Administrative Record Research Articles

Identifying Usability Challenges in Electronic Medication Administration Record Design Through Scenario-Based Evaluations: A Pilot Study

Hospitals have more incentives than ever to make nurse-facing technologies usable. However, the complexities of the nursing workflow are not supported by health information technology. This investigation aimed to identify usability challenges in a hospital system’s electronic medication administration record (eMAR). The research team developed scenarios that nurses completed using a simulated electronic health record. Data was qualitatively analyzed using the reflexive thematic analysis method. Three female medical-surgical nurses participated in the study. Qualitative analysis identified five themes in the data including: 1) essential information exists outside of the eMAR, 2) unable to view future medications, 3) information lost with unit transfer, 4) unable to document home medications, 5) certain medications delay sequential orders. Future usability evaluations of the eMAR should continue to look for poor usability, identify solutions, and consider the process for how individual hospitals can apply these usability evaluations to their own eMARs.

E-Connect: Linking probation youth at risk for suicide to behavioral health services.

Youth involved in the justice system (YIJ) have higher rates of suicidal thoughts and behaviors (STB) and associated behavioral health (BH) problems, yet lower levels of service use compared to youth in the general population. This study examined the efficacy of e-Connect, a digital clinical decision support system (CDSS), at improving STB risk identification, referral, and linkage to BH services by probation officers. As the intervention spanned pre- and post-COVID-19 shutdown periods, we also examined the disruption in public agencies' service provision on study outcomes. Administrative record data (1,488 youth, ages 10-18 years, 56% male, 56% White) allowed examination of differences between care-as-usual (baseline) and e-Connect in screening, identification of STB and BH problems, referral, and treatment initiation. Compared to care-as-usual, probation officers using e-Connect were over five times as likely to identify YIJ with STB (adjusted odds ratio [aOR] = 5.86; 95% confidence interval, CI [3.24, 11.7]) and over 11 times more likely to refer YIJ in need of BH services to treatment (aOR = 11.04; 95% CI [6.54, 19.43]). In turn, youth referred to treatment via e-Connect were nearly 17 times more likely to initiate (aOR = 16.92; 95% CI [9.17, 32.60]). Results remained unchanged during the pre- and post-COVID-19 shutdown periods. e-Connect is one of the first digital STB screening, referral, and linkage-to-service systems that use CDSS technology to successfully assist probation officers in linking youth on their caseload to treatment. Such an approach may support identification of STB and cross-systems linkage in other youth-serving organizations, such as schools, that increasingly manage youth BH problems with minimal clinical support. (PsycInfo Database Record (c) 2023 APA, all rights reserved).

Examining the ethical dilemmas of political impartiality in records administration: a phronetic approach

PurposeThis paper aims to explore the ethical dilemmas faced by records administrators concerning political impartiality by examining the case of the National Archives and Records Administration (NARA) in the USA, which has faced reputational challenges due to perceived political bias.Design/methodology/approachThis paper proposes a phronetic approach to resolve the ethical dilemmas associated with political impartiality in records administration. This approach emphasizes practical wisdom and ethical decision-making, offering a unique and effective way to address the challenges faced by presidential record archivists.FindingsThe proposed phronetic approach provides a means to resolve the ethical challenges posed by political impartiality in records administration, with a particular focus on NARA. By taking a transparent and impartial approach, agencies can minimize criticism and ensure their continued ability to equitably serve the public.Practical implicationsThe phronetic approach offers a framework for addressing ethical dilemmas related to political impartiality in records administration, with potential implications for other independent agencies facing similar challenges.Originality/valueThis paper offers a unique perspective on the ethical dilemmas of political impartiality in records administration and proposes a practical and effective approach to resolving these challenges. It contributes to the broader discussion on the intersection of ethics and public administration.

