Interpreting a standardized and normalized measure of neighborhood socioeconomic status for a better understanding of health differences

Optimization of an artificial neural network for predicting stress in robot-assisted laparoscopic surgery based on EDA sensor data

PURPOSE

This study aims to optimize tunable hyperparameters of the multilayer perceptron (MLP) setup. The optimization procedure is aimed at more accurately predicting potential health risks to the surgeon during robotic-assisted surgery (RAS).

METHODS

Data related to physiological parameters (electrodermal activity-EDA, blood pressure and body temperature) were collected during twenty RAS sessions completed by nine surgeons with different levels of experience. Once the dataset was generated, two preprocessing techniques (scaling and normalized) were applied. These datasets were divided into two subsets: with 80% data for training and cross-validation and 20% for testing. MLP was selected as the prediction technique. Three MLP hyperparameters were selected for optimization: number of epochs, learning rate and momentum. A central composite design (CCD) was applied with a full factorial design with five center points, with 31 combinations for each dataset. Once the models were generated on the training dataset, the optimized models were selected and then validated on the cross-validation and test datasets.

RESULTS

The optimized models were generated with an optimal number of epochs (500), the most applied learning rate was 0.01 and the most applied momentum was 0.05. These results showed significant improvement for EDA (R2 = 0.9722), blood pressure (R2 = 0.9977) and body temperature (R2 = 0.9941).

CONCLUSIONS

MLP parameters have been successfully optimized, and the enhanced models were successfully validated on cross-validation and test datasets. This fact invites us to optimize different AI techniques that could improve results in clinical practice.

Beta Burst Characteristics and Coupling within the Sensorimotor Cortical-Subthalamic Nucleus Circuit Dynamically Relate to Bradykinesia in Parkinson's Disease

BACKGROUND

Bursts of exaggerated subthalamic nucleus (STN) beta activity are believed to contribute to clinical impairments in Parkinson's disease (PD). No previous studies have explored burst characteristics and coupling across the sensorimotor cortical-STN circuit and determined their relationship to dynamic measurements of bradykinesia.

OBJECTIVE

We sought to (1) establish the characteristics of sensorimotor cortical and STN bursts during naturalistic behaviors, (2) determine the predictability of STN bursts from motor cortical recordings, and (3) relate burst features to continuous measurements of bradykinesia using wearable sensors.

METHODS

We analyzed 1046 h of wirelessly streamed bilateral sensorimotor cortical and STN recordings from 5 PD patients with concurrent measurements of bradykinesia.

RESULTS

STN bursts were longer than cortical bursts and had shorter inter-burst intervals. Long bursts (>200 ms) in both structures displayed temporal overlap (>30%), with cortical bursts tending to lead STN burst onset by 8 ms. Worsening bradykinesia was linked to increased cortical burst rates and durations, whereas STN burst properties had the opposite effect.

CONCLUSION

Cortical beta bursts tend to precede STN beta bursts with short delays and their occurrence relates to worsening bradykinesia in naturalistic settings. © 2025 The Author(s). Movement Disorders published by Wiley Periodicals LLC on behalf of International Parkinson and Movement Disorder Society.

DP202216 maize hybrids shift upper limit of C and N partitioning to grain

Increasing both harvest index (HI) and nitrogen (N) harvest index (NHI) is a promising approach for improving the effective use of resources in grain crops. Previous studies on maize (Zea mays L.) reported increments in different carbon (C)-N physiological and morphological traits in DP202216 hybrids (ZmGos2-zmm28, event DP202216, Corteva Agrisciences). The objectives of this study were to i) identify changes in the maximum limit (potential) of C and N partitioning to the grains (HI and NHI, respectively) in DP202216 maize hybrids at equal plant growth levels, and ii) determine the main factors underpinning the mechanisms associated with any observed changes in C and N partitioning to grains. Two DP202216 hybrids were evaluated with their respective wild-type (WT) controls during two field growing seasons (2022 and 2023) under three N rates (0 kg ha-1, 150 kg ha-1, and 300 kg ha-1). Long-term 15N labeling was used to precisely study N remobilization fluxes. The DP202216 plants showed an increase of 2% and 5% in the upper boundary of the HI and NHI, respectively. Furthermore, the DP202216 hybrids incremented 19% the relative allocation of 15N to grains. This was translated into a higher utilization of N absorbed during vegetative stages in DP202216 hybrids, independently of the amount of N uptake. The hybrids with the DP202216 event increased 9% the number of grains per unit of plant biomass. Our study describes improvements on the upper limit of HI and NHI in DP202216 maize hybrids. We showed that the increase in C and N allocation to the reproductive organs in the DP202216 hybrids was related to higher 'relative' C and N demand by the grains. Thus, the DP202216 trait provides a new genetic tool to improve grain yield potential and yield stability via enhanced resource utilization in maize production, offering the farmers the opportunity to maximize return on investment (ROI) for N input costs.

