Effect of coercive measures on mental health status in adult psychiatric populations: a nationwide trial emulation.

AIMS: Healthcare staff use coercive measures to manage patients at acute risk of harm to self or others, but their effect on patients' mental health is underexplored. This nationwide Swiss study emulated a trial to investigate the effects of coercive measures on the mental health of psychiatric inpatients at discharge. METHODS: We analysed retrospective longitudinal data from all Swiss adult psychiatric hospitals that provided acute care (2019-2021). The primary exposure was any coercive measure during hospitalization; secondary exposures were seclusion, restraint and forced medication. Our primary outcome was Health of the Nations Outcome Scale (HoNOS) score at discharge. We used inverse probability of treatment weighting to emulate random assignment to the exposure. RESULTS: Of 178,369 hospitalizations, 9.2% (n = 18,800) included at least one coercive measure. In patients exposed to coercive measures, mental health worsened a small but statistically significant amount more than in non-exposed patients. Those who experienced at least one coercive measure during hospitalization had a significantly higher HoNOS score (1.91-point, p < .001, 95% confidence interval [CI]: 1.73; 2.09) than those who did not experience any coercive measure. Results were similar for seclusion (1.60-point higher score, p < .001, 95% CI: 1.40; 1.79) and forced medication (1.97-point higher score, p < .001, 95% CI: 1.65; 2.30). Restraint had the strongest effect (2.83-point higher score, p < .001, 95% CI: 2.38; 3.28). CONCLUSIONS: Our study presents robust empirical evidence highlighting the detrimental impact of coercive measures on the mental health of psychiatric inpatients. It underscores the importance of avoiding these measures in psychiatric hospitals and emphasized the urgent need for implementing alternatives in clinical practice.

The Effect of Mask Use on Seasonal Virus Diversity in SARS CoV-2 Negative Patients Treated as Inpatients During the 2021-2022 and 2022-2023 Seasonal Flu Period.

The study aimed to explore the protective effect of mask use against respiratory tract viral agents during the pandemic. The study included patients with a COVID-19 negative test who were hospitalized in the pulmonary disease clinic with the diagnoses of asthma attack, chronic obstructive pulmonary disease (COPD) exacerbation, and pneumonia in two periods: during mandatory mask use (October 2021 - May 2022) and after the mask mandate was lifted (October 2022 - May 2023). Combined nose and throat swab samples taken from the patients were evaluated for viral agents by using the PCR test method. Viral agents isolated from the patients in the two periods were compared based on hospitalization diagnoses and periods. The study enrolled 1,335 patients, 483 female and 852 male. It was found that viral agents significantly increased during the period without a mask mandate compared to the period when the mask mandate was in effect (41.6% vs. 23.4%) (p < 0.001). During the period without mask mandate, influenza A, H1N1, and RSV/AB viruses significantly increased (p = 0.019, p = 0.003, p < 0.001, respectively). Our results indicated that mask use during the pandemic is protective against the transmission of respiratory tract viruses. Thus, it can be concluded that mask use is important not only in the coronavirus pandemic but also especially in influenza and RSV epidemics.

Association between polypharmacy and 2-year outcomes among Chinese older inpatients: a multi-center cohort study.

BACKGROUND: The escalating global prevalence of polypharmacy presents a growing challenge to public health. In light of this issue, the primary objective of our study was to investigate the status of polypharmacy and its association with clinical outcomes in a large sample of hospitalized older patients aged 65 years and over. METHODS: A two-year prospective cohort study was carried out at six tertiary-level hospitals in China. Polypharmacy was defined as the prescription of 5 or more different medications daily, including over-the-counter and non-prescription medications. Baseline polypharmacy, multimorbidity, and other variables were collected when at admission, and 2-year outcomes were recorded by telephone follow-up. We used multivariate logistic regression analysis to examine the associations between polypharmacy and 2-year outcomes. RESULTS: The overall response rate was 87.2% and 8713 participants were included in the final analysis. The mean age was 72.40 years (SD = 5.72), and women accounted for 42.2%. The prevalence of polypharmacy among older Chinese inpatients is 23.6%. After adjusting for age, sex, education, marriage status, body mass index, baseline frailty, handgrip strength, cognitive impairment, and the Charlson comorbidity index, polypharmacy is significantly associated with frailty aggravation (OR 1.432, 95% CI 1.258-1.631) and mortality (OR 1.365, 95% CI 1.174-1.592), while inversely associated with readmission (OR 0.870, 95% CI 0.764-0.989). Polypharmacy was associated with a 35.6% increase in the risk of falls (1.356, 95%CI 1.064-1.716). This association weakened after adjustment for multimorbidity to 27.3% (OR 1.273, 95%CI 0.992-1.622). CONCLUSIONS: Polypharmacy was prevalent among older inpatients and was a risk factor for 2-year frailty aggravation and mortality. These results highlight the importance of optimizing medication use in older adults to minimize the risks associated with polypharmacy. Further research and implementing strategies are warranted to enhance the quality of care and safety for older individuals exposed to polypharmacy. TRIAL REGISTRATION: Chinese Clinical Trial Registry, ChiCTR1800017682, registered 09/08/2018.

