Explainable geospatial-artificial intelligence models for the estimation of PM2.5 concentration variation during commuting rush hours in Taiwan.

PM2.5 concentrations are higher during rush hours at background stations compared to the average concentration across these stations. Few studies have investigated PM2.5 concentration and its spatial distribution during rush hours using machine learning models. This study employs a geospatial-artificial intelligence (Geo-AI) prediction model to estimate the spatial and temporal variations of PM2.5 concentrations during morning and dusk rush hours in Taiwan. Mean hourly PM2.5 measurements were collected from 2006 to 2020, and aggregated into morning (7 a.m.-9 a.m.) and dusk (4 p.m.-6 p.m.) rush-hour mean concentrations. The Geo-AI prediction model was generated by integrating kriging interpolation, land-use regression, machine learning, and a stacking ensemble approach. A forward stepwise variable selection method based on the SHapley Additive exPlanations (SHAP) index was used to identify the most influential variables. The performance of the Geo-AI models for morning and dusk rush hours had accuracy scores of 0.95 and 0.93, respectively and these results were validated, indicating robust model performance. Spatially, PM2.5 concentrations were higher in southwestern Taiwan for morning rush hours, and suburban areas for dusk rush hours. Key predictors included kriged PM2.5 values, SO2 concentrations, forest density, and the distance to incinerators for both morning and dusk rush hours. These PM2.5 estimates for morning and dusk rush hours can support the development of alternative commuting routes with lower concentrations.

Automatic Speaker Positioning in Meetings Based on YOLO and TDOA.

In recent years, many things have been held via video conferences due to the impact of the COVID-19 epidemic around the world. A webcam will be used in conjunction with a computer and the Internet. However, the network camera cannot automatically turn and cannot lock the screen to the speaker. Therefore, this study uses the objection detector YOLO to capture the upper body of all people on the screen and judge whether each person opens or closes their mouth. At the same time, the Time Difference of Arrival (TDOA) is used to detect the angle of the sound source. Finally, the person's position obtained by YOLO is reversed to the person's position in the spatial coordinates through the distance between the person and the camera. Then, the spatial coordinates are used to calculate the angle between the person and the camera through inverse trigonometric functions. Finally, the angle obtained by the camera, and the angle of the sound source obtained by the microphone array, are matched for positioning. The experimental results show that the recall rate of positioning through YOLOX-Tiny reached 85.2%, and the recall rate of TDOA alone reached 88%. Integrating YOLOX-Tiny and TDOA for positioning, the recall rate reached 86.7%, the precision rate reached 100%, and the accuracy reached 94.5%. Therefore, the method proposed in this study can locate the speaker, and it has a better effect than using only one source.

A Fact-Finding Procedure Integrating Machine Learning and AHP Technique to Predict Delayed Diagnosis of Bladder Patients with Hematuria.

Bladder cancer, the ninth most common cancer worldwide, requires fast diagnosis and treatment to prevent disease progression and improve patient survival. However, patients with bladder cancer often experience considerable delays in diagnosis. One reason for such delays is that hematuria, a major symptom of bladder cancer, has a high probability of also being a warning sign for urinary tract diseases. Another reason is that the sensitivity of the body parts affected by bladder cancer deters patients from undergoing cystoscopy and influences patients' "physician shopping" behavior. In this study, the analytic hierarchy process was used to determine critical variables influencing delayed diagnosis; moreover, the variables were used to construct models for predicting delayed diagnosis in patients with hematuria by using several machine learning techniques. Furthermore, the critical variables associated with delayed diagnosis of bladder cancer in patients with hematuria were evaluated using GainRatio technology. The study sample was selected from a population-based database. The model evaluation results indicated that the prediction model established using decision tree algorithms outperformed the other models. The critical risk factors for delayed diagnosis of bladder cancer were as follows: (1) cystoscopy performed 6 months after hematuria diagnosis and (2) physician shopping.

Evaluating the impact of soy compounds on breast cancer using the data mining approach.

Accumulating evidence has shown that soy intake is associated with the promotion of health and prevention of cancers. However, the relationship between the intake of soy compounds and the risk of breast cancer is still debatable. In this study, we use mathematical models for assessing the impact of soy phytoestrogens and protein/peptide intervention on breast cancer development using the datasets acquired from a large number of published studies. We used data mining models, including the decision tree classification and association rule methods, to analyze 478 data collected from 201 research papers. The results indicated that the intervention of soy proteins and peptides, especially lunasin (LUN) and bowman-birk protease inhibitor (BBI), has a positive impact on different types of breast cancer, while the effects of soy phytoestrogens are inconsistent in breast cancer development. Among soy phytoestrogens, daidzein (DAI) exhibited the highest negative impact on breast cancer, followed by coumestrol (COU), soysapogenol (SAP), genistein (GEN), and equol (EQ). With regard to the type of cancer, phytoestrogens should be carefully considered in estrogen receptor (ER)+ or progesterone receptor (PR)+ breast cancer. In the case of ER-, PR- or triple negative type, both soy categories can be used as auxiliary interventions. In summary, this is the first study to use data mining to explore the relationship between the intake of soy phytoestrogens or proteins/peptides and breast cancer development. Our findings indicate that soy intervention might reduce breast cancer development. However, the specific soy compound and cancer type should be considered before allocating a precise nutrient intervention.