Correlation Study and Predictive Modelling of Ergonomic Parameters in Robotic-Assisted Laparoscopic Surgery

BACKGROUND

This study aims to continue research on the objective analysis of ergonomic conditions in robotic-assisted surgery (RAS), seeking innovative solutions for the analysis and prevention of ergonomic problems in surgical practice.

METHODS

Four different robotic-assisted tasks were performed by groups of surgeons with different surgical experiences. Different wearable technologies were used to record surgeons' posture and muscle activity during surgical practice, for which the correlation between them was analyzed. A predictive model was generated for each task based on the surgeons' level of experience and type of surgery. Two preprocessing techniques (scaling and normalization) and two artificial intelligence techniques were tested.

RESULTS

Overall, a positive correlation between prolonged maintenance of an ergonomically inadequate posture during RAS and increased accumulated muscle activation was found. Novice surgeons showed improved posture when performing RAS compared to expert surgeons. The predictive model obtained high accuracy for cutting, peg transfer, and labyrinth tasks.

CONCLUSIONS

This study expands on the existing ergonomic analysis of the lead surgeon during RAS and develops predictive models for future prevention of ergonomic risk situations. Both posture and muscle loading are highly related to the surgeon's previous experience.

Applying artificial intelligence on EDA sensor data to predict stress on minimally invasive robotic-assisted surgery

PURPOSE

This study aims predicting the stress level based on the ergonomic (kinematic) and physiological (electrodermal activity-EDA, blood pressure and body temperature) parameters of the surgeon from their records collected in the previously immediate situation of a minimally invasive robotic surgery activity.

METHODS

For this purpose, data related to the surgeon's ergonomic and physiological parameters were collected during twenty-six robotic-assisted surgical sessions completed by eleven surgeons with different experience levels. Once the dataset was generated, two preprocessing techniques were applied (scaled and normalized), these two datasets were divided into two subsets: with 80% of data for training and cross-validation, and 20% of data for test. Three predictive techniques (multiple linear regression-MLR, support vector machine-SVM and multilayer perceptron-MLP) were applied on training dataset to generate predictive models. Finally, these models were validated on cross-validation and test datasets. After each session, surgeons were asked to complete a survey of their feeling of stress. These data were compared with those obtained using predictive models.

RESULTS

The results showed that MLR combined with the scaled preprocessing achieved the highest R2 coefficient and the lowest error for each parameter analyzed. Additionally, the results for the surgeons' surveys were highly correlated to the results obtained by the predictive models (R2 = 0.8253).

CONCLUSIONS

The linear models proposed in this study were successfully validated on cross-validation and test datasets. This fact demonstrates the possibility of predicting factors that help us to improve the surgeon's health during robotic surgery.

Enhancing infectious disease prediction model selection with multi-objective optimization: an empirical study

As the pandemic continues to pose challenges to global public health, developing effective predictive models has become an urgent research topic. This study aims to explore the application of multi-objective optimization methods in selecting infectious disease prediction models and evaluate their impact on improving prediction accuracy, generalizability, and computational efficiency. In this study, the NSGA-II algorithm was used to compare models selected by multi-objective optimization with those selected by traditional single-objective optimization. The results indicate that decision tree (DT) and extreme gradient boosting regressor (XGBoost) models selected through multi-objective optimization methods outperform those selected by other methods in terms of accuracy, generalizability, and computational efficiency. Compared to the ridge regression model selected through single-objective optimization methods, the decision tree (DT) and XGBoost models demonstrate significantly lower root mean square error (RMSE) on real datasets. This finding highlights the potential advantages of multi-objective optimization in balancing multiple evaluation metrics. However, this study's limitations suggest future research directions, including algorithm improvements, expanded evaluation metrics, and the use of more diverse datasets. The conclusions of this study emphasize the theoretical and practical significance of multi-objective optimization methods in public health decision support systems, indicating their wide-ranging potential applications in selecting predictive models.

Discriminating insulin resistance in middle-aged nondiabetic women using machine learning approaches

Objective

We employed machine learning algorithms to discriminate insulin resistance (IR) in middle-aged nondiabetic women.

Methods

The data was from the National Health and Nutrition Examination Survey (2007-2018). The study subjects were 2084 nondiabetic women aged 45-64. The analysis included 48 predictors. We randomly divided the data into training (n = 1667) and testing (n = 417) datasets. Four machine learning techniques were employed to discriminate IR: extreme gradient boosting (XGBoosting), random forest (RF), gradient boosting machine (GBM), and decision tree (DT). The area under the curve (AUC) of receiver operating characteristic (ROC), accuracy, sensitivity, specificity, positive predictive value, negative predictive value, and F1 score were compared as performance metrics to select the optimal technique.

