dynr.mi: An R Program for Multiple Imputation in Dynamic Modeling

Machine learning for risk prediction of acute kidney injury in patients with diabetes mellitus combined with heart failure during hospitalization

This study aimed to develop a machine learning (ML) model for predicting the risk of acute kidney injury (AKI) in diabetic patients with heart failure (HF) during hospitalization. Using data from 1,457 patients in the MIMIC-IV database, the study identified twenty independent risk factors for AKI through LASSO regression and logistic regression. Six ML algorithms were evaluated, including LightGBM, random forest, and neural networks. The LightGBM model demonstrated superior performance with the highest prediction accuracy, with AUC values of 0.973 and 0.804 in the training and validation sets, respectively. The Shapley additive explanations algorithm was used to visualize the model and identify the most relevant features for AKI risk. Clinical impact curves further confirmed the strong discriminatory ability and generalizability of the LightGBM model. This study highlights the potential of ML models, particularly LightGBM, to effectively predict AKI risk in diabetic patients with HF, enabling early identification of high-risk patients and timely interventions to improve prognosis.

Healthy Mom Zone Adaptive Intervention With a Novel Control System and Digital Platform to Manage Gestational Weight Gain in Pregnant Women With Overweight or Obesity: Study Design and Protocol for a Randomized Controlled Trial

BACKGROUND

Regulating gestational weight gain (GWG) in pregnant women with overweight or obesity is difficult, particularly because of the narrow range of recommended GWG for optimal health outcomes. Given that many pregnant women show excessive GWG and considering the lack of a "gold standard" intervention to manage GWG, there is a timely need for effective and efficient approaches to regulate GWG. We have enhanced the Healthy Mom Zone (HMZ) 2.0 intervention with a novel digital platform, automated dosage changes, and personalized strategies to regulate GWG, and our pilot study demonstrated successful recruitment, compliance, and utility of our new control system and digital platform.

OBJECTIVE

The goal of this paper is to describe the study protocol for a randomized controlled optimization trial to examine the efficacy of the enhanced HMZ 2.0 intervention with the new automated control system and digital platform to regulate GWG and influence secondary maternal and infant outcomes while collecting implementation data to inform future scalability.

METHODS

This is an efficacy study using a randomized controlled trial design. HMZ 2.0 is a multidosage, theoretically based, and individually tailored adaptive intervention that is delivered through a novel digital platform with an automated link of participant data to a new model-based predictive control algorithm to predict GWG. Our new control system computes individual dosage changes and produces personalized physical activity (PA) and energy intake (EI) strategies to deliver just-in-time dosage change recommendations to regulate GWG. Participants are 144 pregnant women with overweight or obesity randomized to an intervention (n=72) or attention control (n=72) group, stratified by prepregnancy BMI (<29.9 vs ≥30 kg/m2), and they will participate from approximately 8 to 36 weeks of gestation. The sample size is based on GWG (primary outcome) and informed by our feasibility trial showing a 21% reduction in GWG in the intervention group compared to the control group, with 3% dropout. Secondary outcomes include PA, EI, sedentary and sleep behaviors, social cognitive determinants, adverse pregnancy and delivery outcomes, infant birth weight, and implementation outcomes. Analyses will include descriptive statistics, time series and fixed effects meta-analytic approaches, and mixed effects models.

RESULTS

Recruitment started in April 2024, and enrollment will continue through May 2027. The primary (GWG) and secondary (eg, maternal and infant health) outcome results will be analyzed, posted on ClinicalTrials.gov, and published after January 2028.

CONCLUSIONS

Examining the efficacy of the novel HMZ 2.0 intervention in terms of GWG and secondary outcomes expands the boundaries of current GWG interventions and has high clinical and public health impact. There is excellent potential to further refine HMZ 2.0 to scale-up use of the novel digital platform by clinicians as an adjunct treatment in prenatal care to regulate GWG in all pregnant women.

INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID)

DERR1-10.2196/66637.

Arthritis increases the risk of erectile dysfunction: Results from the NHANES 2001-2004

Objective

This study assessed the association between erectile dysfunction (ED) and arthritis.

Methods

Weighted logistic regression and subgroup analyses were used to investigate the association between arthritis incidence and ED among participants in the 2001-2004 National Health and Nutrition Examination Survey database.