Metode Economic Order Quantity dalam Sistem Manajemen Stok Bandar Barang Bekas (SiBandar)

Junk goods are no longer piles of worthless goods for businessmen who are keen to see the economic value by taking this opportunity by becoming a pelapak company to buy and sell junk goods purchased from collectors to be sold to buyers. The problems found with Pelapak include the manual recording of sales administration which has the potential to cause recording errors. Pelapak does not know for sure the stock of junk they own and those owned by collectors because the locations of the collectors are far apart. Orders of junk goods between pelapak and collectors are still via telephone so pelapak does not know which collectors are in the process of sending goods. Problems also occur on the part of collectors including unprofessional sales transactions. Based on these problems, a used goods stock management system is needed using the Economic Order Quantity (EOQ) method. The purpose of this study is to build a used goods stock management information system that can monitor the availability of used goods owned by collectors and pelapak. System development uses the prototype method and designs with concepts. The results of the research are that the system created can help find out the stock and the amount in each collector, recap sales reports, provide accurate information, facilitate business transactions and fulfill sales targets to buyers.

Telemedicine and Telehealth Solutions

Telemedicine and telehealth solutions are witnessing a dramatic shift in the global healthcare sector at a time of unprecedented technological advancements. These innovative approaches are changing the way healthcare is delivered, increasing accessibility, efficacy, and patient-centeredness. Telemedicine has evolved as a powerful technique for overcoming the geographic limits that have long prohibited patients from obtaining high-quality medical treatment. Telemedicine allows patients and healthcare providers to connect without being physically separated, whether they are in crowded cities or remote rural regions. This technical breakthrough has improved patient outcomes while also allowing for the provision of emergency treatment during times of crisis and disaster. Patients may rapidly schedule online consultations, obtain medical advice, and receive tailored treatment plans. This degree of ease encourages patients to actively manage their health, strengthening the trust- and cooperation-based doctor-patient relationship. Telehealth technologies play a critical role in improving healthcare accessible in areas with inadequate healthcare infrastructure. Medical expertise may be extended to underserved areas using telemedicine platforms, allowing professionals to consult, diagnose, and treat patients who would otherwise face major hurdles to timely medical care. Furthermore, telemedicine programs have shown to be critical in delivering mental health care, particularly in areas where mental health resources are few. The combination of telemedicine and telehealth technology has transformed the delivery of healthcare services. Remote patient monitoring gadgets and wearable technology have enabled healthcare practitioners to continually monitor their patients' health state, allowing them to discover possible issues early and respond proactively. Furthermore, telemedicine has simplified medical record administration, improved care coordination, and reduced medical mistakes. While the advantages of telemedicine solutions are obvious, difficulties remain. These include worries about data security, privacy, and the need for regulatory frameworks to properly control telemedicine operations. Addressing these issues would need the collaboration of governments, healthcare institutions, and technology suppliers. We can establish a safe atmosphere for telehealth solutions to thrive by creating strong rules and guidelines. Telemedicine and telehealth have emerged as viable options for addressing Pakistan's healthcare concerns. With a rising population and restricted access to medical facilities, these revolutionary technologies are reshaping the country's healthcare scene. Telemedicine connects patients from rural and underprivileged locations with healthcare specialists via virtual consultations, allowing for quick diagnosis and treatment suggestions [1]. Furthermore, telehealth efforts enable people to take an active role in their health management by putting medical information and services at their fingertips. Despite certain infrastructure and regulatory difficulties, the use of telemedicine and telehealth in Pakistan has enormous potential to improve healthcare access and patient outcomes across the country.

