scholarly journals Development and validation of a machine learning model for predicting illness trajectory and hospital resource utilization of COVID-19 hospitalized patients - a nationwide study

2020 ◽  
Author(s):  
Michael Roimi ◽  
Rom Gutman ◽  
Jonathan Somer ◽  
Asaf Ben Arie ◽  
Ido Calman ◽  
...  
Keyword(s):  
Machine Learning ◽  
Critical Care ◽  
Critical Illness ◽  
Length Of Stay ◽  
Hospital Mortality ◽  
Hospital Utilization ◽  
Care Hospital ◽  
Hospital Resource ◽  
Hospital Bed ◽  
The Impact

Background: The spread of COVID-19 has led to a severe strain on hospital capacity in many countries. There is a need for a model to help planners assess expected COVID-19 hospital resource utilization. Methods: Retrospective nationwide cohort study following the day-by-day clinical status of all hospitalized COVID-19 patients in Israel from March 1st to May 2nd, 2020. Patient clinical course was modelled with a machine learning approach based on a set of multistate Cox regression-based mod- els with adjustments for right censoring, recurrent events, competing events, left truncation, and time-dependent covariates. The model predicts the patient's entire disease course in terms of clinical states, from which we derive the patient's hospital length-of-stay, length-of-stay in critical state, the risk of in-hospital mortality, and total and critical care hospital-bed utilization. Accuracy assessed over eight cross-validation cohorts of size 330, using per-day Mean Absolute Error (MAE) of predicted hospital utilization averaged over 64 days; and area under the receiver operating characteristics (AUROC) for individual risk of critical illness and in-hospital mortality, assessed on the first day of hospitalization. We present predicted hospital utilization under hypothetical incoming patient scenarios. Findings: During the study period, 2,703 confirmed COVID-19 patients were hospitalized in Israel. The per-day MAEs for total and critical-care hospital- bed utilization, were 4.72 ± 1.07 and 1.68 ± 0.40 respectively; the AUROCs for prediction of the probabilities of critical illness and in-hospital mortality were 0.88 ± 0.04 and 0.96 ± 0.04, respectively. We further present the impact of several scenarios of patient influx on healthcare system utilization, and provide an R software package for predicting hospital-bed utilization. Interpretation: We developed a model that, given basic easily obtained data as input, accurately predicts total and critical care hospital utilization. The model enables evaluating the impact of various patient influx scenarios on hospital utilization and planning ahead of hospital resource allocation.

scholarly journals Development and validation of a machine learning model predicting illness trajectory and hospital utilization of COVID-19 patients—a nationwide study

2021 ◽  
Author(s):  
Michael Roimi ◽  
Rom Gutman ◽  
Jonathan Somer ◽  
Asaf Ben Arie ◽  
Ido Calman ◽  
...  
Keyword(s):  
Critical Care ◽  
Clinical Status ◽  
Patient Characteristics ◽  
Hospitalized Patients ◽  
Hospital Utilization ◽  
Clinical State ◽  
Care Hospital ◽  
System Utilization ◽  
The Impact ◽  
Day By Day

Abstract Objective The spread of COVID-19 has led to severe strain on hospital capacity in many countries. We aim to develop a model helping planners assess expected COVID-19 hospital resource utilization based on individual patient characteristics. Materials and Methods We develop a model of patient clinical course based on an advanced multistate survival model. The model predicts the patient's disease course in terms of clinical states—critical, severe, or moderate. The model also predicts hospital utilization on the level of entire hospitals or healthcare systems. We cross-validated the model using a nationwide registry following the day-by-day clinical status of all hospitalized COVID-19 patients in Israel from March 1st to May 2nd, 2020 (n = 2,703). Results Per-day mean absolute errors for predicted total and critical-care hospital-bed utilization were 4.72 ± 1.07 and 1.68 ± 0.40 respectively, over cohorts of 330 hospitalized patients; AUCs for prediction of critical illness and in-hospital mortality were 0.88 ± 0.04 and 0.96 ± 0.04, respectively. We further present the impact of patient influx scenarios on day-by-day healthcare system utilization. We provide an accompanying R software package. Discussion The proposed model accurately predicts total and critical-care hospital utilization. The model enables evaluating impacts of patient influx scenarios on utilization, accounting for the state of currently hospitalized patients and characteristics of incoming patients. We show that accurate hospital-load predictions were possible using only a patient’s age, sex, and day-by-day clinical state (critical, severe or moderate). Conclusion The multistate model we develop is a powerful tool for predicting individual-level patient outcomes and hospital-level utilization.

scholarly journals Evaluation of Clinical Outcomes after Introduction of a Dedicated Infectious Diseases- Critical Care Medicine Service in Critical Care Units