Results

Among the participants, 27.8% and 18.5% had a self-reported history of ED and arthritis, respectively. ED was associated with arthritis (odds ratio [OR]=4.00; 95% confidence interval [CI]: 3.20-4.99; p<0.001], which remained significant after adjustment (OR=1.42, 95% CI: 1.00-1.96; p<0.001). Stratified by type of arthritis, after full adjustment, osteoarthritis remained significant (OR=1.11; 95% CI: 1.03-1.20; p=0.017), and rheumatoid arthritis (OR=1.03, 95% CI: 0.93-1.13; p= 0.5) and other arthritis (OR=1.04, 95% CI: 0.98-1.11; p=0.2) were not significantly correlated with ED. Multiple inference analyses confirmed the robustness of the results.

Conclusion

Our study showed that arthritis was strongly associated with ED. There is an urgent need to raise awareness and conduct additional research on the reasons behind this association in order to implement more scientific and rational treatment programs for patients with ED and arthritis.

Multiple imputation of missing data in multilevel ecological momentary assessments: an example using smoking cessation study data

Advances in digital technology have greatly increased the ease of collecting intensive longitudinal data (ILD) such as ecological momentary assessments (EMAs) in studies of behavior changes. Such data are typically multilevel (e.g., with repeated measures nested within individuals), and are inevitably characterized by some degrees of missingness. Previous studies have validated the utility of multiple imputation as a way to handle missing observations in ILD when the imputation model is properly specified to reflect time dependencies. In this study, we illustrate the importance of proper accommodation of multilevel ILD structures in performing multiple imputations, and compare the performance of a multilevel multiple imputation (multilevel MI) approach relative to other approaches that do not account for such structures in a Monte Carlo simulation study. Empirical EMA data from a tobacco cessation study are used to demonstrate the utility of the multilevel MI approach, and the implications of separating participant- and study-initiated EMAs in evaluating individuals' affective dynamics and urge.

Different Machine Learning Approaches for Implementing Telehealth-Based Cancer Pain Management Strategies

Background: The most effective strategy for managing cancer pain remotely should be better defined. There is a need to identify those patients who require increased attention and calibrated follow-up programs. Methods: Machine learning (ML) models were developed using the data prospectively obtained from a single-center program of telemedicine-based cancer pain management. These models included random forest (RF), gradient boosting machine (GBM), artificial neural network (ANN), and the LASSO−RIDGE algorithm. Thirteen demographic, social, clinical, and therapeutic variables were adopted to define the conditions that can affect the number of teleconsultations. After ML validation, the risk analysis for more than one remote consultation was assessed in target individuals. Results: The data from 158 patients were collected. In the training set, the accuracy was about 95% and 98% for ANN and RF, respectively. Nevertheless, the best accuracy on the test set was obtained with RF (70%). The ML-based simulations showed that young age (<55 years), lung cancer, and occurrence of breakthrough cancer pain help to predict the number of remote consultations. Elderly patients (>75 years) with bone metastases may require more telemedicine-based clinical evaluations. Conclusion: ML-based analyses may enable clinicians to identify the best model for predicting the need for more remote consultations. It could be useful for calibrating care interventions and resource allocation.

Bayesian Forecasting with a Regime-Switching Zero-Inflated Multilevel Poisson Regression Model: An Application to Adolescent Alcohol Use with Spatial Covariates

In this paper, we present and evaluate a novel Bayesian regime-switching zero-inflated multilevel Poisson (RS-ZIMLP) regression model for forecasting alcohol use dynamics. The model partitions individuals' data into two phases, known as regimes, with: (1) a zero-inflation regime that is used to accommodate high instances of zeros (non-drinking) and (2) a multilevel Poisson regression regime in which variations in individuals' log-transformed average rates of alcohol use are captured by means of an autoregressive process with exogenous predictors and a person-specific intercept. The times at which individuals are in each regime are unknown, but may be estimated from the data. We assume that the regime indicator follows a first-order Markov process as related to exogenous predictors of interest. The forecast performance of the proposed model was evaluated using a Monte Carlo simulation study and further demonstrated using substance use and spatial covariate data from the Colorado Online Twin Study (CoTwins). Results showed that the proposed model yielded better forecast performance compared to a baseline model which predicted all cases as non-drinking and a reduced ZIMLP model without the RS structure, as indicated by higher AUC (the area under the receiver operating characteristic (ROC) curve) scores, and lower mean absolute errors (MAEs) and root-mean-square errors (RMSEs). The improvements in forecast performance were even more pronounced when we limited the comparisons to participants who showed at least one instance of transition to drinking.