20-Year trends of hospitalisation among people with dementia: a region-wide retrospective cohort study from Lombardy, Italy

ObjectivesThe aim of this study was to investigate the trends of hospitalisations among people with dementia, linking region-wide hospital and demographic health records. Study designA retrospective cohort study was conducted using hospitalisation health records from the Lombardy region in Italy. MethodsThe study included people aged ≥65 years with a diagnosis of dementia who were hospitalised between 2002 and 2020 in Lombardy, which is the most populated region in Italy with 10 million inhabitants. Using data on resident population, this study computed rates of hospitalisation by calendar year, age, sex and cause of hospitalisation. ResultsIn total, 340,144 hospitalised patients with dementia were included in the study. The rate of hospitalisation was 100.6 per 10,000 in 2002 and progressively decreased to 65.1 per 10,000 in 2020. The average age at hospitalisation in 2002 was 78.9 years for men and 81.8 years for women, which increased to 82.0 years and 84.2 years, respectively, in 2020. Respiratory diseases caused 10.4% of all hospitalisations in 2002 and grew steadily to 26.8% in 2020, becoming the leading cause of hospital admissions since 2017. ConclusionsHospitalisation patterns for people with dementia have changed over the last 20 years, reflecting evolving epidemiological trends and the impact of healthcare policies. Region-wide administrative health record data analysis should be further utilised to explore the health needs of people with dementia and inform the planning, implementation and monitoring of effective prevention strategies in this population group.

Defining career success: A cross-sectional analysis of health information managers' perceptions.

Career success can be defined as the accomplishment of desirable outcomes in an individual's work experiences. It can be divided into objective and subjective career success. Objective success refers to tangible and measurable outcomes such as promotions and position titles. Subjective career success relates to an individual's interpretations of their success or accomplishments. The career success of health information management professionals has not been explored in the literature. To determine the indicators of career success as reported by health information managers (HIMs) and identify whether there are any differences based on length of time in the profession. Using a cross-sectional study design, an online survey was administered to a sample of La Trobe University and Lincoln Institute of Health Sciences Medical Record Administration and Health Information Management graduates from 1985, 1995, 2005 and 2015, which included the following question: "How would you define success in your career?" Almost 88% (n = 63) of overall participants in the study responded to this item. Subjective factors (n = 77) of career success, compared to objective factors (n = 22), were more common. The categories of recognition (feeling valued/appreciated), job satisfaction and feelings of accomplishment/sense of achievement were commonly reported. Subjective factors of an individual's career success were deemed to be more significant than objective factors among HIMs. Factors such as recognition and appreciation at work, job satisfaction, fostering high-quality work outputs and creating a sense of achievement should be the major foci for managers, organisations and individuals.

Comorbidity and polypharmacy impact neurobehavioral symptoms and symptom validity failure among post-9/11 veterans with mild traumatic brain injury.

The study aimed to examine the association between post-concussive comorbidity burdens [post-traumatic stress disorder (PTSD), depression, and/or headache] and central nervous system (CNS) polypharmacy (five or more concurrent medications) with reported neurobehavioral symptoms and symptom validity screening among post-9/11 veterans with a history of mild traumatic brain injury (mTBI). Administrative medical record data from the Department of Veterans Affairs (VA) were used in the study. Post-9/11 veterans with mTBI and at least 2 years of VA care between 2001 and 2019 who had completed the comprehensive traumatic brain injury evaluation (CTBIE) were included in the study. Retrospective cross-sectional design was used in the study. Neurobehavioral Symptom Inventory (NSI), International Classification of Diseases, Ninth Revision, and Clinical Modification diagnosis codes were included in the study. Of the 92,495 veterans with a history of TBI, 90% had diagnoses of at least one identified comorbidity (PTSD, depression, and/or headache) and 28% had evidence of CNS polypharmacy. Neurobehavioral symptom reporting and symptom validity failure was associated with comorbidity burden and polypharmacy after adjusting for sociodemographic characteristics. Veterans with concurrent diagnoses of PTSD, depression, and headache were more than six times more likely [Adjusted odds ratio = 6.55 (99% CI: 5.41, 7.92)]. to fail the embedded symptom validity measure (Validity-10) in the NSI. TBI-related multimorbidity and CNS polypharmacy had the strongest association with neurobehavioral symptom distress, even after accounting for injury and sociodemographic characteristics. Given the regular use of the NSI in clinical and research settings, these findings emphasize the need for comprehensive neuropsychological evaluation for individuals who screen positively for potential symptom overreporting, the importance of multidisciplinary rehabilitation to restore functioning following mTBI, and the conscientious utilization of symptom validity measures in research efforts.