2021 ◽  
Author(s):  
Polina Trachuk ◽  
Vagish Hemmige ◽  
Ruth Eisenberg ◽  
Kelsie Cowman ◽  
Victor Chen ◽  
...  
Keyword(s):  
Critical Care ◽  
Infectious Diseases ◽  
Clinical Outcomes ◽  
Broad Spectrum ◽  
Critical Care Medicine ◽  
Care Hospital ◽  
Intervention Period ◽  
Broad Spectrum Antibiotics ◽  
Antibiotic Utilization ◽  
The Impact

Abstract Objective Infection is a leading cause of admission to intensive care units (ICU), with critically ill patients often receiving empiric broad-spectrum antibiotics. Nevertheless, a dedicated infectious diseases (ID) consultation and stewardship team is not routinely established. An ID-Critical Care Medicine (ID-CCM) pilot program was designed at a 400-bed tertiary care hospital in which an ID attending was assigned to participate in daily rounds with the ICU team, as well as provide ID consultation on select patients. We sought to evaluate the impact of this dedicated ID program on antibiotic utilization and clinical outcomes in patients admitted to the ICU. Method In this single site retrospective study, we analyzed antibiotic utilization and clinical outcomes in patients admitted to an ICU during post-intervention period from January 1, 2017 to December 31, 2017 and compared it to antibiotic utilization in the same ICUs during the pre-intervention period from January 1, 2015 to December 31, 2015. Results Our data showed a statistically significant reduction in usage of most frequently prescribed antibiotics including vancomycin, piperacillin-tazobactam and cefepime during the intervention period. When compared to pre-intervention period there was no difference in-hospital mortality, hospital length of stay and re-admission. Conclusion With this multidisciplinary intervention, we saw a decrease in the use of the most frequently prescribed broad-spectrum antibiotics without a negative impact on clinical outcomes. Our study shows that the implementation of an ID-CCM service is a feasible way to promote antibiotic stewardship in the ICU and can be used as a strategy to reduce unnecessary patient exposure to broad-spectrum agents.

scholarly journals Temporal Changes in Central-Line–Associated Bloodstream Infection Time Between Events, 2017–2018 Versus 2015–2016

2020 ◽  
Vol 41 (S1) ◽  
pp. s403-s404
Author(s):  
Jonathan Edwards ◽  
Katherine Allen-Bridson ◽  
Daniel Pollock
Keyword(s):  
Length Of Stay ◽  
Patient Care ◽  
Average Length ◽  
Bloodstream Infections ◽  
Central Line ◽  
Significant Shift ◽  
Care Hospital ◽  
Average Length Of Stay ◽  
Period 2 ◽  
Hospital Bed

Background: The CDC NHSN surveillance coverage includes central-line–associated bloodstream infections (CLABSIs) in acute-care hospital intensive care units (ICUs) and select patient-care wards across all 50 states. This surveillance enables the use of CLABSI data to measure time between events (TBE) as a potential metric to complement traditional incidence measures such as the standardized infection ratio and prevention progress. Methods: The TBEs were calculated using 37,705 CLABSI events reported to the NHSN during 2015–2018 from medical, medical-surgical, and surgical ICUs as well as patient-care wards. The CLABSI TBE data were combined into 2 separate pairs of consecutive years of data for comparison, namely, 2015–2016 (period 1) and 2017–2018 (period 2). To reduce the length bias, CLABSI TBEs were truncated for period 2 at the maximum for period 1; thereby, 1,292 CLABSI events were excluded. The medians of the CLABSI TBE distributions were compared over the 2 periods for each patient care location. Quantile regression models stratified by location were used to account for factors independently associated with CLABSI TBE, such as hospital bed size and average length of stay, and were used to measure the adjusted shift in median CLABSI TBE. Results: The unadjusted median CLABSI TBE shifted significantly from period 1 to period 2 for the patient care locations studied. The shift ranged from 20 to 75.5 days, all with 95% CIs ranging from 10.2 to 32.8, respectively, and P < .0001 (Fig. 1). Accounting for independent associations of CLABSI TBE with hospital bed size and average length of stay, the adjusted shift in median CLABSI TBE remained significant for each patient care location that was reduced by ∼15% (Table 1). Conclusions: Differences in the unadjusted median CLABSI TBE between period 1 and period 2 for all patient care locations demonstrate the feasibility of using TBE for setting benchmarks and tracking prevention progress. Furthermore, after adjusting for hospital bed size and average length of stay, a significant shift in the median CLABSI TBE persisted among all patient care locations, indicating that differences in patient populations alone likely do not account for differences in TBE. These findings regarding CLABSI TBEs warrant further exploration of potential shifts at additional quantiles, which would provide additional evidence that TBE is a metric that can be used for setting benchmarks and can serve as a signal of CLABSI prevention progress.Funding: NoneDisclosures: None

