Personal Risk Profile Research Articles

A second space age spanning omics, platforms and medicine across orbits.

The recent acceleration of commercial, private and multi-national spaceflight has created an unprecedented level of activity in low Earth orbit, concomitant with the largest-ever number of crewed missions entering space and preparations for exploration-class (lasting longer than one year) missions. Such rapid advancement into space from many new companies, countries and space-related entities has enabled a 'second space age'. This era is also poised to leverage, for the first time, modern tools and methods of molecular biology and precision medicine, thus enabling precision aerospace medicine for the crews. The applications of these biomedical technologies and algorithms are diverse, and encompass multi-omic, single-cell and spatial biology tools to investigate human and microbial responses to spaceflight. Additionally, they extend to the development of new imaging techniques, real-time cognitive assessments, physiological monitoring and personalized risk profiles tailored for astronauts. Furthermore, these technologies enable advancements in pharmacogenomics, as well as the identification of novel spaceflight biomarkers and the development of corresponding countermeasures. In this Perspective, we highlight some of the recent biomedical research from the National Aeronautics and Space Administration, Japan Aerospace Exploration Agency, European Space Agency and other space agencies, and detail the entrance of the commercial spaceflight sector (including SpaceX, Blue Origin, Axiom and Sierra Space) into aerospace medicine and space biology, the first aerospace medicine biobank, and various upcoming missions that will utilize these tools to ensure a permanent human presence beyond low Earth orbit, venturing out to other planets and moons.

Distinct personality profiles associated with disease risk and diagnostic status in eating disorders

BackgroundPersonality traits have been associated with eating disorders (EDs) and comorbidities. However, it is unclear which personality profiles are premorbid risk rather than diagnostic markers. MethodsWe explored associations between personality and ED-related mental health symptoms using canonical correlation analyses. We investigated personality risk profiles in a longitudinal sample, associating personality at age 14 with onset of mental health symptoms at ages 16 or 19. Diagnostic markers were identified in a sample of young adults with anorexia nervosa (AN, n = 58) or bulimia nervosa (BN, n = 63) and healthy controls (n = 47). ResultsTwo significant premorbid risk profiles were identified, successively explaining 7.93 % and 5.60 % of shared variance (Rc2). The first combined neuroticism (canonical loading, rs = 0.68), openness (rs = 0.32), impulsivity (rs = 0.29), and conscientiousness (rs = 0.27), with future onset of anxiety symptoms (rs = 0.87) and dieting (rs = 0.58). The other, combined lower agreeableness (rs = −0.60) and lower anxiety sensitivity (rs = −0.47), with future deliberate self-harm (rs = 0.76) and purging (rs = 0.55). Personality profiles associated with “core psychopathology” in both AN (Rc2 = 80.56 %) and BN diagnoses (Rc2 = 64.38 %) comprised hopelessness (rs = 0.95, 0.87) and neuroticism (rs = 0.93, 0.94). For BN, this profile also included impulsivity (rs = 0.60). Additionally, extraversion (rs = 0.41) was associated with lower depressive risk in BN. LimitationsThe samples were not ethnically diverse. The clinical cohort included only females. There was non-random attrition in the longitudinal sample. ConclusionsThe results suggest neuroticism and impulsivity as risk and diagnostic markers for EDs, with neuroticism and hopelessness as shared diagnostic markers. They may inform the design of more personalised prevention and intervention strategies.

Machine learning models for predicting early hemorrhage progression in traumatic brain injury.

This study explores the progression of intracerebral hemorrhage (ICH) in patients with mild to moderate traumatic brain injury (TBI). It aims to predict the risk of ICH progression using initial CT scans and identify clinical factors associated with this progression. A retrospective analysis of TBI patients between January 2010 and December 2021 was performed, focusing on initial CT evaluations and demographic, comorbid, and medical history data. ICH was categorized into intraparenchymal hemorrhage (IPH), petechial hemorrhage (PH), and subarachnoid hemorrhage (SAH). Within our study cohort, we identified a 22.2% progression rate of ICH among 650 TBI patients. The Random Forest algorithm identified variables such as petechial hemorrhage (PH) and countercoup injury as significant predictors of ICH progression. The XGBoost algorithm, incorporating key variables identified through SHAP values, demonstrated robust performance, achieving an AUC of 0.9. Additionally, an individual risk assessment diagram, utilizing significant SHAP values, visually represented the impact of each variable on the risk of ICH progression, providing personalized risk profiles. This approach, highlighted by an AUC of 0.913, underscores the model's precision in predicting ICH progression, marking a significant step towards enhancing TBI patient management through early identification of ICH progression risks.

Endurant Stent Graft for Treatment of Abdominal Aortic Aneurysm Inside and Outside of the Instructions for Use for the Proximal Neck: A 14-Year, Single-Center Experience.