Outcomes after definitive radiation therapy for localized prostate cancer in a national health care delivery system.

Accurate information regarding real-world outcomes after contemporary radiation therapy for localized prostate cancer is important for shared decision-making. Clinically relevant end points at 10years among men treated within a national health care delivery system were examined. National administrative, cancer registry, and electronic health record data were used for patients undergoing definitive radiation therapy with or without concurrent androgen deprivation therapy within the Veterans Health Administration from 2005 to 2015. National Death Index data were used through 2019 for overall and prostate cancer-specific survival and identified date of incident metastatic prostate cancer using a validated natural language processing algorithm. Metastasis-free, prostate cancer-specific, and overall survival using Kaplan-Meier methods were estimated. Among 41,735 men treated with definitive radiation therapy, the median age at diagnosis was 65years and median follow-up was 8.7years. Most had intermediate (42%) and high-risk (33%) disease, with 40% receiving androgen deprivation therapy as part of initial therapy. Unadjusted 10-year metastasis-free survival was 96%, 92%, and 80% for low-, intermediate-, and high-risk disease. Similarly, unadjusted 10-year prostate cancer-specific survival was 98%, 97%, and 90% for low-, intermediate-, and high-risk disease. The unadjusted overall survival was lower across increasing disease risk categories at 77%, 71%, and 62% for low-, intermediate-, and high-risk disease (p<.001). These data provide population-based 10-year benchmarks for clinically relevant end points, including metastasis-free survival, among patients with localized prostate cancer undergoing radiation therapy using contemporary techniques. The survival rates for high-risk disease in particular suggest that outcomes have recently improved.

Pendampingan dan Implementasi Aplikasi Bank Sampah Pada TPS-3R Banjar Bonjaka

Garbage is a common problem that needs serious attention. Waste problems can have an impact on public health and environmental health. The local governments and community's form of effort in dealing with waste problems is the formation of TPS-3R by applying the concept of reduce, reuse, and recycle. Implementing the TPS-3R Institution requires proper management with the support of information technology. One of the TPS-3Rs located in the Gianyar – Bali area is TPS-3R Banjar Bonjaka which provides waste processing services for 345 households. The problem encountered during the observation was the manual recording of TPS-3R operational activities. The recording is currently only in the form of a physical book which carries the risk of errors, loss of records, and physical damage. Thus, in carrying out community service activities, it is proposed to provide assistance activities and implement the Garbage Bank application for TPS-3R managers. Community service activities aim to increase the ability to use information technology to manage TPS-3R. Thus, it can help optimize administrative governance. The activity was carried out for one day and attended by 10-15 participants. The evaluation of community service activities shows that participants have been able to input or manage data in the waste bank application. Achievement of abilities is a benchmark for the success of community service activities, with a success percentage of around 80-90%. This activity's benefit is facilitating administrative recording and management of TPS-3R activities by implementing the waste bank application.

Effect on life expectancy of temporal sequence in a multimorbidity cluster of psychosis, diabetes, and congestive heart failure among 1·7 million individuals in Wales with 20-year follow-up: a retrospective cohort study using linked data

