Search

To assess the impacts of multiple chronic conditions (MCC) and frailty on 30-day post-discharge readmission and mortality among older patients with delayed discharge.We used a retrospective cohort of older patients in the Discharge Abstract Database (DAD) between 2004 and 2017 in Ontario, Canada. We extracted data on patients aged ≥ 65 who experienced delayed discharge during hospitalization (N = 353,106).We measured MCC and frailty using the Elixhauser Comorbidity Index (ECI) and the Hospital Frailty Risk Score (HFRS), respectively. We used multinomial logistic regression to model the main and interactive effects of MCC and frailty on the adverse outcomes.After adjusting for sex, discharge destination, urban/rural residency, wait time for alternative care, and socioeconomic status, the coexistence of MCC and high frailty increased the relative risk of 30-day mortality and readmission when compared to the references group, i.e., non-MCC patients with low-to-moderate frailty.Multimorbidity and frailty each provide unique information about adverse outcomes among older patients with delayed discharge but are most informative when examined in unison.To minimize the risk of adverse outcomes among older delayed discharge patients, discharge planning must be tailored to their concurrent multimorbidity and frailty status.

Sepsis is a major public and global health concern. Every hour of delay in detecting sepsis significantly increases the risk of death, highlighting the importance of accurately predicting sepsis in a timely manner. A growing body of literature has examined developing new or improving the existing machine learning (ML) approaches for timely and accurate predictions of sepsis. This study contributes to this literature by providing clear insights regarding the role of the recency and adequacy of historical information in predicting sepsis using ML. To this end, we implemented a deep learning model using a bidirectional long short-term memory (BiLSTM) algorithm and compared it with six other ML algorithms based on numerous combinations of the prediction horizons (to capture information recency) and observation windows (to capture information adequacy) using different measures of predictive performance. Our results indicated that the BiLSTM algorithm outperforms all other ML algorithms and provides a great separability of the predicted risk of sepsis among septic versus non-septic patients. Moreover, decreasing the prediction horizon (in favor of information recency) always boosts the predictive performance; however, the impact of expanding the observation window (in favor of information adequacy) depends on the prediction horizon and the purpose of prediction. More specifically, when the prediction is responsive to the positive label (i.e., Sepsis), increasing historical data improves the predictive performance when the prediction horizon is short-moderate.

In the wake of the COVID-19 pandemic, those planning and conducting research involving older adults have faced many challenges, in part because of the public health measures in place. This article details the early steps and corresponding strategies implemented by our multidisciplinary team to pivot our large-scale aging and mobility study. Based on the premise that all current and emerging research in aging has been impacted by the pandemic, we propose a continuum approach whereby the research question, analysis, and interpretation are situated in accordance with the stage of the pandemic. Using examples from our own study, we outline potential ways to partner with older adults and other stakeholders as well as to encourage collaboration beyond disciplinary silos even under the current circumstances. Finally, we suggest the formation of a Canadian-led consortium that leverages cross-disciplinary expertise to address the complexities of our aging population in the COVID-19 era and beyond.

Background Paramedics are mandated to transport emergently triaged patients to the closest emergency department (ED). The closest ED may not be the optimal transport destination if further distanced ED’s can provide specialized care or are less crowded. Machine learning may support paramedic decision-making to transport a specific subgroup of emergently triaged patients that are unlikely to require hospital admission or emergency care to a more appropriate ED. We examined whether prehospital patient characteristics known to paramedics were predictive of hospital admission. Methods We conducted a retrospective cohort study using machine learning algorithms to analyze ED visits of the National Ambulatory Care Reporting System from Jan 1, 2018 to Dec 31, 2019 in Ontario, Canada. We included all adult (≥ 18 years) paramedic transports to the ED who had an emergent Canadian Triage Acuity Scale score (CTAS 2). Eight prehospital characteristic classes known to paramedics were used. We applied four machine learning algorithms that were trained and assessed using 10-fold cross-validation to predict the ED visit disposition of admission to hospital or discharged from ED. Predictive model performance was determined using the area under the receiving operating characteristic curve (AUC) with 95% confidence intervals and probabilistic accuracy using the Brier Scaled score. Variable importance scores were computed to determine the top 10 predictors of hospital admission. We also reported sensitivity, specificity, and positive and negative predictive values to support performance interpretation. Results All machine learning algorithms performed similarly for the prediction of which ED patient visits would be admitted to hospital (AUC 0.77–0.78, Brier Scaled 0.22–0.24). The characteristics most predictive of admission included age 65 to 105 years, referral source from a residential care facility, presenting with a respiratory complaint, and receiving home care. Conclusions Machine learning algorithms performed well in predicting ED visit dispositions using a comprehensive list of prehospital patient characteristics. To the best of our knowledge, this study is the first to utilize machine learning to predict ED visit outcomes from patient characteristics known prior to paramedic transport. This study has potential to inform paramedic regulations regarding the distribution of emergently triaged patients.