Aim: To assess the medium and long-term performance of the Endurant stent graft in a cohort of consecutive patients treated with this device for an abdominal aortic aneurysm (AAA) both inside and outside of the instructions for use (IFU) and to find factors influencing the outcomes. Methods: Our observational, retrospective, single-center study included all patients who consecutively underwent endovascular aneurysm repair with the Endurant stent graft from February 2009 to January 2023. Patients with an AAA to treat according to current guidelines were included. Patients were divided into two groups: Group 1 inside of the IFUs and Group 2 outside of the IFUs for the proximal aortic neck. Patients were followed up after the procedure with computed angiography tomography, ultrasound examination, and interviews. Aneurysm-related mortality, procedure-related reinterventions, and type IA and III endoleaks were considered primary endpoints. Secondary endpoints included aneurysmal sac variations and graft thrombosis. Results: A total of 795 patients were included, 650 in Group 1 and 145 in Group 2; 732 were males, and the mean age was 74 ± 8. Anamnestic baseline did not differ between the two groups. Neck length, width, and angulation were different between the two groups (all p < 0.001). A total of 40 patients had a ruptured AAA, while 56 were symptomatic. At a mean follow-up of 43 ± 39 months, aneurysm-related mortality was less than 1%, and 82 endoleak (10.5%) were observed. Overall endoleak rate and type 1A endoleak, as well as procedure-related reintervention, were significantly more frequent in Group 2. Sac regression of at least 5 mm was observed in 65.9% of cases. AAAs larger than 60.5 mm carried a higher risk of endoleak (HR: 1.025; 95% CI: 1.013-1.37; p < 0.001) and proximal necks shorter than 13.5 mm carried a higher type 1A risk (HR: 0.890; 95% CI: 0.836-0.948; p < 0.001). Patients without chronic obstructive pulmonary disease and taking lipid-lowering drugs had an overall more consistent sac-shrinking rate. Conclusions: The Endurant stent graft proves safe and reliable. Out-of-IFU treatment has poorer medium and long-term outcomes. Some conditions influence medium and long-term reintervention risk and sac behavior. Patients with bigger aneurysms, proximal necks shorter than 13.5 mm, and chronic obstructive pulmonary disease should be more carefully evaluated during follow-up. Consistent follow-up is in keeping low aneurysm-related mortality. Personalized risk profiles and peri and postoperative management strategies are needed.

How Consideration of Future Consequences, Prior Gain or Loss, Personal Risk Profile, and Justification Affect Risk–Payoff Preferences

This study examines (1) how risk–payoff preference can be affected by differences in consideration of future consequences (CFC), prior gain/loss, and personal risk profile, and (2) whether one’s risk–payoff preference may vary with justification prompts. Using an experimental design with 366 undergraduate business students, participants are tasked to make risk–payoff choices in two scenarios, with the combined risk–payoff outcomes serving as the dependent variable. In addition, participants are assessed on their personal risk profiles and also complete the 14-item CFC scale to gauge the propensity to take into account future consequences of their behaviors. Findings show that one who scores low (high) in CFC will prefer lower (higher) risk and payoff. Further, for an individual who scores high in CFC and has a prior gain (loss), he/she will be more inclined to prefer lower (higher) risk and payoff, though this effect is moderated by one’s risk profile. Finally, justification prompts help to reduce one’s propensity toward high risk–payoff, irrespective of prior gain/loss and risk profile considerations. With regard to consumers’ financial choices, particularly in a volatile economic environment, the findings here indicate that prompting for strategic justifications before making decisions can help lower one’s overall propensity toward high risk–payoff choices.

Tailoring community preventive care to personal health needs: a data-driven and participatory approach

A digital platform with tools for health promotion was developed as a proof of concept in co-creation with all relevant stakeholders involved: citizens, caregivers, and local policy makers, aiming to optimize community preventive care.&#x0D; The platform, referred to as BIBOPP, was developed as a proof of concept focusing on prevention and health promotion for citizens, local policy makers but also for primary care givers wanting to offer personalized follow up. To this end, we set up multiple co-creation sessions with different target groups of end users, including those with expected limited digital literacy skills, eg. older adults and people with no or low formal educational background. Based on this input, the functionalities of the tools were designed and developed and afterwards tested with a new group of end-users.&#x0D; The online prevention platform offered citizens from 5 Flemish municipalities a digital screening, allowing them to evaluate their health and lifestyle. This screening is the Domus Medica Health Guide (GGDM), an evidence-based tool predicting personal risk for chronic diseases. The outcome of the screening is linked to the electronic medical health record hosted by the general practitioner, notifying the latter in case of excessive risk and involving him in the process of disease prevention and health promotion.&#x0D; Based on the personalized lifestyle advice resulting from the survey responses, end users then received an overview of activities and primary care providers in their community, tailored to their personal risk profile and preferences.&#x0D; The data collected with consent from the end users, yielded insights on the self-reported lifestyle and health of these participants. On an aggregated level, this tool has the potential to provide data for population health management.&#x0D; First lessons learned indicate that the platform did require significant digital literacy skills from end-users, as indicated by the participants younger age and relatively healthy lifestyle (eg. less than 10% smokers, +50% daily physical activity, …). However, in a co-creation session group with older adults, they indicated that digital skills were not a threshold when peer support was available. Furthermore, they recognized that the tool helped them in the self-management of their health and that they trusted the data governance. People with low to no formal educational background on the other hand were more suspicious about the tool and data governance unless this was offered to them through their trusted care providers. Also, older adults indicated that support with the interpretation of the advices by a health professional could be of added value.&#x0D; Next steps for BIBOPP now are involving these health professionals, and more specifically primary care actors in onboarding and guiding people to and through the platform.&#x0D; To conclude, this data-driven proof of concept co-designed with end-users, has promise to deliver personalized services, strengthen community preventive care, and optimize the local health policy.&#x0D; &#x0D;

