Personal Assessment Research Articles

Unsupervised machine learning identifies distinct phenotypes in cardiac complications of pediatric patients treated with anthracyclines

BackgroundAnthracyclines are essential in pediatric cancer treatment, but patients are at risk cancer therapy-related cardiac dysfunction (CTRCD). Standardized definitions by the International Cardio-Oncology Society (IC-OS) aim to enhance precision in risk assessment.ObjectivesCategorize distinct phenotypes among pediatric patients undergoing anthracycline chemotherapy using unsupervised machine learning.MethodsPediatric cancer patients undergoing anthracycline chemotherapy at our institution were retrospectively included. Clinical and echocardiographic data at baseline, along with follow-up data, were collected from patient records. Unsupervised machine learning was performed, involving dimensionality reduction using principal component analysis and K-means clustering to identify different phenotypic clusters. Identified phenogroups were analyzed for associations with CTRCD, defined following contemporary IC-OS definitions, and hypertensive response.ResultsA total of 187 patients (63.1% male, median age 15.5 years [10.4–18.7]) were included and received anthracycline chemotherapy with a median treatment duration of 0.66 years [0.35–1.92]. Median follow-up duration was 2.78 years [1.31–4.21]. Four phenogroups were identified with following distribution: Cluster 0 (32.6%, n = 61), Cluster 1 (13.9%, n = 26), Cluster 2 (24.6%, n = 46), and Cluster 3 (28.9%, n = 54). Cluster 0 showed the highest risk of moderate CTRCD (HR: 3.10 [95% CI: 1.18–8.16], P = 0.022) compared to other clusters. Cluster 3 demonstrated a protective effect against hypertensive response (HR: 0.30 [95% CI: 0.13– 0.67], P = 0.003) after excluding baseline hypertensive patients. Longitudinal assessments revealed differences in global longitudinal strain and systolic blood pressure among phenogroups.ConclusionsUnsupervised machine learning identified distinct phenogroups among pediatric cancer patients undergoing anthracycline chemotherapy, offering potential for personalized risk assessment.

Machine learning for pacemaker implantation prediction after TAVI using multimodal imaging data

Pacemaker implantation (PMI) after transcatheter aortic valve implantation (TAVI) is a common complication. While computed tomography (CT) scan data are known predictors of PMI, no machine learning (ML) model integrating CT with clinical, ECG, and transthoracic echocardiography (TTE) data has been proposed. This study investigates the contribution of ML methods to predict PMI after TAVI, with a focus on the role of CT imaging data. A retrospective analysis was conducted on a cohort of 520 patients who underwent TAVI. Recursive feature elimination with SHAP values was used to select key variables from clinical, ECG, TTE, and CT data. Six ML models, including Support Vector Machines (SVM), were trained using these selected variables. The model’s performance was evaluated using AUC-ROC, F1 score, and accuracy metrics. The PMI rate was 18.8%. The best-performing model achieved an AUC-ROC of 92.1% ± 4.7, an F1 score of 71.8% ± 9.9, and an accuracy of 87.9% ± 4.7 using 22 variables, 9 of which were CT-based. Membranous septum measurements and their dynamic variations were critical predictors. Our ML model provides robust PMI predictions, enabling personalized risk assessments. The model is implemented online for broad clinical use.

Changes in Auditory Performance Following a Virtual Reality Music Concert.