The COVID-19 pandemic - as a massive disruption - has significantly increased the need for medical services putting an unprecedented strain on health systems. This study presents a robust location-allocation model under uncertainty to increase the resiliency of health systems by applying alternative resources, such as backup and field hospitals and student nurses. A multi-objective optimization model is developed to minimize the system's costs and maximize the satisfaction rate among medical staff and COVID-19 patients. A robust approach is provided to face the data uncertainty, and a new mathematical model is extended to linearize a nonlinear constraint. The ICU beds, ward beds, ventilators, and nurses are considered the four main capacity limitations of hospitals for admitting different types of COVID-19 patients. The sensitivity analysis is performed on a real-world case study to investigate the applicability of the proposed model. The results demonstrate the contribution of student nurses and backup and field hospitals in treating COVID-19 patients and provide more flexible decisions with lower risks in the system by managing the fluctuations in both the number of patients and available nurses. The results showed that a reduction in the number of available nurses incurs higher costs for the system and lower satisfaction among patients and nurses. Moreover, the backup and field hospitals and the medical staff elevated the system's resiliency. By allocating backup hospitals to COVID-19 patients, only 37% of severe patients were lost, and this rate fell to less than 5% after establishing field hospitals. Moreover, medical students and field hospitals curbed the costs and increased the satisfaction rate of nurses by 75%. Finally, the system was protected from failure by increasing the conservatism level. With a 2% growth in the price of robustness, the system saved 13%.

Background Patient complexity among older delayed-discharge patients complicates discharge planning, resulting in a higher rate of adverse outcomes, such as readmission and mortality. Early prediction of multimorbidity, as a common indicator of patient complexity, can support proactive discharge planning by prioritizing complex patients and reducing healthcare inefficiencies. Objective We set out to accomplish the following two objectives: 1) to examine the predictability of three common multimorbidity indices, including Charlson–Deyo Comorbidity Index (CDCI), the Elixhauser Comorbidity Index (ECI), and the Functional Comorbidity Index (FCI) using machine learning (ML), and 2) to assess the prognostic power of these indices in predicting 30-day readmission and mortality. Materials and Methods We used data including 163,983 observations of patients aged 65 and older who experienced discharge delay in Ontario, Canada, during 2004 – 2017. First, we utilized various classification ML algorithms, including classification and regression trees, random forests, bagging trees, extreme gradient boosting, and logistic regression, to predict the multimorbidity status based on CDCI, ECI, and FCI. Second, we used adjusted multinomial logistic regression to assess the association between multimorbidity indices and the patient-important outcomes, including 30-day mortality and readmission. Results For all ML algorithms and regardless of the predictive performance criteria, better predictions were established for the CDCI compared with the ECI and FCI. Remarkably, the most predictable multimorbidity index (i.e., CDCI with Area Under the Receiver Operating Characteristic Curve = 0.80, 95% CI = 0.79 – 0.81) also offered the highest prognostications regarding adverse events (RRRmortality = 3.44, 95% CI = 3.21 – 3.68 and RRRreadmission = 1.36, 95% CI = 1.31 – 1.40). Conclusions Our findings highlight the feasibility and utility of predicting multimorbidity status using ML algorithms, resulting in the early detection of patients at risk of mortality and readmission. This can support proactive triage and decision-making about staffing and resource allocation, with the goal of optimizing patient outcomes and facilitating an upstream and informed discharge process through prioritizing complex patients for discharge and providing patient-centered care.

This paper proposes a novel algorithm for optimizing decision variables with respect to an outcome variable of interest in complex problems, such as those arising from big data. The proposed algorithm builds on the notion of Markov blankets in Bayesian networks to alleviate the computational challenges associated with optimization tasks in complex datasets. Through a case study, we apply the algorithm to optimize medication prescriptions for diabetic patients, who have different characteristics, suffer from multiple comorbidities, and take multiple medications concurrently. In particular, we demonstrate how the optimal combination of diabetic medications can be found by examining the comparative effectiveness of the medications among similar patients. The case study is based on 5 years of data for 19,223 diabetic patients. Our results indicate that certain patient characteristics (e.g., clinical and demographic features) influence optimal treatment decisions. Among patients examined, monotherapy with metformin was the most common optimal medication decision. The results are consistent with the relevant clinical guidelines and reports in the medical literature. The proposed algorithm obviates the need for knowledge of the whole Bayesian network model, which can be very complex in big data problems. The procedure can be applied to any complex Bayesian network with numerous features, multiple decision variables, and a target variable.

