ABSTRACT
Introduction: This study conducts a comprehensive exploration of the neurocognitive processes underlying consumer credit decision-making using cutting-edge techniques from neuroscience and machine learning (ML). Employing functional Near-Infrared Spectroscopy (fNIRS), the research examines the hemodynamic responses of participants while evaluating diverse credit offers. Methods: The experimental phase of this study investigates the hemodynamic responses collected from 39 healthy participants with respect to different loan offers. This study integrates fNIRS data with advanced ML algorithms, specifically Extreme Gradient Boosting, CatBoost, Extra Tree Classifier, and Light Gradient Boosted Machine, to predict participants' credit decisions based on prefrontal cortex (PFC) activation patterns. Results: Findings reveal distinctive PFC regions correlating with credit behaviors, including the dorsolateral prefrontal cortex (dlPFC) associated with strategic decision-making, the orbitofrontal cortex (OFC) linked to emotional valuations, and the ventromedial prefrontal cortex (vmPFC) reflecting brand integration and reward processing. Notably, the right dorsomedial prefrontal cortex (dmPFC) and the right vmPFC contribute to positive credit preferences. Discussion: This interdisciplinary approach bridges neuroscience, machine learning and finance, offering unprecedented insights into the neural mechanisms guiding financial choices regarding different loan offers. The study's predictive model holds promise for refining financial services and illuminating human financial behavior within the burgeoning field of neurofinance. The work exemplifies the potential of interdisciplinary research to enhance our understanding of human financial decision-making.
ABSTRACT
Background: Various visual tools are used to improve medication adherence in communication with the patient. Pharmaceutical pictograms are one such tool utilized within this communication process. Objective: The aim of this study is to investigate the eye movement of the participants and to recommend the most suitable location of pictograms on pharmaceutical packaging accordingly. It also aims to show whether there is a significant correlation between the effectiveness of pictograms and the health literacy, age, and gender of the participant. Methods: Forty-two participants were exposed to sixty stimuli showing four different pharmaceutical packages as an on-screen slide show. Participants were asked what they understood from the pictograms on the packaging, and their eye movements were examined using eye tracking to determine heat maps and areas of interest, and to measure the time to first fixation, total fixation duration, and percentage fixated. Results: The study revealed that the understanding level of the pictograms was determined at between 11.9 % and 71.43 %. Among the pictograms, only a small percentage 13% - namely numbers 12 and 13 which were prepared and validated by the FIP, achieved a score of 67%, the minimum level of comprehension in accordance with ISO 3684. We observed that participants fixated at least once on the pictograms up to 95% of the time. The pictograms were found to be most easily noticed at the center with a secondary focus area towards center-right parts of the packaging. Vertical design was highly engaging for participants regardless of health literacy. The significant relationship was found between the understanding of the pictograms and gender when mean values are examined. However, no significant relationship was between health literacy and pictogram comprehension level. Conclusions: This is the first study to have used eye tracking to analyze pictograms added to real pharmaceutical packaging on the market. Its findings can guide pharmaceutical companies to design their packaging in a way that prioritizes patient safety, and to place critical pictograms more effectively. These results can be adapted medication label design in hospitals to promote appropriate use. Studies to improve patient adherence by using pictograms should be diversified.