The purpose of this study was to evaluate threshold and suprathreshold auditory risk from a newly popular platform of music concert entertainment; virtual reality (VR) headsets. Recreational noise exposure to music is the primary source of hearing hazard in young-adults, with noise doses of in-person concert venues and music festivals well in excess of the recommended daily exposure recommendation from the National Institute for Occupational Safety and Health. While research on the relationship between personal music players and noise-induced hearing loss risk is abundant, no study has yet evaluated noise-induced hearing loss risk from VR headsets, which are newest to the commercial market at this time. Thirty-one young-adult participants (18 to 25 years) with normal-hearing sensitivity (0 to 16 dB HL) experienced a VR music concert and participated in three data collection timepoints: Session A preexposure, Session A post-exposure, and Session B post-exposure. Participants underwent baseline testing for audiometry (0.25 to 20 kHz), distortion product otoacoustic emission testing (1 to 10 kHz), and Words-in-Noise testing. Participants then wore a commercially available VR headset (Meta Quest 2) and experienced a freely available online VR music concert (via the video-sharing website "YouTube"). The VR music concert duration was 90 min set to maximum volume, which yielded an average sound level equivalent of 78.7 dBA, max sound level of 88.2 dBA, and LC peak sound level of 98.6 dBA. Post-exposure testing was conducted immediately at the conclusion of the VR concert, and again within 24 hr to 1 week after the exposure. Participants also answered a questionnaire that estimated noise exposure history (National Acoustics Laboratory "Noise Calculator"). Post-exposure deficit was not observed in DPOAEs or Words-in-Noise score (p's > 0.05). However, statistically significant temporary post-exposure deficit was observed in audiometry at 4, 8, and 12.5 kHz (p's < 0.05) (mean differences: 2 to 3 dB HL). Twenty-four hours and 1-week post-exposure measurements revealed no permanent changes from baseline measurements (p's > 0.05) aside from one spurious difference at 12.5 kHz. Males tended to exhibit a significantly higher noise history score on average than females. The primary, secondary, and tertiary sources of noise hazard history in this young-adult cohort included amplified music. These preliminary data suggest that VR music concerts-which are likely to produce a substantially lower noise dose than in-person music concerts-may still be capable of producing at least slight, temporary threshold shifts on the order of 2 to 3 dB HL. Future research should include VR headsets in personal music player risk assessment, as the VR music concert platform is increasing rapidly in popularity among young-adults.

Disease Prediction and Drug Recommendation Using ML

In today's dynamic healthcare landscape, the integration of technology has become indispensable. The project sets out to create a cutting-edge healthcare solution that will transform the very foundations of healthcare decision-making by utilizing the powerful powers of machine learning. The main objective of this project is to develop a dual-dashboard system that will serve both patients and medical staff. The main objective is to reduce the gap between patients and healthcare professionals, which has existed for a long time. It makes it possible for people to receive highly personalized health assessments, enables efficient appointment scheduling, and provides doctors with recommendations for data-driven treatments. Ultimately, this project aims to profoundly impact the accessibility and quality of healthcare services. It seeks to enhance the patient experience, augment the precision of medical decision-making, and foster seamless collaboration between individuals and their healthcare providers.

A Tribute to Jaume Porta Casanellas and His Influence on Soil Science

This article provides personal and professional assessments from disciples, colleagues and friends of Jaume Porta Casanellas (Barcelona, 1944; Lleida, 2023), a prominent soil scientist. He began his agricultural engineering studies at the Polytechnic University of Madrid (UPM) where he met Marta López-Acevedo, his wife and outstanding collaborator. At UPM, he started his early work in soil science under the guidance of Professor Carlos Roquero who became his mentor and friend. Jaume Porta was a dedicated, passionate soil scientist who engaged extensively in teaching and research in Soil Science, while also excelling as a manager. He emerged as a leader due to his initiatives in promoting Soil Science in Catalonia and Spain, and for his forward-thinking vision, evident in his decisions as Rector of the University of Lleida, which have significantly contributed to the city’s development. From the beginning, he advocated for detailed (1:25,000) soil mapping of Catalonia to enhance territorial planning and agricultural progress. His primary research focus was on salt-affected soils and soils with gypsum, alongside soil erosion and conservation. Porta devoted a lot of effort to improve soil field descriptions with his Agenda de campo. He played a key role in standardizing soil analytical methods, establishing large series laboratories in Spain, notably the LAF in Sidamon (Lleida), and aligning Spanish soil labs with the international GLOSOLAN network. As president of the SECS, he energized activities and encouraged member participation. His educational publications, mainly his comprehensive textbook Edafología, are considered fundamental in Soil Science across Spanish-speaking countries, as is the Multilingual Dictionary of Soil Science, representing the pinnacle of his efforts to rigorously disseminate soil science concepts and terms in Spanish, Catalan, Galician, and Portuguese. He contributed significantly to international Soil Science courses in Mexico and played a key role in establishing the JADE postgraduate training program. He facilitated the creation and international visibility of the Spanish Journal of Soil Science. Additionally, he advocated for the establishment of the Soil Sciences Documentation Centre (Ce.SECS) to preserve historical publications and the legacy of soil scientists. Jaume Porta’s enduring impact, both professionally and personally, will be felt for years to come.

