Data science vs. statistics: two cultures?

Machine Learning for Treatment Management Prediction in Laryngeal Fractures

OBJECTIVES

Laryngeal fractures are rare but potentially life-threatening traumas. Complications, such as airway obstruction and disrupted laryngeal anatomy, associate with significant morbidity. Early identification of at-risk patients and optimal management remain crucial for improved outcomes. Recently, machine learning (ML) has attained great attention as a unique and novel technique for evaluating complex nonlinear relationships between multiple observations to create a predictive model with greater accuracy. This study aimed to demonstrate the potential of ML in predicting airway and surgical management of laryngeal fracture patients and identify key contributing parameters for the predictive performance of the ML models.

METHODS

The ML models were developed using a patient series managed at the Helsinki University Hospital during 2005-2019. The developed models were further evaluated independently using a different cohort collected from the same institution between 1995 and 2004.

RESULTS

The ML showed a weighted area under curve (AUC) of 0.93 and accuracy of 0.86 following training for airway management. Likewise, for treatment approach, weighted AUC was 0.85 and accuracy 0.78. Injury type, Schaefer-Fuhrman grade (SF gr), age at incident, cause of injury, and fracture of the cricoid, in decreasing order of significance, were the most prominent features for the model's predictive performance for airway management. Similarly, our model identified SF gr, fracture of the cricoid, injury type, age at incident, and cause of injury as the most significant predictors for surgical treatment approach.

CONCLUSIONS

The proposed prediction of management approach by an ML technique can provide accurate predictions and thus aid clinicians in administering early and personalized interventions. The model may serve as a supporting tool in recognizing at-risk patients and in timely decision-making. Further independent external validation is warranted for model generalizability.

Irruption of Network Analysis to Explain Dietary, Psychological and Nutritional Patterns and Metabolic Health Status in Metabolically Healthy and Unhealthy Overweight and Obese University Students: Ecuadorian Case

BACKGROUND

The association between dietary nutritional patterns, psychological factors, and metabolic health status has not been investigated in university students. There are studies that include numerous variables to test hypotheses from various theoretical bases, but due to their complexity, they have not been studied in combination. The scientific community recognizes the use of Gaussian graphical models (GGM) as a set of novel methods capable of addressing this.

OBJECTIVE

To apply GGMs to derive specific networks for groups of healthy and unhealthy obese individuals that represent nutritional, psychological, and metabolic patterns in an Ecuadorian population.

METHODOLOGY

This was a quantitative, non-experimental, cross-sectional, correlational study conducted on a sample of 230 obese/overweight university students, selected through a multi-stage random sampling method. To assess usual dietary intake, a Food Frequency Questionnaire (FFQ) was used; to evaluate psychological profiles (anxiety, depression, and stress), the DASS-21 scale was employed; blood pressure and anthropometric data were collected; and insulin levels, lipid profiles, and glucose levels were determined using fasting blood samples. The International Diabetes Federation (IDF) criteria were applied to identify metabolically healthy and unhealthy individuals. Statistical analysis relied on univariate methods (frequencies, measures of central tendency, and dispersion), and the relationships were analyzed through networks. The Mann-Whitney U test was used to analyze differences between groups.

RESULTS

In metabolically unhealthy obese individuals, GGMs identified a primary network consisting of the influence of waist circumference on blood pressure and insulin levels. In the healthy obese group, a different network was identified, incorporating stress and anxiety variables that influenced blood pressure, anthropometry, and insulin levels. Other identified networks show the dynamics of obesity and the effect of waist circumference on triglycerides, anxiety, and riboflavin intake.

CONCLUSIONS

GGMs are an exploratory method that can be used to construct networks that illustrate the behavior of obesity in the studied population. In the future, the identified networks could form the basis for updating obesity management protocols in Primary Care Units and supporting clinical interventions in Ecuador.

Utilizing a novel high-resolution malaria dataset for climate-informed predictions with a deep learning transformer model

Climatic factors influence malaria transmission via the effect on the Anopheles vector and Plasmodium parasite. Modelling and understanding the complex effects that climate has on malaria incidence can enable important early warning capabilities. Deep learning applications across fields are proving valuable, however the field of epidemiological forecasting is still in its infancy with a lack of applied deep learning studies for malaria in southern Africa which leverage quality datasets. Using a novel high resolution malaria incidence dataset containing 23 years of daily data from 1998 to 2021, a statistical model and XGBOOST machine learning model were compared to a deep learning Transformer model by assessing the accuracy of their numerical predictions. A novel loss function, used to account for the variable nature of the data yielded performance around + 20% compared to the standard MSE loss. When numerical predictions were converted to alert thresholds to mimic use in a real-world setting, the Transformer's performance of 80% according to AUROC was 20-40% higher than the statistical and XGBOOST models and it had the highest overall accuracy of 98%. The Transformer performed consistently with increased accuracy as more climate variables were used, indicating further potential for this prediction framework to predict malaria incidence at a daily level using climate data for southern Africa.

R package DCchoice for dichotomous choice contingent valuation: a contribution to open scientific software and its impact

The R package DCchoice is designed to mitigate programing-related barriers to the application of dichotomous choice contingent valuation (DCCV) methods in empirical studies. Since its release in 2014, DCchoice has been updated. This paper introduces the current version of DCchoice which supports single-, one-and-one-half-, and double-bounded DCCVs, with and without a spike. Additionally, the willingness-to-pay and its confidence intervals can be calculated for a representative respondent as well as for a user-defined specific respondent using the current version. The associated web tutorial and R Commander plug-in for basic usage of DCchoice are also available. DCchoice has advanced DCCV applications in various fields.

Artificial intelligence for renal cancer: From imaging to histology and beyond

Artificial intelligence (AI) has made considerable progress within the last decade and is the subject of contemporary literature. This trend is driven by improved computational abilities and increasing amounts of complex data that allow for new approaches in analysis and interpretation. Renal cell carcinoma (RCC) has a rising incidence since most tumors are now detected at an earlier stage due to improved imaging. This creates considerable challenges as approximately 10%–17% of kidney tumors are designated as benign in histopathological evaluation; however, certain co-morbid populations (the obese and elderly) have an increased peri-interventional risk. AI offers an alternative solution by helping to optimize precision and guidance for diagnostic and therapeutic decisions. The narrative review introduced basic principles and provide a comprehensive overview of current AI techniques for RCC. Currently, AI applications can be found in any aspect of RCC management including diagnostics, perioperative care, pathology, and follow-up. Most commonly applied models include neural networks, random forest, support vector machines, and regression. However, for implementation in daily practice, health care providers need to develop a basic understanding and establish interdisciplinary collaborations in order to standardize datasets, define meaningful endpoints, and unify interpretation.