To inform targeted public health strategies, it is crucial to understand how coexisting diseases develop over time and their associated impacts on patient outcomes and health-care resources. This study aimed to examine how psychosis, diabetes, and congestive heart failure, in a cluster of physical-mental health multimorbidity, develop and coexist over time, and to assess the associated effects of different temporal sequences of these diseases on life expectancy in Wales. In this retrospective cohort study, we used population-scale, individual-level, anonymised, linked, demographic, administrative, and electronic health record data from the Wales Multimorbidity e-Cohort. We included data on all individuals aged 25 years and older who were living in Wales on Jan 1, 2000 (the start of follow-up), with follow-up continuing until Dec 31, 2019, first break in Welsh residency, or death. Multistate models were applied to these data to model trajectories of disease in multimorbidity and their associated effect on all-cause mortality, accounting for competing risks. Life expectancy was calculated as the restricted mean survival time (bound by the maximum follow-up of 20 years) for each of the transitions from the health states to death. Cox regression models were used to estimate baseline hazards for transitions between health states, adjusted for sex, age, and area-level deprivation (Welsh Index of Multiple Deprivation [WIMD] quintile). Our analyses included data for 1 675 585 individuals (811 393 [48·4%] men and 864 192 [51·6%] women) with a median age of 51·0 years (IQR 37·0-65·0) at cohort entry. The order of disease acquisition in cases of multimorbidity had an important and complex association with patient life expectancy. Individuals who developed diabetes, psychosis, and congestive heart failure, in that order (DPC), had reduced life expectancy compared with people who developed the same three conditions in a different order: for a 50-year-old man in the third quintile of the WIMD (on which we based our main analyses to allow comparability), DPC was associated with a loss in life expectancy of 13·23 years (SD 0·80) compared with the general otherwise healthy or otherwise diseased population. Congestive heart failure as a single condition was associated with mean a loss in life expectancy of 12·38 years (0·00), and with a loss of 12·95 years (0·06) when preceded by psychosis and 13·45 years (0·13) when followed by psychosis. Findings were robust in people of older ages, more deprived populations, and women, except that the trajectory of psychosis, congestive heart failure, and diabetes was associated with higher mortality in women than men. Within 5 years of an initial diagnosis of diabetes, the risk of developing psychosis or congestive heart failure, or both, was increased. The order in which individuals develop psychosis, diabetes, and congestive heart failure as combinations of conditions can substantially affect life expectancy. Multistate models offer a flexible framework to assess temporal sequences of diseases and allow identification of periods of increased risk of developing subsequent conditions and death. Health Data Research UK.

Perioperative Dexamethasone Does Not Reduce Postoperative Opioid Use Following Anterior Cervical Discectomy and Fusion

(1) To determine whether dexamethasone administration reduced narcotic consumption during hospitalization and (2) to evaluate if patients who received dexamethasone refilled fewer opioid prescriptions postoperatively. We retrospectively identified all adult patients who underwent primary elective 1-4-level ACDF at a single center. Prescription opioid use was collected from governmental online prescription drug monitoring programs and in-hospital opioids were collected from each patient's medication administration record and recorded as milligrams of morphine equivalents (MMEs). Patients were categorized by whether or not intravenous dexamethasone was administered perioperatively. Dexamethasone protocols were considered high dose if weight-based dosing was >0.20 mg/kg and low-dose if <0.20 mg/kg Multivariable linear regression was conducted accounting confounders to assess the relationship between dexamethasone administration and MME prescribed at each time point. We included 249 patients, 167 (67%) of whom were administered dexamethasone. Patients in both groups utilized a similar quantity of opioids while hospitalized (no dexamethasone: 56.7 vs. dexamethasone: 39.4 MME/day, p=0.3499). Patients in both groups refilled a similar quantity of opioids in all postoperative time periods; 0-3 week (3.38 vs. 4.07 MME/day, p=0.5277), 3-6 week (0.36 vs. 0.75 MME/day, p=0.1979), 6-12 week (0.53 vs. 0.75MME/day, p=0.9000), and 3-month to one-year (0.28 vs. 0. MME/day, p=0.5310). On multivariable linear regression, dexamethasone was not associated with a reduction in opioid volume at any time point (all p>0.05). Administration of perioperative dexamethasone does not reduce in-hospital or home opioid usage regardless of weight-based dose. Analgesia should not be the primary driver of dexamethasone administration for ACDF.