Does informing people about modifiable dementia risk factors lead to improved behavioral risk profiles?

AbstractBackgroundThe Island Study Linking Ageing and Neurodegenerative Disease (ISLAND) is a large, online, prospective public health cohort study with nested interventions targeting modifiable dementia risk. The objective of ISLAND is to investigate the effectiveness of public health strategies aimed at increasing knowledge about behavioral and lifestyle factors associated with dementia, and to encourage behavior change to reduce future risk profiles at individual and population level.MethodCommencing October 2019, Tasmanian residents aged 50 and over were invited via a rolling media campaign to join ISLAND. Online surveys administered at baseline were repeated annually to enable tracking of changes in physical and mental health, social functioning, dementia risk knowledge, motivations and behaviors. After each survey wave, participants were provided a personal Dementia Risk Profile (DRP), a traffic‐light style report of their own risk level against nine domains, together with WHO recommendations for achieving ‘low risk’ status. For analyses, the DRP provides individual domain scores and a cumulative risk score, computed by summing domain scores (low = 0, medium = 0.5, high = 1). Newsletters and study information included prompts for participants to join the PD‐MOOC, a free, 4‐week online course about preventing dementia, which runs three times each year.ResultParticipants who provided full data at baseline and the October 2021 annual surveys (n = 2,935) reported a significant and moderate‐sized reduction in their cumulative DRP scores (βs = ‐.36 [95%CI ‐.40, ‐.31]. Within this sample, the participants who engaged with the PD‐MOOC (1,208, 42%) reported a small additional independent benefit (βs = ‐.08 [95%CI‐.11, ‐.05]). General knowledge about dementia risk reduction increased across all respondents (βs = .11 [95%CI .06, .15]) and amongst PD‐MOOC participants, the effect was stronger (βs = .61 [95%CI .53, .70]). The results of mediation models testing the role of knowledge and motivations in observed DRP changes will be presented.ConclusionThese preliminary findings support the core hypothesis of ISLAND, that increasing knowledge about modifiable dementia risk factors is associated with action‐taking to change key risk behaviors. Future work will link dementia‐risk knowledge and behavioral patterns over time with cognitive and blood‐based markers of neurodegeneration, to understand the long‐term effects of this online public health project.

Cross-sectional survey of attitudes and beliefs towards dementia risk reduction among Australian older adults

BackgroundLittle is known about what drives older adults’ motivation to change their behaviour and whether that is associated with their personal dementia risk profile. Our aims were to (i) understand what sociodemographic factors are associated with older Australians’ motivation to change behaviour to reduce their dementia risk, and (ii) explore the relationship between socio-demographic factors and motivation to reduce dementia risk with health- and lifestyle-based dementia risk scores in older adults.MethodsA cross-sectional online postal or telephone survey was administered to community-dwelling older adults in New South Wales, Australia between January and March 2021. Measures included socioeconomic status, locality, and health status, the Motivation to Change Lifestyle and Health Behaviours for Dementia Risk Reduction (MCLHB-DRR) scale and the lifestyle-based dementia risk score (LIBRA index). Multiple linear regression analyses were used to explore the associations for (i) sociodemographic factors and motivation to reduce dementia risk (MCLHB-DRR scales) and (ii) sociodemographic factors and motivation to reduce dementia risk with health- and lifestyle-based dementia risk (LIBRA index).ResultsA total of 857 older adults (mean age 73.3 years, SD = 6.0, range 65–94; 70% women; 34.6% less than grade 6 education) completed the survey. Respondents reported high levels of motivation to adopt behaviour changes, agreeing on the importance of good health. Individuals who were younger were more likely to have greater motivation to modify lifestyle to reduce dementia risk and had higher perceived benefits to gain by adopting a healthy lifestyle. Dementia risk scores were moderately low (mean LIBRA index =− 2.8 [SD = 2.0], range − 5.9–3.8), indicating relatively moderate-to-good brain health. Men with low socioeconomic status and higher perceived barriers to lifestyle change had higher dementia risk scores.ConclusionsPublic health campaigns need to overcome motivational barriers to support reductions in dementia risk. A multifaceted and inclusive approach targeting both sociodemographic differences and impediments to brain healthy lifestyles is required to achieve genuine change.Trial registrationACTRN12621000165886, Date of registration: 17/02/2021.

