Association of Hospital Readmission Rates With Discharge Disposition for Patients With Psychotic Disorders.

GOAL: We explored how readmissions may result from patients' lack of access to aftercare services, failure to adhere to psychotropic medication plans, and inability to understand and follow hospital discharge recommendations. We also investigated whether insurance status, demographics, and socioeconomic status are associated with hospital readmissions. This study is important because readmissions contribute to increased personal and hospital expenses and decreased community tenure (the ability to maintain stability between hospital admissions). Addressing hospital readmissions will promote optimal discharge practices beginning on day one of hospital admission. METHODS: The study examined the differences in hospital readmission rates for patients with a primary psychotic disorder diagnosis. Discharge data were drawn in 2017 from the Nationwide Readmissions Database. Inclusion criteria included patients aged 0-89 years who were readmitted to a hospital between less than 24 hr and up to 30 days from discharge. Exclusion criteria were principal medical diagnoses, unplanned 30-day readmissions, and discharges against medical advice. The sampling frame included 269,906 weighted number of patients diagnosed with a psychotic disorder treated at one of 2,355 U.S. community hospitals. The sample size was 148,529 unweighted numbers of patients discharged. PRINCIPAL FINDINGS: In a logistic regression model, weighted variables were calculated and used to determine an association between the discharge dispositions and readmissions. After controlling for hospital characteristics and patient demographics, we found that the odds for readmission for routine and short-term hospital discharge dispositions decreased for home health care discharges, which indicated that home health care can prevent readmissions. The finding was statistically significant when controlling for payer type and patient age and gender. PRACTICAL APPLICATIONS: The findings support home health care as an effective option for patients with severe psychosis. Home health care reduces readmissions and is recommended, when appropriate, as an aftercare service following inpatient hospitalization and may enhance the quality of patient care. Improving healthcare quality involves optimizing, streamlining, and promoting standardized processes in discharge planning and direct transitions to aftercare services.

Multifactorial analysis to examine drivers of CMS summary star ratings in home health agencies.

This cross-sectional study examines factors associated with the CMS Summary Star Ratings in Home Health Agencies (HHA). Using Home Health Compare, medical claims, and census data, negative binomial regression analysis was conducted at the HHA level. Positive associations were found between Summary Star Ratings and beneficiary age, the number of claims, the proportion for specific diagnoses, the agency being hospital based, HHA age since establishment, patient retainment, improved walking/moving/bathing, and homeownership. Negative associations were found for specific ICD diagnosis proportions, HHAs serving special populations, the rate of non-white patients, patients transferred to different HHAs, income, and marital status in the coverage area. These findings are relevant to both practitioners and policymakers, in that they highlight major non-service factors associated with perceived quality of care.

CDSS-RM: a clinical decision support system reference model.

Clinical Decision Support Systems (CDSS) provide aid in clinical decision making and therefore need to take into consideration human, data interactions, and cognitive functions of clinical decision makers. The objective of this paper is to introduce a high level reference model that is intended to be used as a foundation to design successful and contextually relevant CDSS systems. The paper begins by introducing the information flow, use, and sharing characteristics in a hospital setting, and then it outlines the referential context for the model, which are clinical decisions in a hospital setting. Important characteristics of the Clinical decision making process include: (i) Temporally ordered steps, each leading to new data, which in turn becomes useful for a new decision, (ii) Feedback loops where acquisition of new data improves certainty and generates new questions to examine, (iii) Combining different kinds of clinical data for decision making, (iv) Reusing the same data in two or more different decisions, and (v) Clinical decisions requiring human cognitive skills and knowledge, to process the available information. These characteristics form the foundation to delineate important considerations of Clinical Decision Support Systems design. The model includes six interacting and interconnected elements, which formulate the high-level reference model (CDSS-RM). These elements are introduced in the form of questions, as considerations, and are examined with the use of illustrated scenario-based and data-driven examples. The six elements /considerations of the reference model are: (i) Do CDSS mimic the cognitive process of clinical decision makers? (ii) Do CDSS provide recommendations with longitudinal insight? (iii) Is the model performance contextually realistic? (iv) Is the 'Historical Decision' bias taken into consideration in CDSS design? (v) Do CDSS integrate established clinical standards and protocols? (vi) Do CDSS utilize unstructured data? The CDSS-RM reference model can contribute to optimized design of modeling methodologies, in order to improve response of health systems to clinical decision-making challenges.