Enhancing Flexible Assessment Through ePortfolios: A Scholarly Examination

In contemporary educational settings, the demand for flexible assessment practices has gained prominence due to students' diverse learning needs and preferences. Portfolios have emerged as a versatile tool for facilitating personalised and adaptable assessment processes. This paper investigates how ePortfolios can cater to students' flexible assessment needs. By examining the benefits, challenges, and implementation strategies associated with ePortfolios, this paper highlights their potential to enhance assessment practices, foster student engagement, and promote lifelong learning. As part of implementation strategies, we provide examples to support teaching staff and institutions in translating the underpinning principles and theory into actionable practice.

Overall survival and disease-free survival prediction in Chinese women with breast cancer aged 70 years or older by using nomograms.

By analyzing the existing data of this study, a prediction tool for the overall breast cancer survival and disease-free survival (DFS) of elderly women was established. Clinicopathologic data were collected from elderly women with BC who were admitted to the Tianjin Medical University Cancer Institute and Hospital from August 2014 to December 2017. Independent prognostic factors for BC in elderly patients were confirmed using the Cox proportional hazards model. Nomograms were developed with these factors for predicting the 3- and 5-year overall survival (OS) as well as DFS. The nomograms' discrimination ability and calibration were assessed through the area under the curve (AUC), concordance index (C-index), decision curve analysis (DCA), and calibration plots. We enroled 889 elderly patients with BC, and the results showed that the 3-year OS rate was 93.4% (95%CI = 91.8%-95.1%), the 3-year DFS rate was 87.8% (95%CI = 85.7%-90.0%), the 5-year OS rate was 85.6% (95%CI = 83.3%-87.9%), and the 5-year DFS rate was 80.1%(95%CI = 77.5%-82.8%). The corrected C-indices of the OS and DFS nomograms were 0.799 and 0.667, respectively (95%CI = 0.767-0.830 and 0.632-0.702, respectively). Relatively high AUC values were shown by the nomograms for estimating OS and DFS. The DCA revealed that the constructed nomograms had net benefits for clinical application. The calibration curves demonstrated an excellent correspondence between the data predicted by the nomograms and the actual survival data. Survival curves indicated that risk stratification could differentiate OS and DFS. This study developed novel and practical nomograms for individual prediction of DFS and OS in elderly BC patients. These nomograms can predict 3- and 5-year OS as well as DFS in the elderly BC patient population, thereby enabling personalized risk assessment and risk-based therapy.

Foreign experience of evaluating the effectiveness of police activity and the possibility of its implementation in Ukraine