Introducing and Evaluating an Architectural Model for Smart Tourism Health Insurance based on IoT and Cloud

Introduction: Tourism as one of the programs to earn money leads to economic growth; however, due to the non -providing of medical and health services by insurance organizations, the Iranian tourism industry has faced a recession. Therefore, this study aimed to provide a smart tourism health insurance architecture in the context of the Internet of Things (IoT) and cloud to serve tourists. Method : This practical study was conducted to achieve a smart tourism health insurance architecture. First, its requirements were determined by reviewing the related literature and open interview with four experts from Iran Insurance Corporation. Then, by examining different types of tourism health insurance architectural models, a proposed service -oriented layered architecture was presented on the platform of IoT and cloud. Finally, the proposed architecture was evaluated by the ATAM method . Results: The proposed architecture has two components (i.e., the requester and the service provider) with user, network, cloud, and database layers that are connected in a service - oriented manner. Also, the evaluation of the proposed architecture by the ATAM method showed that it can respond to the health needs of tourists. Conclusion: This architecture is presented on the platform of IoT and cloud that provides an intelligent background, and by recording people's data in personal risk profiles, it facilitates providing special tariffs and reducing tourism costs. Therefore, tourists will be able to travel with more confidence in controlling their health status.

Cardiovascular and psychosocial risks among patients below age 50 with acute myocardial infarction

BackgroundDespite improvements in the treatment and prevention of cardiovascular disease since the 1960s, the incidence of cardiovascular diseases among young people has remained the same for many years. This study aimed to compare the clinical and psychosocial attributes of young persons affected by myocardial infarction under the age of 50 years compared to middle-aged myocardial infarction patients 51–65 years old.MethodsData from patients with a documented STEMI or NSTEMI elevated acute myocardial infarction in the age groups up to 65 years, were collected from cardiology clinics at three hospitals in southeast Sweden. The Stressheart study comprised a total of 213 acute myocardial infarction patients, of which n = 33 (15.5%) were under 50 years of age and n = 180 (84.5%) were middle-aged, (51–65 years). These acute myocardial infarction patients filled in a questionnaire at discharge from the hospital and further information through documentation of data in their medical records.ResultsBlood pressure was significantly higher in young compared to middle-aged patients. For diastolic blood pressure (p = 0.003), systolic blood pressure (p = 0.028), and mean arterial pressure (p = 0.005). Young AMI patients had a higher (p = 0.030) body mass index (BMI) than the middle-aged. Young AMI patients were reported to be more stressed (p = 0.042), had more frequently experienced a serious life event the previous year (p = 0.029), and felt less energetic (p = 0.044) than middle-aged AMI patients.ConclusionsThis study revealed that persons under the age of 50 affected by acute myocardial infarction exhibit traditional cardiovascular risk factors like high blood pressure, and higher BMI, and were more exposed to some psychosocial risk factors. The risk profile of young persons under age 50 affected by AMI was in these respects more exaugurated than for middle-aged persons with AMI. This study underlines the importance of the early discovery of those at increased risk and encourages preventative actions to focus on both clinical and psychosocial risk factors.

European Cancer Summit 2022 submission for Digital Health NetworkThe Survivorship Passport: a digital tool for better and homogeneous long-term care for childhood cancer survivors

BackgroundMany childhood and adolescent cancer survivors (CCS) and their healthcare professionals lack information about possible late effects, personal risk profiles and the need of long-term follow-up care. Most have poor or no access to their clinical and treatment data as well as to a survivorship care plan. The Survivorship Passport (SurPass) is an innovative, digital tool, developed by the PanCare community in previous and on-going EU-funded projects (ENCCA, ExPO-r-Net, PanCareSurFup, PanCareFollowUp, PanCareSurPass), that can be used to overcome these gaps and improve people-centered long-term follow-up care. MethodsAim of the SurPass and of the PanCare community is to improve the quality of life and health status of CCS and to address their potential needs through the development of successively improving versions and functionalities of the platform. The SurPass provides an electronical and paper-based summary of a CCS´s clinical history, with detailed information about diagnosis and treatment, coupled with personalized follow-up and screening recommendations based on evidence-based guidelines published by the International Guidelines Harmonization Group (IGHG) and the PanCare Guidelines Group. Algorithms built into the platform allow the creation of an individualized care plan. ResultsThis endeavor started in 2011 when the prototype of the SurPass platform was developed (ENCCA) and integrated the first set of IGHG follow-up recommendations. SurPass was further improved (v1.1) by multi-language translation (ExPO-r-Net), and with a complete set of organ-specific recommendations alongside further new IGHG and PanCare guidelines (PanCareFollowUp v1.2). SurPass v2.0 is currently implemented and spread over several centers in six European countries (PanCareSurPass) whilst testing the interoperability between institutional electronic medical records and the SurPass platform. Similar to Europe's vision of a ‘Cancer Survivor Smart Card’, the SurPass tool was developed as a ‘resource’ function to link the individual treatment history to best surveillance and individual follow-up care recommendations for CCS. ConclusionsSurPass can be considered a proof of concept of the clinical-history and personalized-care modules sought under the EU-announced Cancer Survivor Smart Card initiative. Within the newly funded smartCARE project coordinated by ECO, we will share the experiences of the PanCare community with SurPass and international guideline development in survivorship since 2011.