Generation of a complete single-gene knockout bacterial artificial chromosome library of cowpox virus and identification of its essential genes.

Cowpox virus (CPXV) belongs to the genus Orthopoxvirus in the Poxviridae family. It infects a broad range of vertebrates and can cause zoonotic infections. CPXV has the largest genome among the orthopoxviruses and is therefore considered to have the most complete set of genes of all members of the genus. Since CPXV has also become a model for studying poxvirus genetics and pathogenesis, we created and characterized a complete set of single gene knockout bacterial artificial chromosome (BAC) clones of the CPXV strain Brighton Red. These mutants allow a systematic assessment of the contribution of single CPXV genes to the outcome of virus infection and replication, as well as to the virus host range. A full-length BAC clone of CPXV strain Brighton Red (pBRF) harboring the gene expressing the enhanced green fluorescent protein under the control of a viral late promoter was modified by introducing the mrfp1 gene encoding the monomeric red fluorescent protein driven by a synthetic early vaccinia virus promoter. Based on the modified BAC (pBRFseR), a library of targeted knockout mutants for each single viral open reading frame (ORF) was generated. Reconstitution of infectious virus was successful for 109 of the 183 mutant BAC clones, indicating that the deleted genes are not essential for virus replication. In contrast, 74 ORFs were identified as essential because no virus progeny was obtained upon transfection of the mutant BAC clones and in the presence of a helper virus. More than 70% of all late CPXV genes belonged to this latter group of essential genes.

Identification of 10 cowpox virus proteins that are necessary for induction of hemorrhagic lesions (red pocks) on chorioallantoic membranes.

UNLABELLED: Cowpox viruses (CPXV) cause hemorrhagic lesions ("red pocks") on infected chorioallantoic membranes (CAM) of embryonated chicken eggs, while most other members of the genus Orthopoxvirus produce nonhemorrhagic lesions ("white pocks"). Cytokine response modifier A (CrmA) of CPXV strain Brighton Red (BR) is necessary but not sufficient for the induction of red pocks. To identify additional viral proteins involved in the induction of hemorrhagic lesions, a library of single-gene CPXV knockout mutants was screened. We identified 10 proteins that are required for the formation of hemorrhagic lesions, which are encoded by CPXV060, CPXV064, CPXV068, CPXV069, CPXV074, CPXV136, CPXV168, CPXV169, CPXV172, and CPXV199. The genes are the homologues of F12L, F15L, E2L, E3L, E8R, A4L, A33R, A34R, A36R, and B5R of vaccinia virus (VACV). Mutants with deletions in CPXV060, CPXV168, CPXV169, CPXV172, or CPXV199 induced white pocks with a comet-like shape on the CAM. The homologues of these five genes in VACV encode proteins that are involved in the production of extracellular enveloped viruses (EEV) and the repulsion of superinfecting virions by actin tails. The homologue of CPXV068 in VACV is also involved in EEV production but is not related to actin tail induction. The other genes encode immunomodulatory proteins (CPXV069 and crmA) and viral core proteins (CPXV074 and CPXV136), and the function of the product of CPXV064 is unknown. IMPORTANCE: It has been known for a long time that cowpox virus induces hemorrhagic lesions on chicken CAM, while most of the other orthopoxviruses produce nonhemorrhagic lesions. Although cowpox virus CrmA has been proved to be responsible for the hemorrhagic phenotype, other proteins causing this phenotype remain unknown. Recently, we generated a complete single-gene knockout bacterial artificial chromosome (BAC) library of cowpox virus Brighton strain. Out of 183 knockout BAC clones, 109 knockout viruses were reconstituted. The knockout library makes possible high-throughput screening for studying poxvirus replication and pathogenesis. In this study, we screened all 109 single-gene knockout viruses and identified 10 proteins necessary for inducing hemorrhagic lesions. The identification of these genes gives a new perspective for studying the hemorrhagic phenotype and may give a better understanding of poxvirus virulence.

The effect of an electronic documentation system on the trauma patient's length of stay in an emergency department.