The article is devoted to the study of foreign experience in assessing the effectiveness of police activities and the analysis of the possibility of its application in Ukraine. In particular, the author examines the foreign experience of evaluating the effectiveness of police activities in such countries as Austria, Great Britain, Estonia, Canada, Latvia, Lithuania, the USA, France, and the possibility of its implementation in Ukraine. Particular attention is paid to evaluation methods that combine quantitative and qualitative indicators of police performance. The authors point out the importance of internal and external control, with a significant role for public control, which is ensured through surveys, reporting and other forms of interaction with the public. The experience of foreign countries also includes the use of statistical reports on crime, such as in the United States and Austria, which allow not only to assess the work of the police but also to increase the level of trust in law enforcement agencies. It is concluded that the introduction of a point-based performance evaluation system should be applied to the personal assessment of each police officer. Based on the study, we conclude that in all foreign countries analyzed by us, today much attention is paid to the assessment of the effectiveness of police activities, which is due to the social purpose of its activities, but, given the existing legal system, organizational and legal framework for the activities of police units, and the adopted system of their management, the criteria for such assessment differ. In addition, we have found that certain forms of police performance evaluation, such as public opinion polls and annual reports on police performance, are common to both national and most foreign police systems. As a result of summarizing foreign experience in assessing the effectiveness of police activities, the author suggests using the following positive issues, namely: introduction of the above-mentioned US experience in Ukraine, since such ‘Crime Maps’ are available; use of the positive experience of the HM Inspectorate for Constabulary (UK) in the activities of the newly established Department of the Main Inspectorate and Human Rights of the National Police of Ukraine, in particular, in assessing the quality of police services.

Adherence to high-frequency ecological momentary assessment in persons with moderate-to-severe traumatic brain injury.

Ecological momentary assessment (EMA) involves repeated collection of real-time self-report data, often multiple times per day, nearly always delivered electronically by smartphone. While EMA has shown promise for researching internal states, behaviors, and experiences in multiple populations, concerns remain regarding its feasibility in samples with cognitive impairments, like those associated with chronic moderate-to-severe traumatic brain injury (TBI). This study examines adherence to a 7-week high-frequency (5x daily) EMA protocol in individuals with moderate-to-severe TBI, considering changes in response rate over time, as well as individual participant characteristics (memory function, education, injury severity, and age). In the sample of 39 participants, the average overall response rate was 65% (range: 5%-100%). Linear mixed-effects modeling revealed a small but statistically significant linear decay in response rate over 7 weeks of participation. Individual trajectories were variable, as evidenced by the significant effect of random slope. A better response rate was positively associated with greater educational attainment and better episodic memory function (statistical trend), whereas the effects of age and injury severity were not significant. These findings shed light on the potential of EMA in TBI studies but underscore the need for tailored strategies to address individual barriers to adherence.

Comparative Outcomes of a Cognitive-Behavioral Skills Building Program on the Mental Health and Healthy Behaviors of Prenursing Students

Background: Nursing students experience significantly more stress related diseases when compared to non-nursing students, and the state of their mental health can result in short-term increased attrition rates and increased nursing shortages. Purpose: A preexperimental pre-post study design was used to examine mental health and healthy behaviors among prenursing students. Methods: Cohorts received the MINDSTRONG© program either in-person or virtually. Data analysis included Personal Wellness Assessments completed at both pre- and poststudy for all participants (n = 110). Results: Both groups postintervention had statistically significant decreases in anxiety, depression, and stress and statistically significant increases in healthy lifestyle behaviors and beliefs. Students with elevated depression and anxiety scores at baseline had greater decreases postintervention than the overall groups. Conclusion: The outcomes for both cohorts were positive and effective in reducing stress, anxiety, and depressive symptoms. Healthy behaviors were improved and align with findings with an in-person format. Findings from this study support implementation of MINDSTRONG in synchronous sessions, either in-person or virtual.

The influence of entrepreneurial education on the development of entrepreneurial intentions of young people

A successful start-up begins with an innovative idea, which is then realized by identifying and seizing an opportunity. Innovation is one of the most crucial entrepreneurial qualities in this type of entrepreneurship. The aim of this paper is to determine the fundamental and specific characteristics of start-up entrepreneurship and to examine the entrepreneurial intentions and knowledge of young people in this field. The empirical research in this paper includes both secondary and primary research. Secondary research involves the presentation of relevant studies in the fields of start-up entrepreneurship and entrepreneurial education. The primary empirical research was conducted on a sample of 160 students from higher education institutions in Međimurje and Varaždin counties. The results indicate that students are relatively well-informed about the possibilities of starting a start-up company. Their personal assessments of their familiarity with the processes involved in starting a start-up are of average value. Additionally, respondents identified administrative procedures, high taxes, lack of knowledge about funding sources, and insufficient information about reference centers as the main obstacles to entering entrepreneurship. By testing the research hypotheses, it was found that attending formal classes in entrepreneurship positively affects the entrepreneurial intentions of young people. The limitations of the research include the restriction of the sample to northwestern Croatia. The findings suggest a further need to strengthen entrepreneurship education and expand it to younger populations in the Republic of Croatia.