Patient satisfaction and associated factors with inpatient health services at public hospitals in Ethiopia: a systematic review and meta-analysis.

BACKGROUND: The way the healthcare delivery system is reflected by patient satisfaction. Establishing a health system with better results depends on it. It has been assumed that higher patient satisfaction levels correlate with quality healthcare outcomes. There is little national data to support patient satisfaction with inpatient health services in Ethiopia. In order to estimate the pooled proportion of patient satisfaction and determine the associated factors with inpatient health services at public hospitals, a systematic review and meta-analysis were conducted. METHODS: The Preferred Reporting Items for Systematic Review and Meta-Analysis (PRISMA) guidelines were followed in the extraction of the data. To get the included studies, the following electronic databases were searched: Pub-Med, Google Scholar, Med-Line, Web of Science, Scopus and Repositories. Software called STATA version 17 was used to analyze statistical data using the random effects model. Forest plots were used to display the pooled results. RESULTS: Of the 1583 records resulted in electronic databases searching, 11 studies with 3,958 participants were included in this systematic review and meta-analysis. The estimated pooled proportion of patient satisfaction with inpatient health services was found to be 57.4% (95% CI: 50.88-64.59, I2 = 95.25%). Assuring privacy for patients (OR = 7.44, 95% CI: 3.63-15.25, I2 = 0.0%), availability of direction signs (2.96, 95% CI: 1.91-4.57, I2 = 0.0%), providing adequate information (OR = 3.27, 95% CI: 1.63-6,58, I2 = 65.60%), history of previous admission (OR = 0.29, 0.18-0.46, I2 = 86.36%) and providing on time treatment (OR = 1.63, 95% CI: 1.21-2.20, I2 = 86.36%) were statistically significant factors associated with patient satisfaction with inpatient health services. CONCLUSION: The estimated pooled level of patient satisfaction with inpatient health services is low in Ethiopia. A higher level of patient satisfaction with inpatient health treatments was predicted by factors such as privacy assurance, fast services, availability of direction signs, provision of services with adequate information transfer, and no history of previous admission. To improve patient satisfaction, the Ministry of Health and hospital administration must place a strong emphasis on ensuring the provision of high-quality, standard-based inpatient healthcare.

Investigation of functional constipation in elderly inpatients and analysis of its influencing factors: A cross-sectional study.

To investigate the prevalence of functional constipation (FC) in elderly hospitalized patients and analyze the influencing factors. This was a cross-sectional study in which 506 patients hospitalized in general surgery from February to June 2020 were selected. Information on patients' age, gender, ethnicity, body mass index, intake of vegetables, fruits, meat, and spicy foods, sleep, smoking, alcohol consumption, time of defecation, and mode of defecation was collected through questionnaires, and the factors affecting functional constipation were analyzed using binary logistic regression models; among 506 patients, 254 had FC, with a prevalence of 50.19%. Among the clinical symptoms of FC, the most common ones were straining to defecate (83.85%) and lumpy or hard stools (81.80%). Univariate analysis revealed statistically significant differences in family history of constipation (P = .033), sedentary (P = .004), self-care ability (P = .001), body mass index (P = .013), defecation time (P < .0001), spicy food intake in dietary preference (P = .001), age (P = .004), and education level (P = .016), and binary logistic regression analysis showed that defecation time and spicy food consumption were independent influencing factors of FC. For hospitalized elderly people, regular morning defecation and not eating spicy foods can more helpful to slow the occurrence of functional constipation.