Weak State as a Security Threat: Study Case of El Salvador (2014-2019)

Weak State as a Security Threat: Study Case of El Salvador (2014-2019)

Comparison of Analgesic Effect of Intravenous Paracetamol with Intravenous Ketorolac in Patients Presenting With Renal Colic in the Emergency Department

Objective: To compare the effects of intravenous (IV) Paracetamol and intravenous (IV) Ketorolac in pain management of patients with renal colic presenting to the emergency department (ED).&#x0D; Study Design: Quasi-experimental study.&#x0D; Place and Duration of Study: Emergency Department, Combined Military Hospital, Rawalpindi Pakistan, from Jan to Jul 2021.&#x0D; Methodology: Eighty patients were included in the study who were selected and divided into two groups, one receiving Paracetamol 1 g intravenous (PC-Group) and the other receiving Ketorolac 30 mg IV (KET-Group). Their effect was compared using differences in visual analogue scale (VAS) before and after giving analgesia. Record of vital signs pre and post-drug administration, adverse effects and need for rescue analgesia was maintained (Nalbuphine). If further analgesia was required, 100 mg intravenous was used as the rescue drug.&#x0D; Results: Ketorolac (KET) Group had a mean age of 37.60±14.56 years, while the Paracetamol (PC) Group had a mean age of 43.2 ± 16.05 years. There was no statistically significant difference in the reduction of pain intensity after giving the drug in the respective study Groups (p=0.09). Adverse effects (p=0.17) and the need for rescue analgesia (p=0.34) were also comparable between the two Groups.&#x0D; Conclusion: The use of either intravenous-PC or intravenous-KET in patients with renal colic had similar analgesic effects with no significant difference in side effects and need for rescue analgesia.

Children’s Indirect Exposure to the U.S. Justice System: Evidence From Longitudinal Links between Survey and Administrative Data

Abstract Children’s indirect exposure to the justice system through biological parents or coresident adults is both a marker of their own vulnerability and a measure of the justice system’s expansive reach in society. Estimating the size of this population for the United States has historically been hampered by inadequate data resources, including the inability to observe nonincarceration events, follow children throughout their childhood, and measure adult nonbiological parent cohabitants. To overcome these challenges, we leverage billions of restricted administrative and survey records linked with Criminal Justice Administrative Records System data and find substantially larger exposure rates than previously reported: prison, 9% of children born between 1999–2005; felony conviction, 18%; and any criminal charge, 39%. Charge exposure rates exceed 60% for Black, American Indian, and low-income children. While broader definitions reach a more expansive population, strong and consistently negative correlations with childhood well-being suggest that these remain valuable predictors of vulnerability. Finally, we document substantial geographic variation in exposure, which we leverage in a movers design to estimate the effect of living in a high-exposure county during childhood. We find that children moving into high-exposure counties are more likely to experience postmove exposure events and exhibit significantly worse outcomes by age 26 on multiple dimensions (earnings, criminal activity, teen parenthood, mortality); effects are strongest for those who moved at earlier ages.

Understanding Heterogeneity in the Impact of Public Preschool Programs.