INTRODUCTION: Electronic patient records are important for quality health services and efficient patient data management. In emergency care, saving valuable time during patient care is of great significance. One out of two fatalities due to trauma occur half an hour after the injury. The aim of this study was to investigate the potential effect of an electronic trauma documentation system on the length of stay in an emergency department. METHODS: A 2-year observational study was conducted in the emergency department of a university hospital located in central Greece. The purpose was to compare 3 length-of-stay parameters with and without the use of an electronic documentation system. Ninety-nine trauma patients were monitored with the use of the electronic system, whereas 101 patients were monitored with a paper-based method (control group). RESULTS: Statistical analysis using independent-samples t tests indicated that the time between admission and completion of the planned care was significantly lower in the electronic documentation patient group (100 ± 92 minutes) than in the control group (149 ± 29 minutes) (P < .01). A similar effect was found on the total ED length of stay (127 ± 93 minutes in electronic documentation group vs 206 ± 41 minutes in control group, P < .01) and the time between completion of care and discharge from the emergency department (26 ± 10 minutes in electronic documentation group vs 57 ± 23 minutes in control group, P < .01). DISCUSSION: We investigated 3 length-of-stay parameters and found that all were lower with the use of the electronic documentation system. This finding is important regarding the quality of trauma patient care because saving time during the first hours after the injury may determine the outcome of the trauma patient.

A Bayesian method for the automatic extraction of meaningful clinical sequences from large clinical databases.

BACKGROUND: Clinical event recognition can have several applications, such as the examination of clinical stories that can be associated with negative hospital outcomes, or its use in clinical education to assist medical students recognize frequent clinical events. OBJECTIVE: The purpose of this study is to develop a non-annotated Bayes-based algorithm to extract useful clinical events from medical data. MATERIALS AND METHODS: We used subsets of MIMIC and CMS LDS datasets that include respiratory diagnoses to calculate two-itemset rules(one item in antecedent and one in consequent) which were used as building blocks for the construction of clinical event sequence order. The main condition for the event sequence is a sequential increase in the conditional probability of two-itemset rules having positive certainty factor, when they are studied together.A clinical event in our framework is defined to be a collection of several blocks of events that meet the aforementioned condition, when considered together. The correctness of our clinical sequences has been validated by two physicians. RESULTS: Our results showed that medical experts scored the rules of this algorithm better than random Apriori rules. A GUI was designed that can be used to examine the association of each clinical event with the clinical outcomes of the length of stay, inpatient mortality, and hospital charges. CONCLUSION: The present work provides a new approach on how we can improve extraction of clinical event sequences automatically, without user annotation. Our algorithm can successfully find, in several cases, blocks of rules which can tell correct clinical event stories.

Cross-cultural evaluation of the relevance of the HCAHPS survey in five European countries.

OBJECTIVE: To describe the systematic language translation and cross-cultural evaluation process that assessed the relevance of the Hospital Consumer Assessment of Healthcare Providers and Systems survey in five European countries prior to national data collection efforts. DESIGN: An approach involving a systematic translation process, expert review by experienced researchers and a review by 'patient' experts involving the use of content validity indexing techniques with chance correction. SETTING: Five European countries where Dutch, Finnish, French, German, Greek, Italian and Polish are spoken. PARTICIPANTS: 'Patient' experts who had recently experienced a hospitalization in the participating country. Main OutcomeMeasure(s) Content validity indexing with chance correction adjustment providing a quantifiable measure that evaluates the conceptual, contextual, content, semantic and technical equivalence of the instrument in relationship to the patient care experience. RESULTS: All translations except two received 'excellent' ratings and no significant differences existed between scores for languages spoken in more than one country. Patient raters across all countries expressed different concerns about some of the demographic questions and their relevance for evaluating patient satisfaction. Removing demographic questions from the evaluation produced a significant improvement in the scale-level scores (P= .018). The cross-cultural evaluation process suggested that translations and content of the patient satisfaction survey were relevant across countries and languages. CONCLUSIONS: The Hospital Consumer Assessment of Healthcare Providers and Systems survey is relevant to some European hospital systems and has the potential to produce internationally comparable patient satisfaction scores.

Integration of data analysis methods in syndromic surveillance systems.

Syndromic surveillance systems perform real-time analysis of health data to enable early identification of potential public health threats, evaluating whether distributional parameters have been increased beyond a threshold. This paper presents the applied data analysis methods in five non-industrial surveillance systems. Four time series and spatial cluster analysis methods were found to be implemented: SMART, EWMA, CuSum and WSARE. Combined use both spatial and time series methods is found in the presented surveillance applications. Data analysis methods for syndromic surveillance are a constantly emerging field, while new statistical methods and algorithms are implemented into surveillance systems.