Nomogram for predicting the risk of nosocomial infections among obstetric inpatients: a large-scale retrospective study in China.

OBJECTIVE: This study aimed to develop and validate a nomogram for assessing the risk of nosocomial infections among obstetric inpatients, providing a valuable reference for predicting and mitigating the risk of postpartum infections. METHODS: A retrospective observational study was performed on a cohort of 28,608 obstetric patients admitted for childbirth between 2017 and 2022. Data from the year 2022, comprising 4,153 inpatients, were utilized for model validation. Univariable and multivariable stepwise logistic regression analyses were employed to identify the factors influencing nosocomial infections among obstetric inpatients. A nomogram was subsequently developed based on the final predictive model. The receiver operating characteristic (ROC) curve was utilized to calculate the area under the curve (AUC) to evaluate the predictive accuracy of the nomogram in both the training and validation datasets. RESULTS: The gestational weeks > = 37, prenatal anemia, prenatal hypoproteinemia, premature rupture of membranes (PROM), cesarean sction, operative delivery, adverse birth outcomes, length of hospitalization (days) > 5, CVC use and catheterization of ureter were included in the ultimate prediction model. The AUC of the nomogram was 0.828 (0.823, 0.833) in the training dataset and 0.855 (0.844, 0.865) in the validation dataset. CONCLUSION: Through a large-scale retrospective study conducted in China, we developed and independently validated a nomogram to enable personalized postpartum infections risk estimates for obstetric inpatients. Its clinical application can facilitate early identification of high-risk groups, enabling timely infection prevention and control measures.

Alcohol use disorder is associated with a lower risk of in-hospital mortality in type A aortic dissection repair: a population-based study of National Inpatient Sample from 2015-2020.

BACKGROUND: While alcohol consumption is implicated in the development of aortic dissection, the impact of alcohol use disorder (AUD) on the outcomes of type A aortic dissection (TAAD) repair is still largely unexplored. This study aimed to conduct a comprehensive, population-based analysis of effect of AUD on in-hospital outcomes following TAAD repair using National/Nationwide Inpatient Sample, the largest all-payer database in the United States. METHODS: Patients undergoing TAAD repair were identified in National/Nationwide Inpatient Sample from Q4 2015-2020. Demographics, comorbidities, hospital characteristics, primary payer status, and transfer-in status between patients with and without AUD were matched by a 1:3 propensity-score matching. In-hospital outcomes were examined. RESULTS: There were 220 patients with AUD who underwent TAAD repair. Meanwhile, 4062 non-AUD patients went under TAAD repair, where 646 of them were matched to all AUD patients. After propensity-score matching, AUD patients had a lower risk of in-hospital mortality (7.76% vs 13.31%, P = 0.03) while there was no difference in transfer-in status or time from admission to operation. However, patients with AUD had a higher rate of respiratory complications (27.40% vs 19.66%, P = 0.02) and a longer hospital length of stay (16.20 ± 11.61 vs 11.72 ± 1.69 days, P = 0.01). All other in-hospital outcomes were comparable between AUD and non-AUD patients. CONCLUSION: AUD patients had a lower risk of in-hospital mortality but a higher rate of respiratory complications and a longer LOS. These findings can provide insights into preoperative risk stratification of these patients. Nonetheless, reasons underlying the lower mortality rate in AUD patients and their long-term prognosis require further investigation.

Experiences of Inpatient Healthcare Services Among Children With Medical Complexity and Their Families: A Scoping Review.

BACKGROUND: Children with medical complexity (CMC) have high healthcare utilization and face unique challenges during hospital admissions. The evidence describing their experiences of inpatient care is distributed across disciplines. The aim of this scoping review was to map the evidence related to the inpatient experience of care for CMC and their families, particularly related to key aspects and methodological approaches, and identify gaps that warrant further study. METHODS: This scoping review was conducted in accordance with JBI methodology and included all studies that reported experiences of acute hospital care for CMC/families. All study designs were included. Databases searched included EMBASE, CINAHL Plus with Full Text, Web of Science, MEDLINE(R) and APA PsycInfo from 2000 to 2022. Details about the participants, concepts, study methods and key findings were abstracted using a data abstraction tool. A thematic analysis was conducted. RESULTS: Forty-nine papers were included: 27 qualitative studies, 10 quantitative studies, six mixed methods studies, two descriptive studies and four reviews. Some quantitative studies used validated instruments to measure experience of care, but many used non-validated surveys. There were a few interventional studies with a small sample size. Results of thematic analysis described the importance of negotiating care roles, shared decision-making, common goal setting, relationship-building, communication, sharing expertise and the hospital setting itself. CONCLUSION: CMC and families value relational elements of care and partnering through sharing expertise, decision-making and collaborative goal-setting when admitted to hospital. PATIENT OR PUBLIC CONTRIBUTION: This review was conducted in alignment with the principles of patient and family engagement. The review was conceptualized, co-designed and conducted with the full engagement of the project's parent-partner. This team member was involved in all stages from constructing the review question, to developing the protocol, screening articles and drafting this manuscript.