Background Emergency departments (ED) are a portal of entry into the hospital and are uniquely positioned to influence the health care trajectories of older adults seeking medical attention. Older adults present to the ED with distinct needs and complex medical histories, which can make disposition planning more challenging. Machine learning (ML) approaches have been previously used to inform decision-making surrounding ED disposition in the general population. However, little is known about the performance and utility of ML methods in predicting hospital admission among older ED patients. We applied a series of ML algorithms to predict ED admission in older adults and discuss their clinical and policy implications. Materials and methods We analyzed the Canadian data from the interRAI multinational ED study, the largest prospective cohort study of older ED patients to date. The data included 2274 ED patients 75 years of age and older from eight ED sites across Canada between November 2009 and April 2012. Data were extracted from the interRAI ED Contact Assessment, with predictors including a series of geriatric syndromes, functional assessments, and baseline care needs. We applied a total of five ML algorithms. Models were trained, assessed, and analyzed using 10-fold cross-validation. The performance of predictive models was measured using the area under the receiver operating characteristic curve (AUC). We also report the accuracy, sensitivity, and specificity of each model to supplement performance interpretation. Results Gradient boosted trees was the most accurate model to predict older ED patients who would require hospitalization (AUC = 0.80). The five most informative features include home intravenous therapy, time of ED presentation, a requirement for formal support services, independence in walking, and the presence of an unstable medical condition. Conclusion To the best of our knowledge, this is the first study to predict hospital admission in older ED patients using a series of geriatric syndromes and functional assessments. We were able to predict hospital admission in older ED patients with good accuracy using the items available in the interRAI ED Contact Assessment. This information can be used to inform decision-making about ED disposition and may expedite admission processes and proactive discharge planning.

Limited guidance is available for providing patient‐specific care to hypertensive patients, although this chronic condition is the leading risk factor for cardiovascular diseases. To address this issue, we develop an analytical model that takes into account the most relevant risk factors including age, sex, blood pressure, diabetes status, smoking habits, and blood cholesterol. Using the Markov Decision Process framework, we develop a model to maximize expected quality‐adjusted life years, as well as characterize the optimal sequence and combination of antihypertensive medications. Assuming the physician uses the standard medication dose for each drug, and the patient fully adheres to the prescribed treatment regimen, we prove that optimal treatment policies exhibit a threshold structure. Our findings indicate that our recommended thresholds vary by age and other patient characteristics, for example (1) the optimal thresholds for all medication prescription are nonincreasing in age, and (2) the medications need to be prescribed at lower thresholds for males who smoke than for males who have diabetes. The improvements in quality‐adjusted life years associated with our model compare favorably with those obtained by following the British Hypertension Society's guideline, and the gains increase with the severity of risk factors. For instance, in both genders (although at different rates), diabetic patients gain more than non‐diabetic patients. Our sensitivity analysis results indicate that the optimal thresholds decrease if the medications have lower side‐effects and vice versa.

In learning causal networks, typically cross-sectional data are used and the sequence among the network nodes is learned through conditional independence. Sequence is inherently a longitudinal concept. We propose to learn sequence of events in longitudinal data and use it to orient arc directions in a network learned from cross-sectional data. The network is learned from cross-sectional data using various established algorithms, with one modification. Arc directions that do not agree with the longitudinal sequence were prohibited. We established longitudinal sequence through two methods: Probabilistic Contrast, and Goodman and Kruskal error reduction methods. In simulated data, the error reduction method was used to learn the sequence in the data. The procedure reduced the number of arc direction errors and larger improvements were observed with increasing number of events in the network. In real data, different algorithms were used to learn the network from cross-sectional data, while prohibiting arc directions not supported by longitudinal information. The agreement among learned networks increased significantly. It is possible to combine sequence information learned from longitudinal data with algorithms organized for learning network models from cross-sectional data. Such models may have additional causal interpretation as they more explicitly take into account observed sequence of events.

Purpose of the study This study provides benchmarks for likelihood, number of days until, and sequence of functional decline and recovery. Design and methods We analyzed activities of daily living (ADLs) of 296,051 residents in Veteran Affairs nursing homes between January 1, 2000 and October 9, 2012. ADLs were extracted from standard minimum data set assessments. Because of significant overlap between short- and long-stay residents, we did not distinguish between these populations. Twenty-five combinations of ADL deficits described the experience of 84.3% of all residents. A network model described transitions among these 25 combinations. The network was used to calculate the shortest, longest, and maximum likelihood paths using backward induction methodology. Longitudinal data were used to derive a Bayesian network that preserved the sequence of occurrence of 9 ADL deficits. Results The majority of residents (57%) followed 4 pathways in loss of function. The most likely sequence, in order of occurrence, was bathing, grooming, walking, dressing, toileting, bowel continence, urinary continence, transferring, and feeding. The other three paths occurred with reversals in the order of dressing/toileting and bowel/urinary continence. ADL impairments persisted without any change for an average of 164 days (SD = 62). Residents recovered partially or completely from a single impairment in 57% of cases over an average of 119 days (SD = 41). Recovery rates declined as residents developed more than 4 impairments. Implications Recovery of deficits among those studied followed a relatively predictable path, and although more than half recovered from a single functional deficit, recovery exceeded 100 days suggesting time to recover often occurs over many months.