Distributed and grid computing projects with research focus in human health.

Distributed systems and grid computing systems are used to connect several computers to obtain a higher level of performance, in order to solve a problem. During the last decade, projects use the World Wide Web to aggregate individuals' CPU power for research purposes. This paper presents the existing active large scale distributed and grid computing projects with research focus in human health. There have been found and presented 11 active projects with more than 2000 Processing Units (PUs) each. The research focus for most of them is molecular biology and, specifically on understanding or predicting protein structure through simulation, comparing proteins, genomic analysis for disease provoking genes and drug design. Though not in all cases explicitly stated, common target diseases include research to find cure against HIV, dengue, Duchene dystrophy, Parkinson's disease, various types of cancer and influenza. Other diseases include malaria, anthrax, Alzheimer's disease. The need for national initiatives and European Collaboration for larger scale projects is stressed, to raise the awareness of citizens to participate in order to create a culture of internet volunteering altruism.

Development and evaluation of an expert system for the diagnosis of child autism.

This paper presents the development of an expert system for the diagnosis of child autism and discusses potential benefits of its implementation in a clinical environment. The development of the expert system was based on a diagnostic algorithm supported by a developmental scale (PEDS) and a diagnostic tool of autism (CARS). Twelve nurses who work in pediatric hospital were asked to use the expert system for a session of 30 minutes and were asked to assess its usefulness, usability and diagnostic value. The majority of nurses agree that it is a useful and promising diagnostic tool for the clinical practice and for the identification of potential child autism cases.

User-Based Evaluation of a Data-Driven Medical Education Platform.

TrainCoMorb is an online data-driven training platform for medical students and residents who can practice recognizing comorbidities and their attributable risk for negative hospital outcomes. This is a subsequent cross-sectional evaluation study designed to examine four dimensions of the platform (navigation, usefulness, validity, features) and their association with external factors (age, experience in simulation systems, opinion about data-driven education). Eighteen medical residents participated in a scenario-based evaluation session and completed an online survey. The residents evaluated the four composite dimensions with scores between 3.77 and 4.15 (5-scale) and thought highly of data-driven medical education. Those more familiar with clinical simulation systems, and more positive about data-driven education, evaluated the "usefulness", "validity", and "features" dimensions with higher scores. TrainComorb is intended to be a supplementary tool for the education of future physicians, and this user-based evaluation study provided positive feedback that it could serve its intended scope.

Prenatal Buprenorphine/Naloxone or Methadone Use on Neonatal Outcomes in Michigan.

Background Maternal opioid exposure during pregnancy has various effects on neonatal health. Buprenorphine/naloxone and methadone are examples of medications for opioid use disorder (MOUD) used for the treatment of opioid use disorder (OUD). Research comparing the impacts of these MOUD modalities on neonatal outcomes when used to treat pregnant people with OUD remains limited. We evaluated the differences in outcomes between neonates with in-utero exposure to buprenorphine/naloxone versus methadone. Methodology We performed a retrospective cohort chart review between October 15, 2008, and October 15, 2019, evaluating mother/neonate dyads at two medical centers in Michigan. The charts of female patients, aged 18+, with OUD and buprenorphine/naloxone or methadone treatment, were examined. The charts of the corresponding neonates were also examined. Multiple regression analysis was performed. Results In total, 343 mother/infant dyads were included: 99 patients were treated with buprenorphine/naloxone and 232 patients were treated with methadone. The buprenorphine/naloxone group had significant differences in maternal age, hepatitis status, asthma, gestational age in weeks, neonatal intensive care unit (NICU) length of stay (LOS), neonatal opioid withdrawal syndrome (NOWS) peak score, birth head circumference, and birth weight compared to the methadone group at baseline. Adjusted multivariable regression analysis demonstrated neonates with exposure to buprenorphine/naloxone had a NOWS peak score 3.079 points less (95% confidence interval (CI): -4.525, 1.633; p = 0.001) and NICU LOS 8.955 days less (95% CI: -14.399, -3.511; p = 0.001) than neonates exposed to methadone. Conclusions Neonates with in-utero exposure to buprenorphine/naloxone had significantly lower NOWS scores and shorter NICU LOS compared to neonates with in-utero exposure to methadone. These findings demonstrate that buprenorphine/naloxone is potentially a more favorable treatment for the reduction in metrics representing adverse neonatal outcomes in pregnant people with OUD than methadone.