Interventions for smoking cessation in inpatient psychiatry settings.

OBJECTIVES: This is a protocol for a Cochrane Review (intervention). The objectives are as follows: To assess the effects of smoking cessation interventions on tobacco smoking in adults receiving inpatient psychiatry treatment. To assess whether the effects of smoking cessation interventions differ according to psychiatric diagnosis or type of intervention or comparator condition.

Monitoring postures and motions of hospitalized patients using sensor technology: a scoping review.

BACKGROUND: Sensor technology could provide solutions to monitor postures and motions and to help hospital patients reach their rehabilitation goals with minimal supervision. Synthesized information on device applications and methodology is lacking. OBJECTIVES: The purpose of this scoping review was to provide an overview of device applications and methodological approaches to monitor postures and motions in hospitalized patients using sensor technology. METHODS: A systematic search of Embase, Medline, Web of Science and Google Scholar was completed in February 2023 and updated in March 2024. Included studies described populations of hospitalized adults with short admission periods and interventions that use sensor technology to objectively monitor postures and motions. Study selection was performed by two authors independently of each other. Data extraction and narrative analysis focused on the applications and methodological approaches of included articles using a personalized standard form to extract information on device, measurement and analysis characteristics of included studies and analyse frequencies and usage. RESULTS: A total of 15.032 articles were found and 49 articles met the inclusion criteria. Devices were most often applied in older adults (n = 14), patients awaiting or after surgery (n = 14), and stroke (n = 6). The main goals were gaining insight into patient physical behavioural patterns (n = 19) and investigating physical behaviour in relation to other parameters such as muscle strength or hospital length of stay (n = 18). The studies had heterogeneous study designs and lacked completeness in reporting on device settings, data analysis, and algorithms. Information on device settings, data analysis, and algorithms was poorly reported. CONCLUSIONS: Studies on monitoring postures and motions are heterogeneous in their population, applications and methodological approaches. More uniformity and transparency in methodology and study reporting would improve reproducibility, interpretation and generalization of results. Clear guidelines for reporting and the collection and sharing of raw data would benefit the field by enabling study comparison and reproduction.

In a clinical setting, wearables are currently used to monitor postures and motions in a wide variety of study applications and hospital populations.Measurement of postures and motions in the hospital setting is characterized by methodological heterogeneity. This poses a significant challenge, impacting the interpretation of results and hindering meaningful comparisons between studiesFollowing guidelines for reporting and the collection and sharing of raw data would benefit the field.

Postpartum menstrual equity: Video and audio analysis of vaginal bleeding counseling during postpartum inpatient care at a southeastern US tertiary hospital.

BACKGROUND: Despite the universal nature of postpartum vaginal bleeding after childbirth and the importance of managing vaginal bleeding in the postpartum period to monitor health status, little is known about the information or products that birthing individuals are provided. Investigating current practices may offer insights to enacting more supportive and equitable postpartum care. OBJECTIVE: To evaluate the patterns and content of vaginal bleeding counseling provided to birthing parents while on a postnatal inpatient unit. DESIGN: Observational study of inpatient postpartum care. Birthing parents and their companions consented to video and audio recording of themselves, their infants, and healthcare team members during their postnatal unit stay. METHODS: Following IRB approval and in coordination with clinicians at a tertiary hospital in the southeastern United States, data were collected with 15 families from August to December 2020. A multidisciplinary team coded video and audio data from each family from 12 h before hospital discharge. This analysis evaluates patterns of vaginal bleeding counseling timing, content, and language concordance and thematic content of this communication. RESULTS: Birthing parent participants were self-identified Hispanic White (n = 6), non-Hispanic Black (n = 5), non-Hispanic White (n = 3), and non-Hispanic multi-race (n = 1). Six were Spanish-speaking and eight had cesarean section births. The timing, content, and language concordance of vaginal bleeding communication varied, with these topics mainly addressed in the hour preceding discharge. Twelve of the 15 birthing parents had communication on these topics between 2 and 5 times, 2 had one exchange, and 1 had no counseling on postpartum bleeding observed. Four of the six Spanish-speaking birthing parents had counseling on these topics that was not language concordant. Postpartum vaginal bleeding management involved the themes of access to products, patient safety, and meaningful counseling. There was a lack of adequate access, variation in accurate and respectful care, and a busy clinical environment with differences in information provided. CONCLUSION: Findings suggest that there are opportunities to strengthen clinical practices for more consistent, proactive, and language concordant vaginal bleeding and subsequent menstrual care postpartum. Menstrual equity is an important part of dignified and safe care.