We examine the North Carolina Pre-K (NC Pre-K) program to test the hypothesis that observed variation in effects resulting from exposure to the program can be attributed to interactions with other environmental factors that occur before, during, or after the pre-k year. We examine student outcomes in 5th grade and test interaction effects between NC's level of investment in public pre-k and moderating factors. Our main sample includes the population of children born in North Carolina between 1987 and 2005 who later attended a public school in that state, had valid achievement data in 5th grade, and could be matched by administrative record review (n = 1,207,576; 58% White non-Hispanic, 29% Black non-Hispanic, 7% Hispanic, 6% multiracial and Other race/ethnicity). Analyses were based on a natural experiment leveraging variation in county-level funding for NC Pre-K across NC counties during each of the years the state scaled up the program. Exposure to NC Pre-K funding was defined as the per-4-year-old-child state allocation of funds to a county in a year. Regression models included child-level and county-level covariates and county and year fixed effects. Estimates indicate that a child's exposure to higher NC Pre-K funding was positively associated with that child's academic achievement 6 years later. We found no effect on special education placement or grade retention. NC Pre-K funding effects on achievement were positive for all subgroups tested, and statistically significant for most. However, they were larger for children exposed to more disadvantaged environments either before or after the pre-k experience, consistent with a compensatory model where pre-k provides a buffer against the adverse effects of prior negative environmental experiences and protection against the effects of future adverse experiences. In addition, the effect of NC Pre-K funding on achievement remained positive across most environments, supporting an additive effects model. In contrast, few findings supported a dynamic complementarity model. Instrumental variables analyses incorporating a child's NC Pre-K enrollment status indicate that program attendance increased average 5th grade achievement by approximately 20% of a standard deviation, and impacts were largest for children who were Hispanic or whose mothers had less than a high school education. Implications for the future of pre-k scale-up and developmental theory are discussed.

Cross-functional workflows for digital projects in a small academic library: A case study

In 2021, Union College’s Schaffer Library received a National Historical Publications and Records Commission grant from the National Archives and Records Administration to digitise and make accessible a large, and highly requested, collection of materials from one of the institution’s most famous alumni, John Bigelow. Collaborating with the department of Special Collections and Archives, the department of Content and Digital Library Systems had to quickly transform workflows for what had been mostly ad hoc projects into workflows that supported production-level scanning, metadata and digital collection output. In service to this output, a search was made for a new digital space to accommodate the size and robust description of the collection. As Union is a small liberal arts college, the project team also hired an unorthodox group of people to handle and scan the archival material: their undergraduate students. This paper introduces the backgrounds of the collection and the grant; illustrates the various work plans and workflows of the processes; and discusses challenges and opportunities encountered along the way. Brief descriptions of concurrent digital projects related to the grant are also given.

Misclassification and Bias in Predictions of Individual Ethnicity from Administrative Records

We show that a common method of predicting individuals’ race in administrative records, Bayesian Improved Surname Geocoding (BISG), produces misclassification errors that are strongly correlated with demographic and socioeconomic factors. In addition to the high error rates for some racial subgroups, the misclassification rates are correlated with the political and economic characteristics of a voter’s neighborhood. Racial and ethnic minorities who live in wealthy, highly educated, and politically active areas are most likely to be misclassified as white by BISG. Inferences about the relationship between sociodemographic factors and political outcomes, like voting, are likely to be biased in models using BISG to infer race. We develop an improved method in which the BISG estimates are incorporated into a machine learning model that accounts for class imbalance and incorporates individual and neighborhood characteristics. Our model decreases the misclassification rates among non-white individuals, in some cases by as much as 50%.

Use of high cost care among Veterans with comorbid mental illness and Alzheimer's Disease and related dementias.