The efficacy of diabetic medications among patients with multiple comorbidities is not tested in randomized clinical studies. It is important to monitor the performance of these medications after marketing approvals.To investigate the risk of all-cause mortality associated with prescription of hypoglycemic agents.We retrospectively examined data from 17,773 type 2 diabetic patients seen from March 2, 1998, to December 13, 2010, in 3 Veterans Administration medical centers. Severity was measured using patients' inpatient and outpatient comorbidities during the last year of visits. Severity-adjusted logistic regression was used to measure the odds ratio for mortality within the study period.Patients' severity of illness correctly classified mortality for 89.8% of the patients (P less than 0.0001). Being younger, married, and white decreased severity adjusted risk of mortality. Exposure to the following medications increased severity adjusted risk of mortality: glyburide (odds ratio [OR] = 1.804, 95% CI from 1.518 to 2.145), glipizide (OR = 1.566, 95% CI from 1.333 to 1.839), rosiglitazone (OR = 1.805, 95% CI from 1.378 to 2.365), chlorpropamide (OR = 3.026, 95% CI from 1.096 to 8.351), insulin (OR = 2.382, 95% CI from 2.112 to 2.686). None of the other medications (metformin, acarbose, glimepiride, pioglitazone, repaglinide, troglitazone, or dipeptidyl peptidase-4) were associated with excess mortality beyond what could be expected from the patients' severity of illness or demographic characteristics. The reported excess mortality could not be explained away by use of other concurrent, nondiabetic classes of medications.Our findings suggest chlorpropamide, glipizide, glyburide, insulin, and rosiglitazone increased severity-adjusted mortality in veterans with type 2 diabetes. A decision aid that could optimize selection of hypoglycemic medications based on patients' comorbidities might increase patients' survival.

This paper proposes a method for examining the causal relationship among investment in information technology (IT) and the organization's productivity. In this method, first a strong relationship among (1) investment in IT, (2) use of IT and (3) organization's productivity is verified using correlations. Second, the assumption that IT investment preceded improved productivity is tested using partial correlation. Finally, the assumption of what may have happened in the absence of IT investment, the so called counterfactual, is tested through forecasting productivity at different levels of investment. The paper applies the proposed method to investment in the Veterans Health Information Systems and Technology Architecture (VISTA) system. Result show that the causal analysis can be done, even with limited data. Furthermore, because the procedure relies on overall organization's productivity, it might be more objective than when the analyst picks and chooses which costs and benefits should be included in the analysis.

BACKGROUND Improvement teams make causal inferences, but the methods they use are based on statistical associations. This article shows how data and statistical models can be used to help improvement teams make causal inferences and find the root causes of problems. METHODS This article uses attribution data, competing risk survival analysis, and Bayesian network probabilities to analyze excessive emergency department (ED) stays within one hospital. We use data recorded by ED clinicians that attributed the cause of excessive ED stays to 23 causes for the 70 049 ED visits between March 2011 and April 2014. We use competing risk survival analysis to identify contribution of each cause to the delay. We use Bayesian network models to analyze interaction among different causes of excessive stays and find the root causes of this problem. RESULTS This article shows the utility of causal analysis to help improvement teams focus on the root causes of problems. For the example analyzed in the article, most causes for patients' excessive ED stays were related to the hospital operations outside the ED. Therefore, improvement projects inside the ED such as expanding ED, increasing staff at the ED, or improving operations are less likely to have a positive impact on reducing excessive ED stays. On the contrary, interventions that improve hospital occupancy (better discharge, expansion of beds, etc) or improve laboratory response times are more likely to result in positive outcomes.

We examine the role of a common cognitive heuristic in unsupervised learning of Bayesian probability networks from data. Human beings perceive a larger association between causal than diagnostic relationships. This psychological principal can be used to orient the arcs within Bayesian networks by prohibiting the direction that is less predictive. The heuristic increased predictive accuracy by an average of 0.51 % percent, a small amount. It also increased total agreement between different network learning algorithms (Max Spanning Tree, Taboo, EQ, SopLeq, and Taboo Order) by 25 %. Prior to use of the heuristic, the multiple raters Kappa between the algorithms was 0.60 (95 % confidence interval, CI, from 0.53 to 0.67) indicating moderate agreement among the networks learned through different algorithms. After the use of the heuristic, the multiple raters Kappa was 0.85 (95 % CI from 0.78 to 0.92). There was a statistically significant increase in agreement between the five algorithms (alpha