Video analysis of when and what information on vaginal bleeding was shared between people who just gave birth and their healthcare team at the hospital.Why did we do the study? After birth, people must take care of vaginal bleeding. It is important for people in the hospital to recognize warning signs for too much bleeding, have access to pads, and feel supported by their healthcare team before discharging to home. There has been little research on experiences with inpatient counseling on postpartum vaginal bleeding­a part of the reproductive life cycle­for new parents. We wanted to watch and listen in hospital rooms so we could think about the best ways for healthcare providers to talk about vaginal bleeding. What did we do? We asked 15 people who just gave birth, people staying with them at the hospital, and their healthcare team if we could video and sound record in their hospital rooms. They could start and stop recording anytime. We only recorded people who agreed to be in the study. What did we learn? We watched recordings of the last 12 hours at the hospital before each family went home. We found that most of the time, the healthcare workers did not talk about vaginal bleeding. People who spoke Spanish did not always have someone interpreting into their language. Sometimes family members had to translate and ask for pads. Some people did not have enough pads or underwear and had to wait after asking for more. What does it mean? We found ways to improve teaching about vaginal bleeding after birth. We recommend always having an interpreter when needed, giving people enough pads and underwear in their rooms, including companions in the teaching, and having enough healthcare workers to answer requests. These ideas would improve the counseling and give everyone the support needed after giving birth.

Decreased hospital-acquired respiratory infections among older inpatients during the COVID-19 pandemic: a retrospective observational study in a general hospital in China.

BACKGROUND: To mitigate hospital-acquired transmission of coronavirus disease 2019 (COVID-19), various prevention and control measures have been strictly implemented in medical institutions. These stringent measures can potentially reduce the incidence of hospital-acquired respiratory infections. This study aimed to assess if there were changes in the prevalence of hospital-acquired respiratory infections during a period of national attention focused on COVID-19 prevention. METHODS: A retrospective analysis of the clinical data from adult patients with hospital-acquired respiratory infections admitted between October and December 2019 and during the same period in 2020 was performed. All patients were referred from a general hospital in Beijing China and COVID-19 patients were not treated at the hospital. Hospital-acquired respiratory infections were diagnosed based on the criteria of the Centers for Disease Control and Prevention/National Healthcare Safety Network (CDC/NHSN). A comparison of the incidence and mortality rate of hospital-acquired respiratory infections between the two selected time periods was conducted. Additionally, multivariate logistics regression analysis was used to identify mortality-associated risk factors. RESULTS: This study included 2,211 patients from October to December 2019 (pre-COVID-19 pandemic) and 2,921 patients from October to December 2020 (during the COVID-19 pandemic). The incidence of hospital-acquired respiratory infections in 2019 and 2020 was 4.7% and 2.9%, respectively, with odds ratio (OR): 0.61, 95% confidence interval (CI): 0.46-0.81, and P = 0.001. In-hospital mortality of hospital-acquired respiratory infections in 2019 and 2020 was 30.5% and 38.4%, respectively, with OR: 1.42, 95%CI: 0.78-2.59, and P = 0.25. Multivariate logistics regression analysis revealed that a history of previous malignancy (OR: 2.50, 95%CI: 1.16-5.35, P = 0.02), was associated with in-hospital mortality. CONCLUSIONS: The incidence of hospital-acquired respiratory infections was significantly decreased following the implementation of various prevention and control measures during the COVID-19 pandemic. A history of previous malignancy was associated with higher in-hospital mortality in older inpatients with hospital-acquired respiratory infections.