Alzheimer's Disease and Other Related Dementias (AD/ADRD) leads to frequent emergency department (ED) and inpatient use. Mental health symptoms among persons with AD/ADRD increases cognitive and functional disabilities and could contribute to these high rates of intensive health care use. The objective of this paper is to assess the relationship of mental illness on 12-month patterns in hospitalization and ED use among Veterans aged 65 and over with a new AD/ADRD diagnosis. We used an existing dataset of administrative electronic health record data of Veterans with AD/ADRD from the US Veterans Health Administration linked with Medicare claims data from 2011-2015. We use multivariable logistic regression to examine the association between no pre-existing mental illness, pre-existing mental illness (e.g., major depressive disorder, generalized anxiety disorder, or post-traumatic stress disorder), and pre-existing severe mental illness-or SMI-(e.g., bipolar disorder, major depressive disorder with psychosis, or schizophrenia) and 12- month ED and hospitalization use and readmissions among Veterans who had an initial hospitalization visit. We estimated predicted probabilities, differential effect, and associated 95% confidence intervals. In our sample, 1.4% had SMI and 11% had non-SMI mental illness. The unadjusted percentage with inpatient and ED use was higher among Veterans with SMI (34% and 26%, respectively) and Veterans with non-SMI mental illness (20%, 16%) compared with Veterans without pre-existing mental illness (12%, 9%). Compared to individuals with no pre-existing mental illness, having a pre-existing mental illness (1.27 percentage points, 95% CI: 0.76, 1.78) and a pre-existing SMI (7.17 percentage points, 95% CI: 5.66, 8.69) were both associated with an increased likelihood of ED use. The same pattern was observed for any inpatient use (mental illness 2.18, 95% CI: 1.59, 2.77; SMI 9.91, 95% CI: 8.21, 11.61). Only pre-existing SMI was associated higher hospitalization readmission. Pre-existing mental illness increases use of high cost, intensive health care and this association is higher of more severe mental health conditions. We also show that pre-existing mental illness exerts a unique influence, above and beyond other comorbidities, such as diabetes, on ED and inpatient visits. More needs to be done to increase recognition of the unique risks of this combination of health conditions and encourage strategies to address them. Developing, testing, and implementing comprehensive strategies that address the intersection of ADRD and mental illness is promising approach that requires more focused attention.

Pharmacophenotype identification of intensive care unit medications using unsupervised cluster analysis of the ICURx common data model

BackgroundIdentifying patterns within ICU medication regimens may help artificial intelligence algorithms to better predict patient outcomes; however, machine learning methods incorporating medications require further development, including standardized terminology. The Common Data Model for Intensive Care Unit (ICU) Medications (CDM-ICURx) may provide important infrastructure to clinicians and researchers to support artificial intelligence analysis of medication-related outcomes and healthcare costs. Using an unsupervised cluster analysis approach in combination with this common data model, the objective of this evaluation was to identify novel patterns of medication clusters (termed ‘pharmacophenotypes’) correlated with ICU adverse events (e.g., fluid overload) and patient-centered outcomes (e.g., mortality).MethodsThis was a retrospective, observational cohort study of 991 critically ill adults. To identify pharmacophenotypes, unsupervised machine learning analysis with automated feature learning using restricted Boltzmann machine and hierarchical clustering was performed on the medication administration records of each patient during the first 24 h of their ICU stay. Hierarchical agglomerative clustering was applied to identify unique patient clusters. Distributions of medications across pharmacophenotypes were described, and differences among patient clusters were compared using signed rank tests and Fisher's exact tests, as appropriate.ResultsA total of 30,550 medication orders for the 991 patients were analyzed; five unique patient clusters and six unique pharmacophenotypes were identified. For patient outcomes, compared to patients in Clusters 1 and 3, patients in Cluster 5 had a significantly shorter duration of mechanical ventilation and ICU length of stay (p < 0.05); for medications, Cluster 5 had a higher distribution of Pharmacophenotype 1 and a smaller distribution of Pharmacophenotype 2, compared to Clusters 1 and 3. For outcomes, patients in Cluster 2, despite having the highest severity of illness and greatest medication regimen complexity, had the lowest overall mortality; for medications, Cluster 2 also had a comparably higher distribution of Pharmacophenotype 6.ConclusionThe results of this evaluation suggest that patterns among patient clusters and medication regimens may be observed using empiric methods of unsupervised machine learning in combination with a common data model. These results have potential because while phenotyping approaches have been used to classify heterogenous syndromes in critical illness to better define treatment response, the entire medication administration record has not been incorporated in those analyses. Applying knowledge of these patterns at the bedside requires further algorithm development and clinical application but may have the future potential to be leveraged in guiding medication-related decision making to improve treatment outcomes.