Evaluation of Lung Cancer Risk Among Persons Undergoing Screening or Guideline-Concordant Monitoring of Lung Nodules in the Mississippi Delta

Guideline-concordant management of lung nodules promotes early lung cancer diagnosis, but the lung cancer risk profile of persons with incidentally detected lung nodules differs from that of screening-eligible persons. To compare lung cancer diagnosis hazard between participants receiving low-dose computed tomography screening (LDCT cohort) and those in a lung nodule program (LNP cohort). This prospective cohort study included LDCT vs LNP enrollees from January 1, 2015, to December 31, 2021, who were seen in a community health care system. Participants were prospectively identified, data were abstracted from clinical records, and survival was updated at 6-month intervals. The LDCT cohort was stratified by Lung CT Screening Reporting and Data System as having no potentially malignant lesions (Lung-RADS 1-2 cohort) vs those with potentially malignant lesions (Lung-RADS 3-4 cohort), and the LNP cohort was stratified by smoking history into screening-eligible vs screening-ineligible groups. Participants with prior lung cancer, younger than 50 years or older than 80 years, and lacking a baseline Lung-RADS score (LDCT cohort only) were excluded. Participants were followed up to January 1, 2022. Comparative cumulative rates of lung cancer diagnosis and patient, nodule, and lung cancer characteristics between programs, using LDCT as a reference. There were 6684 participants in the LDCT cohort (mean [SD] age, 65.05 [6.11] years; 3375 men [50.49%]; 5774 [86.39%] in the Lung-RADS 1-2 and 910 [13.61%] in the Lung-RADS 3-4 cohorts) and 12 645 in the LNP cohort (mean [SD] age, 65.42 [8.33] years; 6856 women [54.22%]; 2497 [19.75%] screening eligible and 10 148 [80.25%] screening ineligible). Black participants constituted 1244 (18.61%) of the LDCT cohort, 492 (19.70%) of the screening-eligible LNP cohort, and 2914 (28.72%) of the screening-ineligible LNP cohort (P < .001). The median lesion size was 4 (IQR, 2-6) mm for the LDCT cohort (3 [IQR, 2-4] mm for Lung-RADS 1-2 and 9 [IQR, 6-15] mm for Lung-RADS 3-4 cohorts), 9 (IQR, 6-16) mm for the screening-eligible LNP cohort, and 7 (IQR, 5-11) mm for the screening-ineligible LNP cohort. In the LDCT cohort, lung cancer was diagnosed in 80 participants (1.44%) in the Lung-RADS 1-2 cohort and 162 (17.80%) in the Lung-RADS 3-4 cohort; in the LNP cohort, it was diagnosed in 531 (21.27%) in the screening-eligible cohort and 447 (4.40%) in the screening-ineligible cohort. Compared with Lung-RADS 1-2, the fully adjusted hazard ratios (aHRs) were 16.2 (95% CI, 12.7-20.6) for the screening-eligible cohort and 3.8 (95% CI, 3.0-5.0) for the screening-ineligible cohort; compared with Lung-RADS 3-4, the aHRs were 1.2 (95% CI, 1.0-1.5) and 0.3 (95% CI, 0.2-0.4), respectively. The stage of lung cancer was I to II in 156 of 242 patients (64.46%) in the LDCT cohort, 276 of 531 (52.00%) in the screening-eligible LNP cohort, and 253 of 447 (56.60%) in the screening-ineligible LNP cohort. In this cohort study, the cumulative lung cancer diagnosis hazard of screening-age persons enrolled in the LNP was higher than that in a screening cohort, irrespective of smoking history. The LNP provided access to early detection for a higher proportion of Black persons.