Results

The XGBoosting algorithm achieved a relatively high AUC of 0.93 in the training dataset and 0.86 in the testing dataset to discriminate IR using 48 predictors and was followed by the RF, GBM, and DT models. After selecting the top five predictors to build models, the XGBoost algorithm with the AUC of 0.90 (training dataset) and 0.86 (testing dataset) remained the optimal prediction model. The SHapley Additive exPlanations (SHAP) values revealed the associations between the five predictors and IR, namely BMI (strongly positive impact on IR), fasting glucose (strongly positive), HDL-C (medium negative), triglycerides (medium positive), and glycohemoglobin (medium positive). The threshold values for identifying IR were 29 kg/m2, 100 mg/dL, 54.5 mg/dL, 89 mg/dL, and 5.6% for BMI, glucose, HDL-C, triglycerides, and glycohemoglobin, respectively.

Conclusion

The XGBoosting algorithm demonstrated superior performance metrics for discriminating IR in middle-aged nondiabetic women, with BMI, glucose, HDL-C, glycohemoglobin, and triglycerides as the top five predictors.

Modeling children's moral development in postwar Taiwan through naturalistic observations preserved in historical texts

A core issue in the interdisciplinary study of human morality is its ontogeny in diverse cultures, but systematic, naturalistic data in specific cultural contexts are rare to find. This study conducts a novel analysis of 213 children's socio-moral behavior in a historical, non-Western, rural setting, based on a unique dataset of naturalistic observations from the first field research on Han Chinese children. Using multilevel multinomial modeling, we examined a range of proactive behaviors in 0-to-12-year-old children's peer cooperation and conflict in an entire community in postwar Taiwan. We modeled the effects of age, sex, kinship, and behavioral roles, and revealed complex interactions between these four variables in shaping children's moral development. We discovered linkages between coercive and non-coercive behaviors as children strategically negotiated leadership dynamics. We identified connections between prosocial and aggressive behaviors, illuminating the nuances of morality in real life. Our analysis also revealed gendered patterns and age-related trends that deviated from cultural norms and contradicted popular assumptions about Chinese family values. These findings highlight the importance of naturalistic observations in cultural contexts for understanding how we become moral persons. This re-analysis of historically significant fieldnotes also enriches the interdisciplinary study of child development across societies.

3D Video Tracking Technology in the Assessment of Orofacial Impairments in Neurological Disease: Clinical Validation

PURPOSE

This study sought to determine whether clinically interpretable kinematic features extracted automatically from three-dimensional (3D) videos were correlated with corresponding perceptual clinical orofacial ratings in individuals with orofacial impairments due to neurological disorders.

METHOD

45 participants (19 diagnosed with motor neuron diseases [MNDs] and 26 poststroke) performed two nonspeech tasks (mouth opening and lip spreading) and one speech task (repetition of a sentence "Buy Bobby a Puppy") while being video-recorded in a standardized lab setting. The color video recordings of participants were assessed by an expert clinician-a speech language pathologist-on the severity of three orofacial measures: symmetry, range of motion (ROM), and speed. Clinically interpretable 3D kinematic features, linked to symmetry, ROM, and speed, were automatically extracted from video recordings, using a deep facial landmark detection and tracking algorithm for each of the three tasks. Spearman correlations were used to identify features that were significantly correlated (p value < .05) with their corresponding clinical scores. Clinically significant kinematic features were then used in the subsequent multivariate regression models to predict the overall orofacial impairment severity score.

RESULTS

Several kinematic features extracted from 3D video recordings were associated with their corresponding perceptual clinical scores, indicating clinical validity of these automatically derived measures. Different patterns of significant features were observed between MND and poststroke groups; these differences were aligned with clinical expectations in both cases.

CONCLUSIONS

The results show that kinematic features extracted automatically from simple clinical tasks can capture characteristics used by clinicians during assessments. These findings support the clinical validity of video-based automatic extraction of kinematic features.

Census-Tract-Level Median Household Income and Median Family Income Estimates: A Unidimensional Measure of Neighborhood Socioeconomic Status?

Previous studies suggested either census-tract-level median household income (MHI) or median family income (MFI) estimates may be used as a unidimensional measure of neighborhood socioeconomic status (SES) in the United States (US). To better understand its general use, the purpose of this study was to assess the usefulness of MHI and MFI in a wide range of geographic areas. Area-based socioeconomic data at the census tract level were obtained from the 2000 Census as well as the 2005-2009, 2010-2014, and 2015-2019 American Community Survey. MHI and MFI were used as two simple measures of neighborhood SES. Based on the five area-based indexes developed in the US, several census-tract-level socioeconomic indicators were used to derive five composite measures of neighborhood SES. Then, a series of correlation analyses was conducted to assess the relationships between these seven measures in the State of California and its seven Metropolitan Statistical Areas. Two simple measures were very strongly and positively correlated with one another, and were also strongly or very strongly correlated, either positively or negatively, with five composite measures. Hence, the results of this study support an analytical thinking that simple measures and composite measures may capture the same dimension of neighborhood SES in different geographic areas.