Leveraging mitochondrial-programmed cell death dynamics to enhance prognostic accuracy and immunotherapy efficacy in lung adenocarcinoma

BackgroundLung adenocarcinoma (LUAD) is a highly heterogeneous disease, posing significant challenges to accurate prognosis prediction. Mitochondria play a central role in the energy metabolism of eukaryotic cells and can influence...

Determinants and predictors of Occupational Burnout syndrome among Residents Physicians

Background: The burnout syndrome has 3 dimensions; first is emotional exhaustion, second one is depersonalization, and third is low personal accomplishment. Work related burnout is increased nowadays and it becomes a serious problem affecting people who working in human services, particularly healthcare workers. This study aimed to: Determine the frequency of burnout syndrome and related factors among Salahaddin resident physicians. Subject and Method: A cross-sectional study , done from 11th of November 2021 to 15th of March 2022. A convenient sample of 100 resident and permanent doctors, working in Salahdin Public hospitals. Inclusion criteria were current residents doctor who had at least one year in a residency program. Data collected using interview questionnaire form based on the Maslach Burnout Inventory. Results: The 100 resident doctor information analyzed and found that 56(56%) , 44(44%) were male and female respectively. High frequency of the resident aged 26-30 years 68(68%), 75(75%) of them living in Salahdin, junior residents represent 52(52%) and 48(48%) were permanent resident. The high scores of occupational exhaustion was reported among 41(41%). The high scores of depersonalization / loss of empathy was reported among 42(42%). The low scores of personal accomplishment assessment scores was reported among 64(64%). Females 21(47.7%) had more occupational exhaustion than male doctors 20(35.7%). high score of depersonalization / loss of empathy reported among 22(39.3%) of the male and 20(45.5%) of the females. Conclusion: burnout frequency was high among Iraqi residents with high scores of occupational exhaustion, and depersonalization/ loss of empathy, and high percentage of low scores of personal accomplishment assessment.

Identification of a PANoptosis-related prognostic model in triple-negative breast cancer, from risk assessment, immunotherapy, to personalized treatment

BackgroundTriple-negative breast cancer is a breast cancer subtype characterized by its challenging prognosis, and establishing prognostic models aids its clinical treatment. PANoptosis, a recently identified type of programmed cell death, influences tumor growth and patient outcomes. Nonetheless, the precise impact of PANoptosis-related genes on the prognosis of triple-negative breast cancer has yet to be determined. MethodsClinical information for the triple-negative breast cancer samples was collected from the Gene Expression Omnibus and The Cancer Genome Atlas databases, while 19 PANoptosis-related genes were sourced from previous studies. We first categorized PANoptosis-related subtypes and determined the differentially expressed genes between them. Subsequently, we developed and validated a PANoptosis-associated predictive model using LASSO and Cox multivariate regression analyses. Statistical evaluations were conducted using R software, and the mRNA expression levels of the genes were quantified using real-time PCR. ResultsUsing consensus clustering analysis, we divided triple-negative breast cancer patients into two clusters based on PANoptosis-related genes and identified 1054 differentially expressed genes between these clusters. Prognostic-related genes were subsequently selected to re-cluster patients, validating their predictive ability. A prognostic model was then constructed based on four genes: BTN2A2, CACNA1H, PIGR, and S100B. The expression and enriched cell types of these genes were examined and the expression levels were validated in vitro. Furthermore, the model was validated, and a nomogram was created to enhance personalized risk assessment. The risk score, proven to be an independent prognostic indicator for triple-negative breast cancer, showed a positive correlation with both age and disease stage. Immune infiltration and drug sensitivity analyses suggested appropriate therapies for different risk groups. Mutation profiles and pathway enrichment were analyzed, providing insights into potential therapeutic targets. ConclusionA PANoptosis-related prognostic model was successfully developed for triple-negative breast cancer, offering a novel approach for predicting patient prognosis and guiding treatment strategies.