Interpretable Predictive Modeling for Major Adverse Cardiac Events Following Lung Cancer Radiotherapy

<h3>Purpose/Objective(s)</h3> Patients with locally advanced non-small cell lung cancer (NSCLC) are at increased risk of developing major adverse cardiac events (MACE) following radiotherapy. Our group previously identified cardiac substructure dose constraints associated with increased risk of MACE. We employ a machine learning (ML) approach to further identify predictors of MACE and evaluate ML capacity for personalized MACE risk-stratification. <h3>Materials/Methods</h3> Retrospective analysis of 701 patients with locally advanced NSCLC treated with thoracic radiotherapy between 2003-2014. MACE included unstable angina, heart failure, myocardial infarction, coronary revascularization, and cardiac death. We used extreme gradient boosting for MACE prediction. Input features included 195 demographic and 240 radiation dose and/or anatomic. Cardiac substructures were manually delineated; heart and chamber volumes were indexed to body surface area (BSA). We split data 70/30 into training/testing, balanced by MACE. Hyperparameters were bootstrap-tuned with 50-round grid search. Area under the receiver operator characteristic curve (AUC) evaluated model performance. We trained our model on any MACE regardless of timeframe and tested performance at varying timepoints (90-day, 180-day, etc.). Shapley values measured feature importance and were used to construct personalized risk profiles for each patient. <h3>Results</h3> Among 701 patients, 70 developed ≥1 MACE. The median age was 65 and median time to first MACE was 20.6 months. Training AUC for any MACE: 0.67; testing AUC: 0.73. Our model displayed time dependent performance improvement, with high accuracy for MACE closer to radiation start. Testing AUC for 90-day MACE: 0.97; 180-day MACE: 0.94. Table 1 displays additional AUCs. The top 10 predictive features for MACE were coronary heart disease history, right atrial volume, left circumflex coronary artery (CA) volume (V) receiving 15 Gy (V15Gy), heart volume, lung V55Gy and V70Gy, hypertension, left ventricle V15Gy, left main CA volume, and left anterior descending CA V15Gy. Based on patients' Shapley-derived risk profile, radiation dose variables generally became less predictive of MACE as time from radiation increased, while demographics remained generally predictive. <h3>Conclusion</h3> ML modeling enabled high precision for predicting short-term MACE in locally advanced NSCLC patients who received radiotherapy, though long-term MACE was less accurate. ML techniques show promise for identifying patients at high risk of short-term MACE. Our Shapley-derived individual risk profiles may assist with baseline cardiac risk assessment and identify opportunities for risk mitigation. Prospective validation may help implement these tools into clinical practice.

A Robust Environment-Aware Driver Profiling Framework Using Ensemble Supervised Learning

Driver profiling is the real-time process of detecting driving behaviors and computing a driver’s expected risk based on detected behaviors. Predicting risk based solely on the inclusion of detected behaviors may not be accurate because this method of predicting ignores the environmental (e.g., weather conditions, traffic density level) context of detected behaviors. Moreover, coupling detected behaviors with their environmental context can be leveraged towards creating personalized risk profiles for drivers in each driving environment. These profiles can be utilized in various ITS applications including personalized safety-based route planning. In this paper, a novel driver profiling environment-aware framework is presented. In the proposed framework, data processing is distributed over three computational layers to enhance the overall reliability of the system. A risk prediction model is hosted on the edge/fog to determine the driving risk while considering the joint effect of the in-vehicle detected behaviors and their environmental context. Risk values along with a driver’s compliance to warnings are both utilized to compute the risk profile on the cloud. Using SHRP2 Naturalistic Driving (ND) dataset, the development of a novel risk prediction model is presented herein with the underlying sub-processes of data preprocessing, error analysis, and model selection. Then we analyze both the performance of the developed risk prediction model and the overall performance of the proposed system. Validation results for the developed model indicate a good compromise between bias and variance. Moreover, the results of the overall risk scoring model reflect its robustness and reliability in assigning accurate risk scores.

Gestational diabetes screening from the perspective of consumers: Insights from early in the COVID-19 pandemic and opportunities to optimise experiences.

Consumer perspectives are a cornerstone of value-based healthcare. Screening and diagnosis of gestational diabetes mellitus (GDM) were among many of the rapid changes to health care recommended during the COVID-19 pandemic. The changes provided a unique opportunity to add information about women's perspectives on the debate on GDM screening. The aim of this qualitative study was to explore women's perspectives and understanding of GDM screening and diagnosis comparing the modified COVID-19 recommendations to standard GDM screening and diagnostic practices. Women who had experienced both the standard and modified GDM screening and diagnostic processes were recruited for telephone interviews. Data analysis used inductive reflexive thematic analysis. Online surveys were disseminated to any registrant not included in interviews to provide an opportunity for all interested participants to provide their perspective. Twenty-nine telephone interviews were conducted and 19 survey responses were received. Seven themes were determined: (1) information provision from clinicians; (2) acceptability of GDM screening; (3) individualisation of GDM screening methods; (4) safety nets to avoid a missed diagnosis; (5) informed decision making; (6) women want information and evidence; and (7) preferred GDM screening methods for the future. Overall, women preferred the modified GDM screening recommendations put in place due to the COVID-19 pandemic. However, their preference was influenced by their prior screening experience and perception of personal risk profile. Women expressed a strong need for clear communication from health professionals and the opportunity to be active participants in decision making.