Changes in health-related quality of life, depression, and fear of progression during oncological inpatient rehabilitation and beyond: a longitudinal study.

PURPOSE: Studies evaluating oncological inpatient rehabilitation rarely include follow-up intervals beyond 6 months and larger proportions of patients other than those with breast cancer. Therefore, this study investigated changes in health-related quality of life (HRQoL), depression, and fear of progression of patients with breast, colorectal, or prostate cancer from the beginning to the end of oncological rehabilitation and a 9-month follow-up. METHODS: Three hundred seventy-seven patients with breast, colorectal, or prostate cancer undergoing oncological inpatient rehabilitation (median age 61 years, 49% female) completed the EORTC QLQ-C30, the PHQ-9, and the FoP-Q-SF at each measurement point. Data analysis used 3 (tumor site) × 3 (time of measurement) repeated measures ANCOVAs with patient age and time since diagnosis as covariates. At each time point, we also compared our sample to the general population on the measures used. RESULTS: Having controlled for the covariates, we found significant effects of tumor site, which were small except for Diarrhea. Effects of time of measurement were often significant and in part at least medium in size indicating improvement of HRQoL and depression during rehabilitation. At follow-up, some HRQoL domains and depression deteriorated. Women with breast cancer, in particular, showed a greater decrease in emotional functioning then. Compared to the general population, the sample's HRQoL and depression were significantly worse on most occasions. CONCLUSION: Oncological inpatient rehabilitation may improve HRQoL. The subsequent and in part differential deterioration in some HRQoL domains suggests a need for further follow-up care within survivorship programs.

Quantitative Analysis of the Causes of Falls in Adult Hospitalized Patients Based on the Perspective of Text Mining.

OBJECTIVE: This study harnesses the power of text mining to quantitatively investigate the causative factors of falls in adult inpatients, offering valuable references and guidance for fall prevention measures within hospitals. METHODS: Employing KH Coder 3.0, a cutting-edge text mining software, we performed co-occurrence network analysis and text clustering on fall incident reports of 2,772 adult patients from a nursing quality control platform in a particular city in Jiangsu Province, spanning January 2017 to December 2022. RESULTS: Among the 2,772 patients who fell, 80.23% were aged above 60, and 73.27% exhibited physical frailty. Text clustering yielded 16 distinct categories, with four clusters implicating patient factors, four linking falls to toileting processes, four highlighting dynamic interplays between patients, the environment, and objects, and another four clusters revealing the influence of patient-caregiver interactions in causing falls. CONCLUSION: This study highlights the complex, multifactorial nature of falls in adult inpatients. Effective prevention requires a collaborative effort among healthcare staff, patients, and caregivers, focusing on patient vulnerabilities, environmental factors, and improved care coordination. By strengthening these aspects, hospitals can significantly reduce fall risks and promote patient safety.

A Scoping Review of Studies Using Artificial Intelligence Identifying Optimal Practice Patterns for Inpatients With Type 2 Diabetes That Lead to Positive Healthcare Outcomes.

The objective of this scoping review was to survey the literature on the use of AI/ML applications in analyzing inpatient EHR data to identify bundles of care (groupings of interventions). If evidence suggested AI/ML models could determine bundles, the review aimed to explore whether implementing these interventions as bundles reduced practice pattern variance and positively impacted patient care outcomes for inpatients with T2DM. Six databases were searched for articles published from January 1, 2000, to January 1, 2024. Nine studies met criteria and were summarized by aims, outcome measures, clinical or practice implications, AI/ML model types, study variables, and AI/ML model outcomes. A variety of AI/ML models were used. Multiple data sources were leveraged to train the models, resulting in varying impacts on practice patterns and outcomes. Studies included aims across 4 thematic areas to address: therapeutic patterns of care, analysis of treatment pathways and their constraints, dashboard development for clinical decision support, and medication optimization and prescription pattern mining. Multiple disparate data sources (i.e., prescription payment data) were leveraged outside of those traditionally available within EHR databases. Notably missing was the use of holistic multidisciplinary data (i.e., nursing and ancillary) to train AI/ML models. AI/ML can assist in identifying the appropriateness of specific interventions to manage diabetic care and support adherence to efficacious treatment pathways if the appropriate data are incorporated into AI/ML design. Additional data sources beyond the EHR are needed to provide more complete data to develop AI/ML models that effectively discern meaningful clinical patterns. Further study is needed to better address nursing care using AI/ML to support effective inpatient diabetes management.

