then used the QPSO to optimize the hyperparameter for LSTM network for mining the long-terms time series features, and the XGBoost model was adopted to fine-tune the final AQI prediction model. The robustness and reliability of the resulting model were assessed and compared with other widely used models and across meteorological stations. Our proposed model achieves up to 31.13% reduction in MSE, 19.03% reduction in MAE and 2% improvement in R-squared compared to the best appropriate conventional model, indicating a much stronger magnitude of relationships between predicted and actual values. The overall results show that the attentive hybrid deep Quantum inspired Particle Swarm Optimization model is more feasible and efficient in predicting air quality index at both city-wide and station-specific levels.

Optimization and Application of XGBoost Logging Prediction Model for Porosity and Permeability Based on K-means Method

The prediction and distribution of reservoir porosity and permeability are of paramount importance for the exploration and development of regional oil and gas resources. In order to optimize the prediction methods of porosity and permeability and better guide gas field development, it is necessary to identify the most effective approaches. Therefore, based on the extreme gradient boosting (XGBoost) algorithm, laboratory test data of the porosity and permeability of cores from the southern margin of the Ordos Basin were selected as the target labels, conventional logging curves were used as the input feature variables, and the mean absolute error (MAE) and the coefficient of determination (R2) were used as the evaluation indicators. Following the selection of the optimal feature variables and optimization of the hyper-parameters, an XGBoost porosity and permeability prediction model was established. Subsequently, the innovative application of homogeneous clustering (K-means) data preprocessing was applied to enhance the XGBoost model’s performance. The results show that logarithmically preprocessed (LOG(PERM)) target labels enhanced the performance of the XGBoost permeability prediction model, with an increase of 0.26 in its test set R2. Furthermore, the application of K-means improved the performance of the XGBoost prediction model, with an increase of 0.15 in the R2 of the model and a decrease of 0.017 in the MAE. Finally, the POR_0/POR_1 grouped porosity model was selected as the final predictive model for porosity in the study area, and the Arctan(PERM)_0/Arctan(PER0M)_1 grouped model was selected as the final predictive model for permeability, which has better prediction accuracy than logging curves. The combination of K-means and the XGBoost modeling method provides a new approach and reference for the efficient and relatively accurate evaluation of porosity and permeability in the study area.

Establishment and evaluation of a prognostic model for patients with unresectable gastric cancer liver metastases.

Liver metastases (LM) is the primary factor contributing to unfavorable outcomes in patients diagnosed with gastric cancer (GC). The objective of this study is to analyze significant prognostic risk factors for patients with GCLM and develop a reliable nomogram model that can accurately predict individualized prognosis, thereby enhancing the ability to evaluate patient outcomes. To analyze prognostic risk factors for GCLM and develop a reliable nomogram model to accurately predict individualized prognosis, thereby enhancing patient outcome assessment. Retrospective analysis was conducted on clinical data pertaining to GCLM (type III), admitted to the Department of General Surgery across multiple centers of the Chinese PLA General Hospital from January 2010 to January 2018. The dataset was divided into a development cohort and validation cohort in a ratio of 2:1. In the development cohort, we utilized univariate and multivariate Cox regression analyses to identify independent risk factors associated with overall survival in GCLM patients. Subsequently, we established a prediction model based on these findings and evaluated its performance using receiver operator characteristic curve analysis, calibration curves, and clinical decision curves. A nomogram was created to visually represent the prediction model, which was then externally validated using the validation cohort. A total of 372 patients were included in this study, comprising 248 individuals in the development cohort and 124 individuals in the validation cohort. Based on Cox analysis results, our final prediction model incorporated five independent risk factors including albumin levels, primary tumor size, presence of extrahepatic metastases, surgical treatment status, and chemotherapy administration. The 1-, 3-, and 5-years Area Under the Curve values in the development cohort are 0.753, 0.859, and 0.909, respectively; whereas in the validation cohort, they are observed to be 0.772, 0.848, and 0.923. Furthermore, the calibration curves demonstrated excellent consistency between observed values and actual values. Finally, the decision curve analysis curve indicated substantial net clinical benefit. Our study identified significant prognostic risk factors for GCLM and developed a reliable nomogram model, demonstrating promising predictive accuracy and potential clinical benefit in evaluating patient outcomes.