Nurse forecasting in Europe (RN4CAST): Rationale, design and methodology.

BACKGROUND: Current human resources planning models in nursing are unreliable and ineffective as they consider volumes, but ignore effects on quality in patient care. The project RN4CAST aims innovative forecasting methods by addressing not only volumes, but quality of nursing staff as well as quality of patient care. METHODS/DESIGN: A multi-country, multilevel cross-sectional design is used to obtain important unmeasured factors in forecasting models including how features of hospital work environments impact on nurse recruitment, retention and patient outcomes. In each of the 12 participating European countries, at least 30 general acute hospitals were sampled. Data are gathered via four data sources (nurse, patient and organizational surveys and via routinely collected hospital discharge data). All staff nurses of a random selection of medical and surgical units (at least 2 per hospital) were surveyed. The nurse survey has the purpose to measure the experiences of nurses on their job (e.g. job satisfaction, burnout) as well as to allow the creation of aggregated hospital level measures of staffing and working conditions. The patient survey is organized in a sub-sample of countries and hospitals using a one-day census approach to measure the patient experiences with medical and nursing care. In addition to conducting a patient survey, hospital discharge abstract datasets will be used to calculate additional patient outcomes like in-hospital mortality and failure-to-rescue. Via the organizational survey, information about the organizational profile (e.g. bed size, types of technology available, teaching status) is collected to control the analyses for institutional differences.This information will be linked via common identifiers and the relationships between different aspects of the nursing work environment and patient and nurse outcomes will be studied by using multilevel regression type analyses. These results will be used to simulate the impact of changing different aspects of the nursing work environment on quality of care and satisfaction of the nursing workforce. DISCUSSION: RN4CAST is one of the largest nurse workforce studies ever conducted in Europe, will add to accuracy of forecasting models and generate new approaches to more effective management of nursing resources in Europe.

Research management: the case of RN4CAST.

Successful research management requires multifunctional, equal teamwork and efficient coordination, aiming to increase the impact of the research outcomes. Aim of this paper is to present the strategies that have been followed to successfully manage the RN4CAST study, one of the largest multi country research projects ever conducted. The paper focuses on the core research strategies rather than on the administrative management activities also required for the success of this case report. Management of a multi-country nursing survey requires the use of common data collection tools, applicable to every context, research protocols supporting the scope of the research, data models for multi-country analyses and global dissemination strategies.

Assessment of hospital information systems implementation: a case study.

The use of integrated Hospital Information Systems is related with many benefits for the healthcare system, increasing the effectiveness of the provided services and assuring quality of care. Aim of this study is to investigate the types of Information Systems, the level of integration and the problems identified during the implementation phase, in three public hospitals. The above are expected to contribute to the understanding of the organizational, human resource and technical factors related with the successful implementation of a hospital IS. In order to investigate those elements, an assessment questionnaire was developed and completed by nine hospitals IT employees of the three hospitals. In addition, open interviews were organized with the same employees to further formulate an overall aspect, while in one hospital case, observation and discussion with four different categories of involved staff was undertaken. It was found that the implementation problems are mainly related with the underfunding, inadequate use of standards, lack of skilled IT experts, insufficiently trained personnel and users' reserve. The problems may be tackled with a supportive hospital administration committed to the successful implementation. The external contracting company working on its own, without any participation of the hospital IT department seems to be a failure recipe. It is evident that an active management support and skillful hospital IT employees, are expected to result to success stories during the implementation of integrated hospital information systems.

An annotated association mining approach for extracting and visualizing interesting clinical events.