Development and Validation of a Deep Learning Model for Prediction of Adult Physiological Deterioration.

BACKGROUND: Prediction-based strategies for physiologic deterioration offer the potential for earlier clinical interventions that improve patient outcomes. Current strategies are limited because they operate on inconsistent definitions of deterioration, attempt to dichotomize a dynamic and progressive phenomenon, and offer poor performance. OBJECTIVE: Can a deep learning deterioration prediction model (Deep Learning Enhanced Triage and Emergency Response for Inpatient Optimization [DETERIO]) based on a consensus definition of deterioration (the Adult Inpatient Decompensation Event [AIDE] criteria) and that approaches deterioration as a state "value-estimation" problem outperform a commercially available deterioration score? DERIVATION COHORT: The derivation cohort contained retrospective patient data collected from both inpatient services (inpatient) and emergency departments (EDs) of two hospitals within the University of California San Diego Health System. There were 330,729 total patients; 71,735 were inpatient and 258,994 were ED. Of these data, 20% were randomly sampled as a retrospective "testing set." VALIDATION COHORT: The validation cohort contained temporal patient data. There were 65,898 total patients; 13,750 were inpatient and 52,148 were ED. PREDICTION MODEL: DETERIO was developed and validated on these data, using the AIDE criteria to generate a composite score. DETERIO's architecture builds upon previous work. DETERIO's prediction performance up to 12 hours before T0 was compared against Epic Deterioration Index (EDI). RESULTS: In the retrospective testing set, DETERIO's area under the receiver operating characteristic curve (AUC) was 0.797 and 0.874 for inpatient and ED subsets, respectively. In the temporal validation cohort, the corresponding AUC were 0.775 and 0.856, respectively. DETERIO outperformed EDI in the inpatient validation cohort (AUC, 0.775 vs. 0.721; p < 0.01) while maintaining superior sensitivity and a comparable rate of false alarms (sensitivity, 45.50% vs. 30.00%; positive predictive value, 20.50% vs. 16.11%). CONCLUSIONS: DETERIO demonstrates promise in the viability of a state value-estimation approach for predicting adult physiologic deterioration. It may outperform EDI while offering additional clinical utility in triage and clinician interaction with prediction confidence and explanations. Additional studies are needed to assess generalizability and real-world clinical impact.

Implementation and evaluation of a proactive consultation-liaison model on an inpatient obstetric unit.

OBJECTIVE: Perinatal mental and anxiety disorders (PMADs) contribute to adverse health outcomes, though they are underrecognized and undertreated. Inpatient obstetric settings represent a unique opportunity for behavioral health engagement, including screening, brief treatment, and referrals for outpatient care. The proactive consultation-liaison (CL) model has proven effective in general hospital settings but is not well-studied in obstetric settings. This article describes the implementation and evaluation of a proactive CL model in an inpatient obstetric unit within a tertiary medical center. METHODS: We implemented a multidisciplinary, proactive CL model in an inpatient obstetric unit with the purpose of identifying patients at risk for or experiencing PMADs and providing intervention and/or referral to treatment. Systematic screening of 7322 admitted patients was performed over a 17-month period to identify eligible patients for behavioral health consultation. Consultation data was retrospectively extracted from the electronic medical record. Key implementation outcomes were assessed using a RE-AIM measures (Reach, Effectiveness, Adoption, Implementation, and Maintenance) framework. RESULTS: 1589 initial consults were conducted by the multidisciplinary team, yielding a consult rate of 21.7 %. The majority of consults (94 %) were completed by a social worker or psychologist, with most patients identified for consultation at multidisciplinary rounds (60.7 %). The most common indications for consultation with a psychiatrist included medication management, history of bipolar disorder, and history of anxiety. All invited staff and providers participated in the model. Alternative funding sources agreed to cover the salaries of the multidisciplinary team following conclusion of pilot grant funding. CONCLUSIONS: A proactive CL model implemented in an inpatient obstetric unit led to a higher consult rate (21.7 %) than is observed with traditional CL services. A multidisciplinary proactive CL model shows promise in identifying people at-risk for PMADs and providing targeted interventions to prevent PMADs and treat those with active symptoms.