Development of machine learning models for mortality risk prediction after cardiac surgery.

We developed machine learning models that combine preoperative and intraoperative risk factors to predict mortality after cardiac surgery. Machine learning involving random forest, neural network, support vector machine, and gradient boosting machine was developed and compared with the risk scores of EuroSCORE I and II, Society of Thoracic Surgeons (STS), as well as a logistic regression model. Clinical data were collected from patients undergoing adult cardiac surgery at the First Medical Centre of Chinese PLA General Hospital between December 2008 and December 2017. The primary outcome was post-operative mortality. Model performance was estimated using several metrics, including sensitivity, specificity, accuracy, and area under the receiver operating characteristic curve (AUC). The visualization algorithm was implemented using Shapley's additive explanations. A total of 5,443 patients were enrolled during the study period. The mean EuroSCORE II score was 3.7%, and the actual in-hospital mortality rate was 2.7%. For predicting operative mortality after cardiac surgery, the AUC scores were 0.87, 0.79, 0.81, and 0.82 for random forest, neural network, support vector machine, and gradient boosting machine, compared with 0.70, 0.73, 0.71, and 0.74 for EuroSCORE I and II, STS, and logistic regression model. Shapley's additive explanations analysis of random forest yielded the top-20 predictors and individual-level explanations for each prediction. Machine learning models based on available clinical data may be superior to clinical scoring tools in predicting postoperative mortality in patients following cardiac surgery. Explanatory models show the potential to provide personalized risk profiles for individuals by accounting for the contribution of influencing factors. Additional prospective multicenter studies are warranted to confirm the clinical benefit of these machine learning-driven models.

Exploring Uniformity of Clinical Judgment: A Vignette Approach to Understanding Healthcare Professionals' Suicide Risk Assessment Practices.

Suicide risk assessment often requires health professionals to consider a complex interplay of multiple factors, with a significant reliance on judgment, which can be influenced by factors such as education and experience. Our study aimed at assessing the uniformity of decision making around suicide risk within healthcare professionals. We used a factorial survey approach to gather information on healthcare professionals' demographics, clinical experience, and their decision on 3 vignettes of patients with suicidal ideation. We used Kruskal-Wallis tests for determining if there were significant differences between groups for continuous variables and Spearman rank correlation for measuring the association between continuous variables. Content analysis was used for analyzing free-text comments. Responses were gathered from 79 healthcare professionals (nurses, nurse practitioners, physicians) who worked in primary care, mental health, or emergency department settings. Median suicide risk rates across all respondents were 90%, 50%, and 53% for vignettes 1, 2, and 3, respectively. Confidence in healthcare professionals' decisions was significantly associated with the clinical designation and personal risk profile of the healthcare professional in certain vignettes, with nurses and those willing to take more risks having a higher confidence in their decisions for vignettes 1 and 3, respectively. Treatment decision was significantly associated with mental health experience (i.e., those with lengthier mental health experiences were less likely to choose "admit to psychiatry ward" for vignette 2), clinical designation (i.e., nurses were more likely to "admit to psychiatry ward" for vignette 1), and practice setting. It should be noted that these associations were not consistent across all 3 vignettes, and results for each association were only specific to 1 of the 3 vignettes. Findings compare decision-making practices for suicide risk assessment across several types of healthcare professions over a range of practice settings, with the high-risk vignette showing the least variability. Insights from this study are relevant when building clinical decision support systems for suicide risk assessment. Designers should think about incorporating tailored messaging and alerts to health professionals' mental health experience and/or designation. Within our Canadian sample, there was considerable variability among healthcare professionals assessing the risk of suicide, with important implications for tailoring education and decision support.

A smart phone app for individual risk assessment for progression of diabetic retinopathy

AbstractPurposeCreation of a smart phone application containing diabetic retinopathy risk calculator to empower individual diabetic patients to understand their personal risk factors and risk profile. Educate and motivate patients to influence these risk factors.MethodsA previously validated and published diabetic retinopathy risk algorithm (Aspelund et al 2011; Lund et al 2016) was programmed as a smart phone application. Clinical data can be entered by hand or through the digi.me platform, which is available in an increasing number of countries for automatic transmission of clinical data.ResultsThe app is available at no cost in app stores and can be found under search word “retinarisk”. User numbers and responses will be reported.ConclusionsA smartphone app is now available at no cost for all diabetic patients. The app allows each patient to evaluate his/her personal risk for progression to sight threatening diabetic retinopathy. The app provides education about diabetic retinopathy and risk factors and motivates and informs the patient to modify and improve the risk profile. The app is a step in the direction to empower individual patients through validated interpretation of available clinical data: what these data mean for each individual, how the risk factors can be modified for risk reduction. It provides a personal prognosis for retinopathy progression.