Research on optimization of basic rail top bending prediction model

Since the basic rail of the switch needs to have a certain bending angle when the train changes direction, top bending is an important link in the production process of the basic rail. The three-point pressure top bending method is simple, flexible and widely used. In this study, the traditional three-point pressure bending is optimized, the influence of the pick width in the model is considered, a corresponding rebound model is established, and the model is applied to the pressure bending process of the basic rail. The bilinear strengthening model of the material was used to construct the bending moment expressions at different positions during the top bending process, and the relationship between the load and bending deflection in the elastic stage and elastic-plastic stage was obtained. The final top bending prediction model was obtained by combining the load-deflection model in the bending stage and the rebound stage. The correctness of the theoretical mathematical model was verified by establishing finite element simulations, and the theoretical calculation results were compared with the experimental results. The results showed that the top bend prediction optimization model established in this study had high feasibility and met the machining accuracy requirements.

The Postoperative Airway Compromise Score—First Steps to Developing a Postoperative Tool for the Assessment of Upper Airway-Related Complications Following Anterior Cervical Spine Surgery

BackgroundAcute upper airway compromise is a rare but catastrophic complication after anterior cervical discectomy and fusion (ACDF). This study aims to develop a score to identify patients at risk for acute postoperative airway compromise (PAC). MethodsPotential risk factors for acute PAC were selected by a modified Delphi process. Ten patients with acute PAC were identified out of 1,466 patients who underwent elective ACDF between July 2014 - May 2019. A comparison group was created by a randomized selection process (non-PAC group). Associated factors with PAC and a p-value <.10 were entered into a logistic regression model and coefficients contributed each risk factor's overall score. Calibration of the model was evaluated by Hosmer-Lemeshow (H-L) goodness-of-fit test. Quantitative discrimination was calculated and the final model was internally validated with bootstrap sampling. ResultsWe identified 18 potential risk factors from our Delphi process, of which 6 factors demonstrated a significant association with airway compromise: age >65 years, current smoking status, ASA >2, history of a bleeding disorder, surgery of upper subaxial cervical spine (>C4), and duration of surgery >179 min. The final prediction model included five predictors with very strong performance characteristics. These five factors formed the PAC-Score (PACS) which had a range from 0 to 100. A score of 20 yielded the greatest balance of sensitivity (80%) and specificity (88%). ConclusionsThe acute Postoperative Airway Compromise Score (PACS) demonstrates strong performance characteristics. The PAC score may help identify patients at risk for upper airway compromise caused by surgical site abnormalities.

Car Price Prediction Using Regression Techniques of Machine Learning

A car price prediction has been a high-interest research area, as it requires noticeable effort and knowledge of the field expert. Considerable number of distinct attributes are examined for the reliable and accurate prediction. To build a model for predicting the price of used cars in Bosnia and Herzegovina, we applied three machine learning techniques (Artificial Neural Network, Support Vector Machine and Random Forest). However, the mentioned techniques were applied to work as an ensemble. The data used for the prediction was collected from the web portal autopijaca.ba using web scraper that was written in PHP programming language. Respective performances of different algorithms were then compared to find one that best suits the available data set. The final prediction model was integrated into Java application. Furthermore, the model was evaluated using test data and the accuracy of 91% was obtained.

A predictive model for patent ductus arteriosus seven days postpartum in preterm infants: an ultrasound-based assessment of ductus arteriosus intimal thickness within 24 h after birth.