Unscheduled Returns of Older Patients to the Emergency Department of an Irish Teaching Hospital in the Final Quarter of 2023

Abstract Background Rapid unscheduled returns to emergency departments (ED) are considered to be an indication of a potential lack of quality of care of an ED as outlined in the academic literature. Our ED multidisciplinary team (MDT) dedicated to the assessment and treatment of older persons is a relatively new one. In order to evaluate our efficacy, we sought to compare our rate of unscheduled returns with international norms. Methods Retrospective audit of 883 patients from October 2023 to January 2024. Our ED software programme which holds the patient histories was reviewed to establish whether the patients came back to the ED, if so, how quickly, and for what reason. The results were collated and reviewed. Results Average age: 81. Average Clinical Frailty Scale Score (CFS): 5. 69% of older patients assessed by the MDT did not return to our ED. 3% returned within 72hrs. 2% returned within one week. 9% returned within one month. 13% returned within 3 months. 2% returned within 6 months. Conclusion In numerous academic articles, the 72hr unscheduled return should not exceed 3-5%. While we would always seek to reduce the rate of unscheduled returns to our ED, the results show that our 72hr return percentage is within international norms. This is despite the age profile and frailty of the patients assessed, treated and reviewed.

What do women want to see in a personalized breast cancer risk report? A qualitative study of Asian women of two countries.

A breast cancer risk assessment tool for Asian populations, incorporating Polygenic Risk Score and Gail Model algorithm, has been established and validated. However, effective methods for delivering personalized risk information remain underexplored. This study aims to identify and develop effective methods for conveying breast cancer risk information to Asian women. Through ten focus group discussions with 32 women in Indonesia and Singapore, we explored preferences for the presentation of risk information. Participants favored comprehensive reports featuring actionable steps, simplified language, non-intimidating visuals, and personalized risk reduction recommendations. Singaporean participants, more aware of breast cancer prevention, showed a lower likelihood of seeking follow-ups upon receiving low-risk results compared to Indonesians. Overall, participants found the reports useful and advocated for similar approaches in other disease assessments. Balancing content and complexity in reports is crucial, highlighting the need for improved patient understanding and engagement with healthcare providers. Future studies could explore physicians' roles in delivering personalized risk assessments for breast cancer prevention.

Low-Density Lipoprotein Cholesterol Gymnastics: Exploring the Advantages and Limitations of the Friedewald, Martin-Hopkins, and Sampson Equations for Personalized Lipid Management.

The most commonly used method for low-density lipoprotein cholesterol (LDL-C) estimation is the Friedewald equation, which has notable limitations. However, more accurate methods have been proposed. This study investigates the advantages and limitations of these methods and identifies the contexts in which each equation is the most or least applicable. A cohort of 222 individuals underwent a standard lipid profile assessment, including directly measuring their LDL-C (dLDL-C). LDL-C was also estimated using the Friedewald, Martin-Hopkins, and Sampson equations. The differences (%Delta) between the estimated and measured LDL-C were analyzed in relation to dLDL-C, high-density lipoprotein cholesterol (HDL-C), and triglyceride levels. The %Delta was significantly lower (p < 0.0001) for the Martin-Hopkins (-8.8 ± 9.8) and Sampson (-9.5 ± 9.2) equations compared to Friedewald (-12.2 ± 9.2). All equations increasingly underestimated LDL-C as the dLDL-C levels decreased. The %Delta of the Martin-Hopkins equation showed significant positive correlations with dLDL-C (≤130 mg/dL) and triglycerides and a significant negative correlation with HDL-C. In a subgroup of 30 individuals with extreme %Delta values, patterns of gross underestimation were observed, particularly when low LDL-C, low triglycerides, and high HDL-C coincided. The Martin-Hopkins equation is a superior method for LDL-C estimation and a valuable tool in precision medicine. However, clinicians and laboratory professionals must be aware of its limitations and recognize patterns that could lead to significant LDL-C underestimation. We propose an algorithm for clinical laboratories to provide personalized LDL-C assessments.