Abstract- Poster

BACKGROUND (Current Scenario):Evidently, SARS-II due to COVID-19 is a problem increasing at a geometric progression affecting human civilization at large. Unfortunately there is no cure hence we are left to mercy of preventive and social medicine measures. These models of preventive and social medicine measures are dependent on available information.OBJECTIVE (Research Question):To assess the level of awareness about prevention of transmission of COVID-19 illness in community.Methodology:Cases were chosen by purposive sampling as per criteria. After screening and rating, assessment of the level of awareness about prevention of transmission of COVID-19 illness was done by structured questionnaire. The samples shall be collected from community around Burdwan Medical College and Hospital.Result: 1.Demographic characteristics(n=110) showed predominance of female subjects, mainly residing in urban area with majority educated upto higher secondary.2. Source of information was news paper, followed by news app and television.3. Majority were worried and had a close person who was affected by COVID.4.Absence of information was evident as in a scale with maximum score of 23 mean score was 15 and median 12.5.Conclusion:The accelerating rate of new case load of COVID-19 point to a gap in knowledge, attitude and practices. Hence, a deficit in knowledge is evident. Enhancement of public awareness of COVID appropriate behavior is needed for prevention of pandemic. Introduction:Death due to cardiovascular disease is one of the leading causes of mortality in persons with severe mental disorder. There is dearth of information on cardiovascular risk profile of persons with SMD.This study is done to examine the documentation of cardiovascular disease (CVD) risk profile among patients who had cardiac event during inpatient admission in a tertiary care centre.Methods:An audit of electronic medical records for documentation of CVD risk factors of smoking, alcohol use, obesity, elevated glucose levels, elevated blood pressure was done.Results:18 among 1260 in patients with Severe mental disorders had cardiac event during 2-year study period. Nearly half of them were smokers and had alcohol use disorder. Majority of them have diabetes and hypertension. There was no documentation of history of hyperlipidemia or family history of cardiometabolic risk factors in the medical records. Out of 18 who had cardiac event, 13 had elevated FBS, 10 had elevated BP, 10 had BMI>25, 9 had high HBA1C, 17 had deranged lipid profile when evaluated during hospital stay. Though some of the patients were on treatment for diabetes, hypertension and dyslipidemia, these parameters were deranged in most of them suggesting either poor compliance to medications or inadequate management.Conclusion:This study has shown that there are inadequacies in cardiovascular risk assessment and documentation in persons with severe mental disorders. Although the sample may not be representative of persons with severe mental disorders, major disparities in risk factor evaluation were found- particularly in hospitalised patients.

Evaluation of Repeated Web-Based Screening for Predicting Postpartum Depression: Prospective Cohort Study.

BackgroundPostpartum depression (PPD) is a severe mental disorder that often results in poor maternal-infant attachment and negatively impacts infant development. Universal screening has recently been recommended to identify women at risk, but the optimal screening time during pregnancy has not been defined so far. Thus, web-based technologies with widespread use among women of childbearing age create new opportunities to detect pregnancies with a high risk for adverse mental health outcomes at an early stage.ObjectiveThe aim of this study was to stratify the risk for PPD and to determine the optimal screening time during pregnancy by using a web-based screening tool collecting electronic patient-reported outcomes (ePROs) as the basis for a screening algorithm.MethodsIn total, 214 women were repeatedly tested for depressive symptoms 5 times during and 3 times after pregnancy by using the Edinburgh Postnatal Depression Scale (EPDS), accessible on a web-based pregnancy platform, developed by the authors of this study. For each prenatal assessment, the area under the curve (AUC), sensitivity, specificity, and predictive values for PPD were calculated. Multivariate logistic regression analyses were applied to identify further potential predictors, such as age, education, parity, relationship quality, and anxiety, to increase predictive accuracy.ResultsDigitally collected data from 214 pregnant women were analyzed. The predictive accuracy of depressive symptoms 3 and 6 months postpartum was reasonable to good regarding the screening in the second (AUC=0.85) and third (AUC=0.75) trimester. The multivariate logistic regression analyses resulted in an excellent AUC of 0.93 at 3 months and a good AUC of 0.87 at 6 months postpartum.ConclusionsThe best predictive accuracy for PPD has been shown for screening between the 24th and the 28th gestational week (GW) and seems to be beneficial for identifying women at risk. In combination with the aforementioned predictive factors, the discriminatory power improved, particularly at 3 months postpartum. Screening for depression during pregnancy, combined with the women’s personal risk profile, can be used as a starting point for developing a digital screening algorithm. Thereby, web-based assessment tools constitute feasible, efficient, and cost-effective approaches. Thus, they seem to be beneficial in detecting high-risk pregnancies in order to improve maternal and infant birth outcomes in the long term.