To develop a predictive model for patent ductus arteriosus (PDA) in preterm infants at seven days postpartum. The model employs ultrasound measurements of the ductus arteriosus (DA) intimal thickness (IT) obtained within 24 h after birth. One hundred and five preterm infants with gestational ages ranging from 27.0 to 36.7 weeks admitted within 24 h following birth were prospectively enrolled. Echocardiographic assessments were performed to measure DA IT within 24 h after birth, and DA status was evaluated through echocardiography on the seventh day postpartum. Potential predictors were considered, including traditional clinical risk factors, M-mode ultrasound parameters, lumen diameter of the DA (LD), and DA flow metrics. A final prediction model was formulated through bidirectional stepwise regression analysis and subsequently subjected to internal validation. The model's discriminative ability, calibration, and clinical applicability were also assessed. The final predictive model included birth weight, application of mechanical ventilation, left ventricular end-diastolic diameter (LVEDd), LD, and the logarithm of IT (logIT). The receiver operating characteristic (ROC) curve for the model, predicated on logIT, exhibited excellent discriminative power with an area under the curve (AUC) of 0.985 (95% CI: 0.966-1.000), sensitivity of 1.000, and specificity of 0.909. Moreover, the model demonstrated robust calibration and goodness-of-fit (χ2 value = 0.560, p > 0.05), as well as strong reproducibility (accuracy: 0.935, Kappa: 0.773), as evidenced by 10-fold cross-validation. A decision curve analysis confirmed the model's broad clinical utility. Our study successfully establishes a predictive model for PDA in preterm infants at seven days postpartum, leveraging the measurement of DA IT. This model enables identifying, within the first 24 h of life, infants who are likely to benefit from timely DA closure, thereby informing treatment decisions.

Ac4C-AFL: A high-precision identification of human mRNA N4-acetylcytidine sites based on adaptive feature representation learning

RNA N4-acetylcytidine (ac4C) is a highly conserved RNA modification that plays a crucial role in controlling mRNA stability, processing, and translation. Consequently, accurate identification of ac4C sites across the genome is critical for understanding gene expression regulation mechanisms. In this study, we have developed ac4C-AFL, a bioinformatics tool that precisely identifies ac4C sites from primary RNA sequences. In ac4C-AFL, we identified the optimal sequence length for model building and implemented an adaptive feature representation strategy that is capable of extracting the most representative features from RNA. To identify the most relevant features, we proposed a novel ensemble feature importance scoring strategy to rank features effectively. We then used this information to conduct the sequential forward search, which individually determine the optimal feature set from the 16 sequence-derived feature descriptors. Utilizing these optimal feature descriptors, we constructed 176 baseline models using 11 popular classifiers. The most efficient baseline models were identified using the two-step feature selection approach, whose predicted scores were integrated and trained with the appropriate classifier to develop the final prediction model. Our rigorous cross-validations and independent tests demonstrate that ac4C-AFL surpasses contemporary tools in predicting ac4C sites. Moreover, we have developed a publicly accessible web server at https://balalab-skku.org/ac4C-AFL/.

Variability in the prevalence of depression among adults with chronic pain: UK Biobank analysis through clinical prediction models

BackgroundThe prevalence of depression among people with chronic pain remains unclear due to the heterogeneity of study samples and definitions of depression. We aimed to identify sources of variation in the prevalence of depression among people with chronic pain and generate clinical prediction models to estimate the probability of depression among individuals with chronic pain.MethodsParticipants were from the UK Biobank. The primary outcome was a “lifetime” history of depression. The model’s performance was evaluated using discrimination (optimism-corrected C statistic) and calibration (calibration plot).ResultsAnalyses included 24,405 patients with chronic pain (mean age 64.1 years). Among participants with chronic widespread pain, the prevalence of having a “lifetime” history of depression was 45.7% and varied (25.0–66.7%) depending on patient characteristics. The final clinical prediction model (optimism-corrected C statistic: 0.66; good calibration on the calibration plot) included age, BMI, smoking status, physical activity, socioeconomic status, gender, history of asthma, history of heart failure, and history of peripheral artery disease. Among participants with chronic regional pain, the prevalence of having a “lifetime” history of depression was 30.2% and varied (21.4–70.6%) depending on patient characteristics. The final clinical prediction model (optimism-corrected C statistic: 0.65; good calibration on the calibration plot) included age, gender, nature of pain, smoking status, regular opioid use, history of asthma, pain location that bothers you most, and BMI.ConclusionsThere was substantial variability in the prevalence of depression among patients with chronic pain. Clinically relevant factors were selected to develop prediction models. Clinicians can use these models to assess patients’ treatment needs. These predictors are convenient to collect during daily practice, making it easy for busy clinicians to use them.