The Impact of the Moderating Effect of Psychological Health Status on Nurse Healthcare Management Information System Usage Intention.

Nurses play a key role in healthcare but work in a highly stressful and unfriendly environment. Therefore, many medical institutions have adopted nurse healthcare management information systems for nurses to relieve symptoms of mental stress and even improve their psychological health. The key to the success of these systems depends on how nurses intend to use them. In this study, the moderating effect of nurses' psychological health status on their usage of these systems are discussed. This study used a mail survey method for nurses to obtain 1565 valid samples. The results show that perceived usefulness is insignificant toward the usage intention of nurses with a positive psychological health status, which indicates that this system does not meet the needs of these healthy nurses. Furthermore, perceived ease of use is insignificant toward the usage intention of nurses with a negative psychological health status, which indicates that a negative psychological health status may affect one's behavior due to impatience. This study raises the serious issue that nurses should maintain their psychological health in order to ensure the quality of care for patients. People in various fields are expected to pay attention to the psychological health status of nurses and create a win-win situation for both patients and nurses.

Do Patients' Privacy Concerns Influence Their Intention toward Medical Image Exchange Consent in Taiwan?

The primary purpose of this study was to examine patients' concerns surrounding information privacy and their intention toward medical image exchange consent. Patients' concerns about information privacy in terms of collection, unauthorized access, errors and secondary use all have significant relationships with patients' intention toward medical image exchange consent in Taiwan. Trust is the foundation for both parties. In this study, we aimed to determine the moderating effect of trust in order to examine patients' intention toward medical image exchange consent under the influence of their information privacy concerns. Three hundred and fifty patients responded to the survey, which yielded a 92.3% response rate. The results of data analysis revealed that patients' information privacy concerns had no significant relationship with patients' intention toward medical image exchange consent. After considering the moderating effect of trust, patients' information privacy concerns do have a significant relationship with patients' intention toward medical image exchange consent, however, the R-square was only 4.5%. Based on this research result, we modified the research framework in order to examine patients' information privacy concerns in terms of collection/non-collection. The R-square of the modified framework was 18.6%, and both collection and non-collection had significant relationships with patients' intention toward medical image exchange consent. Finally, the implications, limitations and future research have been discussed.

Does Medical Students' Personality Traits Influence Their Attitudes toward Medical Errors?

This study examined medical students' perceptions towards medical errors and the policy of the hospital within the internship curriculum, and explored how aspects of personality traits of medical students relate to their attitude toward medical errors. Based on the theory of the Five-Factor-Model (FFM) and related literature review, this study adopted a self-devised structured questionnaire to distribute to 493 medical students in years five to seven in the top three medical schools, representing a 56.7% valid questionnaire response rate. Results showed that agreeableness is more important than other personality traits, and medical students with high agreeableness are good communicators and have a more positive attitude to avoid errors in the future. On the contrary, students with low neuroticism tended to be more relaxed and gentle. If medical educators can recruit new students with high agreeableness, these students will be more likely to effectively improve the quality of medical care and enhance patient safety. This study anticipates that this method could be easily translated to nearly every medical department entry examination, particularly with regards to a consciousness-based education of future physicians.

Health Knowledge Effects: An Integrated Community Health Promotion Platform.

The Taiwanese government subsidizes healthcare providers offering preventive medicine to patients to help reduce the threats of chronic sickness and halt skyrocketing medical expenditures. Usually, nurses are the primary workers who perform community health promotion; however, because of the chronic shortage of working nurses, many Taiwan hospitals have closed wards and deferred the responsibility of promoting primary prevention. With a community health promotion platform integrating interactive response features and Web sites for community patients and hospital staff, a case hospital efficiently sustained the community health services. The objective of this study was to assess the impact of the integrated community health promotion platform for conducting education. Fifty-four patients/residents were invited to join a quasi-experiment of health education, and a follow-up survey was conducted to assess the acceptance of the community health promotion platform from both the experimental group of learners/users and the hospital staff. The results showed that the community health promotion platform was effective in improving participant health awareness. The experimental group outperformed the control group, with higher posttest scores and longer knowledge retention. Furthermore, users indicated a high acceptance of the community health promotion platform.