OBJECTIVE: This work aims at deriving interesting clinical events using association rule mining based on a user-annotated order of clinical features. MATERIALS AND METHODS: A user specifies a partial temporal order of features by indexing features of interest, with repeated and bundled indexes allowed as needed. An association mining algorithm plugin was designed to generate rules that adhere to the user-specified temporal order. The plugin uses temporal and sequence constraints to reduce rule permutations early in the rule generation process. The method was evaluated with a large medical claims dataset to generate clinical events. RESULTS: Using the plug-in algorithm, the database is scanned to calculate the support of item sequences whose sequential order conforms with the user annotated feature order. In our experiments with 20,000 medical claim data records, our method generated rules in a significantly less time than the standalone Apriori algorithm. Our approach generates dendrograms to organize the rules into meaningful hierarchies and provides a graphical interface to navigate the rules and unfold interesting clinical events. DISCUSSION: Since many associations in healthcare are of sequential nature, some of the derived rules may describe interesting clinical flows or events, while others may be contextually irrelevant. Our method exploits user-specified sequence constraints to eliminate irrelevant rules and reduce rule permutations, speeding up rule mining. CONCLUSION: This work can be the foundation for future association rule mining studies to extract sequential events based on interestingness. The work can support clinical education where the instructor defines feature sequence constraints, and students unfold and examine extracted sequential rules.

A Cross-Sectional Study to Predict Mortality for Medicare Patients Based on the Combined Use of HCUP Tools.

Prediction of inpatient mortality is not an easy problem since multiple comorbidities and other factors in synergy have a variable effect on inpatient death risk. This research combined Healthcare Cost and Utilization Project (HCUP) tools (clinical classification software, CCS; Chronic Condition Indicator, CCI) to recommend a critical set of CCS diagnosis and procedure predictors for mortality. The study motivation is to provide the research community an up-to-date critical set of inhospital mortality predictors. The study follows a cross-sectional design. An inpatient CMS claims file (N = 418,529) was combined with the HCUP grouper to transform the ICD-10-CM and CPT codes to CCS categories and to enhance the data with the acuity and the diagnosis presence/non-presence on admission. Five logistic regressions were conducted to progressively enhance the feature set with the aforementioned dimensions. The Sensitivitydeath and positive predictive value (PPVdeath) were estimated for each consecutive step to examine the attributable predictive power of each dimension. When all information were inserted, the PPVdeath was 65.5%, a 10% increase over a single representation of secondary diagnoses. A critical collection of significant CCS diagnoses and procedures were extracted as predictors of inpatient mortality. The chronicity and POA status of a diagnosis improve the prediction of inpatient mortality. Furthermore, the combined use of these dimensions provides better predictions against the Elixhauser Comorbidity Index. The combined use of HCUP tools provides a reasonable estimate of inpatient mortality. This is the first study that uses the updated HCUP groupers for ICD-10-CM to provide insights about drivers of inpatient mortality.

A framework for the development of patient safety education and training guidelines.

Patient Safety (PS) is a major concern that involves a wide range of roles in healthcare, including those who are directly and indirectly involved, and patients as well. In order to succeed into developing a safety culture among healthcare providers, carers and patients, there should be given great attention into building appropriate education and training tools, especially addressing those who plan patient safety activities. The framework described in this policy paper is based on the results of the European Network for Patient Safety (EUNetPaS) project and analyses the principles and elements of the guidance that should be provided to those who design and implement Patient Safety Education and training activities. The main principles that it should be based on and the core teaching objectives-expected outcomes are addressed. Once the main context and considerations are properly set, the guidance should define the general schema of the content that should be included in the Education and Training activities, as well as how these activities would be delivered. It is also important that the different roles of the recipients are clearly distinguished and linked to their role-specific methods, proper delivery platforms and success stories. Setting these principles into practice when planning and implementing interventions, primarily aims to enlighten and support those who are enrolled to design and implement Patient Safety education and training teaching activities. This is achieved by providing them with a framework to build upon, succeeding to build a collaborative, safety conscious and competent environment, in terms of PS. A guidelines web platform has been developed to support this process.

Enhancing Medical Education with Data-Driven Software: The TrainCoMorb App.

Medical education can take advantage of big data to enhance the learning experience of students. This paper describes the development of TrainCoMorb, an online, data-driven application for medical students who can practice recognizing comorbidities and their attributable risk for negative outcomes. Trainees access TrainCoMorb to create scenarios of comorbidities, step-by-step, and see snapshots of the risk for inpatient death, hospital septicemia and the projected length of stay. The study utilized an enormous claims dataset (N=11m.). A dynamic Bayesian algorithm was developed, which calculates and updates conditional probabilities for the outcomes under study in each phase of an ongoing scenario. The trainee initiates a scenario by selecting demographics and a principal diagnosis, then adds chronic and hospital-acquired conditions to see a summary of the attributable risk in each phase. TrainCoMorb is anticipated to assist medical students gain a better understanding of comorbidities and their impact on clinical outcomes.