Managing motivations and satisfaction in Dark Immersive Theatre Experiences

Dark Immersive Theatre Experiences (DITE) have been growing in popularity in recent years as an innovative product that combines darkness with immersive theatre, attracting individuals all over the world who seek new and enticing experiences. This study aims to develop predictive models of participant satisfaction in DITE based on their underlying motivations. Based on Principal Component Analysis, we were able to identify five motivational components: "dark intensity", "survival", "immersion”, "theatre", and "unwinding", which explained 66.7% of the motivation’s variation. Furthermore, we performed multiple linear regression models to predict participants’ overall satisfaction in DITE. The final predictive models allowed to explain 66.0% of satisfaction’s variance, composed by six independent variables: "novel experience", "captivating plot", "push limits", "to have fun", "coparticipation", and "hyper-realistic experience". Our work contributes for optimizing DITE by presenting specific factors that allow to enhance satisfaction. Our data provide DITE managers useful information to improve and optimize experiences in such a way that enhances participant’s satisfaction and further increase their interest to such experiences.

A Prediction Model for Successful Increase of Adalimumab Dose Intervals in Patients with Crohn’s Disease: Secondary Analysis of the Pragmatic Open-Label Randomised Controlled Non-inferiority LADI Trial

BackgroundIn the pragmatic open-label randomised controlled non-inferiority LADI trial we showed that increasing adalimumab (ADA) dose intervals was non-inferior to conventional dosing for persistent flares in patients with Crohn’s disease (CD) in clinical and biochemical remission.AimsTo develop a prediction model to identify patients who can successfully increase their ADA dose interval based on secondary analysis of trial data.MethodsPatients in the intervention group of the LADI trial increased ADA intervals to 3 and then to 4 weeks. The dose interval increase was defined as successful when patients had no persistent flare (> 8 weeks), no intervention-related severe adverse events, no rescue medication use during the study, and were on an increased dose interval while in clinical and biochemical remission at week 48. Prediction models were based on logistic regression with relaxed LASSO. Models were internally validated using bootstrap optimism correction.ResultsWe included 109 patients, of which 60.6% successfully increased their dose interval. Patients that were active smokers (odds ratio [OR] 0.90), had previous CD-related intra-abdominal surgeries (OR 0.85), proximal small bowel disease (OR 0.92), an increased Harvey-Bradshaw Index (OR 0.99) or increased faecal calprotectin (OR 0.997) were less likely to successfully increase their dose interval. The model had fair discriminative ability (AUC = 0.63) and net benefit analysis showed that the model could be used to select patients who could increase their dose interval.ConclusionThe final prediction model seems promising to select patients who could successfully increase their ADA dose interval. The model should be validated externally before it may be applied in clinical practice.Clinical Trial Registration NumberClinicalTrials.gov, number NCT03172377.

Stack-AAgP: Computational prediction and interpretation of anti-angiogenic peptides using a meta-learning framework

Background:Angiogenesis plays a vital role in the pathogenesis of several human diseases, particularly in the case of solid tumors. In the realm of cancer treatment, recent investigations into peptides with anti-angiogenic properties have yielded encouraging outcomes, thereby creating a hopeful therapeutic avenue for the treatment of cancer. Therefore, correctly identifying the anti-angiogenic peptides is extremely important in comprehending their biophysical and biochemical traits, laying the groundwork for uncovering novel drugs to combat cancer. Methods:In this work, we present a novel ensemble-learning-based model, Stack-AAgP, specifically designed for the accurate identification and interpretation of anti-angiogenic peptides (AAPs). Initially, a feature representation approach is employed, generating 24 baseline models through six machine learning algorithms (random forest [RF], extra tree classifier [ETC], extreme gradient boosting [XGB], light gradient boosting machine [LGBM], CatBoost, and SVM) and four feature encodings (pseudo-amino acid composition [PAAC], amphiphilic pseudo-amino acid composition [APAAC], composition of k-spaced amino acid pairs [CKSAAP], and quasi-sequence-order [QSOrder]). Subsequently, the output (predicted probabilities) from 24 baseline models was inputted into the same six machine-learning classifiers to generate their respective meta-classifiers. Finally, the meta-classifiers were stacked together using the ensemble-learning framework to construct the final predictive model. Results:Findings from the independent test demonstrate that Stack-AAgP outperforms the state-of-the-art methods by a considerable margin. Systematic experiments were conducted to assess the influence of hyperparameters on the proposed model. Our model, Stack-AAgP, was evaluated on the independent NT15 dataset, revealing superiority over existing predictors with an accuracy improvement ranging from 5% to 7.5% and an increase in Matthews Correlation Coefficient (MCC) from 7.2% to 12.2%.