Older adults’ perceptions and behaviors on driving: A mixed method study

Understanding older adults' driving behavior based on their personal assessment, along with challenges they encounter when driving will support community leaders and policymakers to develop effective supportive strategies for their safety on the road. This study uses a mixed methodology approach, including a survey and an interview to examine older drivers' perceptions and concerns regarding their driving habits. Collecting data from cities in Texas and Nevada, to achieve diverse perspectives on older adults who live in environments with different land use patterns and road geometry.Using the survey to understand the older adults' self-evaluated driving skills, where most consider themselves very good drivers even though they have some challenges, based on the roads, their reflexes changing over the years, and the impact of their physical and cognitive health. Supplementing the survey results with the interview allows the study to identify older drivers' major challenges including adverse weather, construction sites, and in-vehicle distractions. Supporting that visual and cognitive challenges are limiting older adults’ driving patterns (e.g., not driving at night).To avoid any conflicts with aggressive drivers, the older adults are passively driving, and if accessible, utilizing in-vehicle technologies to increase their safety. However, older drivers suggested that all drivers, particularly younger drivers, should have access to more educational materials. They recommended that older adults' licensing requirements should be evaluated based on their health condition rather than age. Participants’ concern regarding roadway infrastructure elements and driver behavior can be resolved through improvements in road design and driver education.

Automotive Consumer Loans Risk Assessment Predictive Modeling Using Generative Adversarial Network and Stacked Autoencoder Neural Networks

In this study, we propose a predictive model for automotive consumer loans risk assessment, leveraging Generative Adversarial Networks (GANs) and Stacked Autoencoder Neural Networks (SAEs). We address issues of high dimensionality and sparsity inherent in big data environments and tackle the class imbalance problem using GANs. Feature selection is effectively carried out using SAEs. Experimental results prove the superiority of our approach over traditional neural networks and our model without GANs or SAEs. The proposed model shows significant potential for application in personal credit risk assessment within automotive finance and beyond. Future work is aimed at extending and improving our model and applying it to other domains.

A Behavior-Based Model to Validate Electronic Systems Designed to Collect Patient-Reported Outcomes: Model Development and Application.

The merits of technology have been adopted in capturing patient-reported outcomes (PROs) by incorporating PROs into electronic systems. Following the development of an electronic system, evaluation of system performance is crucial to ensuring the collection of meaningful data. In contemporary PRO literature, electronic system validation is overlooked, and evidence on validation methods is lacking. This study aims to introduce a generalized concept to guide electronic patient-reported outcome (ePRO) providers in planning for system-specific validation methods. Since electronic systems are essentially products of software engineering endeavors, electronic systems used to collect PRO should be viewed from a computer science perspective with consideration to the health care environment. On this basis, a testing model was blueprinted and applied to a newly developed ePRO system designed for clinical use in pediatric dentistry (electronic Personal Assessment Questionnaire-Paediatric Dentistry) to investigate its thoroughness. A behavior-based model of ePRO system validation was developed based on the principles of user acceptance testing and patient-centered care. The model allows systematic inspection of system specifications and identification of technical errors through simulated positive and negative usage pathways in open and closed environments. The model was able to detect 15 positive errors with 1 unfavorable response when applied to electronic Personal Assessment Questionnaire-Paediatric Dentistry system testing. The application of the behavior-based model to a newly developed ePRO system showed a high ability for technical error detection in a systematic fashion. The proposed model will increase confidence in the validity of ePRO systems as data collection tools in future research and clinical practice.