Fitting Multilevel Vector Autoregressive Models in Stan, JAGS, and Mplus

The influx of intensive longitudinal data creates a pressing need for complex modeling tools that help enrich our understanding of how individuals change over time. Multilevel vector autoregressive (mlVAR) models allow for simultaneous evaluations of reciprocal linkages between dynamic processes and individual differences, and have gained increased recognition in recent years. High-dimensional and other complex variations of mlVAR models, though often computationally intractable in the frequentist framework, can be readily handled using Markov chain Monte Carlo techniques in a Bayesian framework. However, researchers in social science fields may be unfamiliar with ways to capitalize on recent developments in Bayesian software programs. In this paper, we provide step-by-step illustrations and comparisons of options to fit Bayesian mlVAR models using Stan, JAGS and Mplus, supplemented with a Monte Carlo simulation study. An empirical example is used to demonstrate the utility of mlVAR models in studying intra- and inter-individual variations in affective dynamics.

Daily associations among craving, affect, and social interactions in the lives of patients during residential opioid use disorder treatment

OBJECTIVE

This study captured the interrelationships among craving, negative affect, and positive and negative social exchanges in the daily lives of patients in residential treatment for opioid use disorders (OUDs).

METHOD

Participants were 73 patients (77% male), age 19 to 61 (Mage = 30.10, SDage = 10.13) in residential treatment for OUD. Participants completed a smartphone-based survey 4 times per day for 12 consecutive days that measured positive and negative social exchanges (Test of Negative Social Exchange), negative affect (PA-NA scales), and craving (frequency and intensity). Within-person, day-level associations among daily positive and negative social exchanges, negative affect, and craving were examined using multilevel modeling.

RESULTS

Daily negative social exchanges (M = 1.44, SD = 2.27) were much less frequent than positive social exchanges (M = 6.59, SD = 4.00) during residential treatment. Whereas negative social exchanges had a direct association with same-day craving (β = 0.08; 95% CI = 0.01, 0.16, ΔR2 = 0.01), positive social exchanges related to craving indirectly via moderation of the within-person negative affect-craving link (β = -0.01; 95% CI = -0.01, -0.001, ΔR2 = 0.002). Positive social exchanges decoupled the same-day linkage between negative affect and craving on days when individuals had at least four more positive social exchanges than usual.

CONCLUSIONS

These results indicate that both negative affect and negative social exchanges are uniquely related to craving on a daily basis, and that extra positive social interactions can reduce the intraindividual coupling of negative affect and craving during residential treatment for OUD. (PsycInfo Database Record (c) 2021 APA, all rights reserved).

Development and validation of a novel 15-CpG-based signature for predicting prognosis in triple-negative breast cancer

DNA methylation is an important biological regulatory mechanism that changes gene expression without altering the DNA sequence. Increasing studies have revealed that DNA methylation data play a vital role in the field of oncology. However, the methylation site signature in triple‐negative breast cancer (TNBC) remains unknown. In our research, we analysed 158 TNBC samples and 98 noncancerous samples from The Cancer Genome Atlas (TCGA) in three phases. In the discovery phase, 86 CpGs were identified by univariate Cox proportional hazards regression (CPHR) analyses to be significantly correlated with overall survival (P < 0.01). In the training phase, these candidate CpGs were further narrowed down to a 15‐CpG‐based signature by conducting least absolute shrinkage and selector operator (LASSO) Cox regression in the training set. In the validation phase, the 15‐CpG‐based signature was verified using two different internal sets and one external validation set. Furthermore, a nomogram comprising the CpG‐based signature and TNM stage was generated to predict the 1‐, 3‐ and 5‐year overall survival in the primary set, and it showed excellent performance in the three validation sets (concordance indexes: 0.924, 0.974 and 0.637). This study showed that our nomogram has a precise predictive effect on the prognosis of TNBC and can potentially be implemented for clinical treatment and diagnosis.