Cognitive Impairment and Length of Stay in Acute Care Hospitals: A Scoping Review of the Literature

2021 ◽  
pp. 1-19
Author(s):  
Jonathan Plante ◽  
Karine Latulippe ◽  
Edeltraut Kröger ◽  
Dominique Giroux ◽  
Martine Marcotte ◽  
...  
Keyword(s):  
Cognitive Impairment ◽  
Length Of Stay ◽  
Acute Care ◽  
Scoping Review ◽  
Research Question ◽  
Positive Association ◽  
Well Being ◽  
Future Research ◽  
Care Hospital ◽  
The Impact

Abstract Older persons experiencing a longer length of stay (LOS) or delayed discharge (DD) may see a decline in their health and well-being, generating significant costs. This review aimed to identify evidence on the impact of cognitive impairment (CI) on acute care hospital LOS/DD. A scoping review of studies examining the association between CI and LOS/DD was performed. We searched six databases; two reviewers independently screened references until November 2019. A narrative synthesis was used to answer the research question; 58 studies were included of which 33 found a positive association between CI and LOS or DD, 8 studies had mixed results, 3 found an inverse relationship, and 14 showed an indirect link between CI-related syndromes and LOS/DD. Thus, cognitive impairment seemed to be frequently associated with increased LOS/DD. Future research should consider CI together with other risks for LOS/DD and also focus on explaining the association between the two.

scholarly journals Association of hospital admission service structure with early transfer to critical care, hospital readmission, and length of stay

2016 ◽  
Vol 11 (10) ◽  
pp. 669-674 ◽  
Author(s):  
G. Randy Smith ◽  
Madeleine Ma ◽  
Luke O. Hansen ◽  
Nick Christensen ◽  
Kevin J. O'Leary
Keyword(s):  
Critical Care ◽  
Length Of Stay ◽  
Hospital Admission ◽  
Hospital Readmission ◽  
Care Hospital ◽  
Early Transfer

THE IMPACT OF ANTIMICROBIAL STEWARDSHIP ON THE PATTERNS OF ANTIBIOTICS’ PRESCRIPTION AND CLINICAL OUTCOMES IN THE MEDICAL WARD OF A MALAYSIAN TERTIARY CARE HOSPITAL

2021 ◽  
pp. 20-25
Author(s):  
OVAIS ULLAH SHIRAZI ◽  
NORNY SYAFINAZ AB RAHMAN ◽  
CHE SURAYA ZIN ◽  
HANNAH MD MAHIR ◽  
SYAMHANIN ADNAN
Keyword(s):  
Length Of Stay ◽  
Clinical Outcomes ◽  
Antimicrobial Stewardship ◽  
Tertiary Care Hospital ◽  
Tertiary Care ◽  
Medical Ward ◽  
Prescribing Patterns ◽  
Care Hospital ◽  
Slope Change ◽  
The Impact

Objective: To evaluate the impact of antimicrobial stewardship (AMS) on antibiotic prescribing patterns and certain clinical outcomes, the length of stay (LOS) and the re-admission rate (RR) of the patients treated within the medical ward of a tertiary care hospital in Malaysia. Methods: This quasi-experimental study was conducted retrospectively. The prescriptions of the AMS included alert antibiotics (AA) such as cefepime, ceftazidime, colistin (polymyxin E), imipenem-cilastatin, meropenem, piperacillin-tazobactam and vancomycin were reviewed for the period of 24 mo before (May, 2012–April, 2014) and after (May, 2014–April, 2016) the AMS implementation for the patients who were treated within the medical ward of a Malaysian tertiary care hospital. Patterns of antibiotics prescribed were determined descriptively. The impact of the AMS on the length of stay (LOS) and readmission rate (RR) was determined by the interrupted time series (ITS) comparative analysis of the pre-and post-AMS segments segregated by the point of onset (May, 2014) of the AMS program. Data analysis was performed through autoregressive integrated moving average (ARIMA) Winter Additive model and the Games-Howell non-parametric post hoc test by using IBM Statistical Package for Social Sciences version 25.0 for Windows (SPSS Inc., Chicago, IL, USA). Results: A total of 1716 prescriptions of the AA included for the AMS program showed that cefepime (623, 36.3%) and piperacillin-tazobactam (424, 24.7%) were the most prescribed antibiotics from May 2012 to April 2016. A 23.6% drop in the number of the AA prescriptions was observed during the 24-month post-AMS period. The LOS of the patients using any of the AA showed a post-AMS decline by 3.5 d. The patients’ LOS showed an average reduction of 0.12 (95% CI, 0.05–0.19, P=0.001) with the level and slope change of 0.18 (95% CI, 0.04–0.32, P=0.02) and 0.074 (95% CI, 0.02–0.12, P=0.002), respectively. Similarly, the percent RR reduced from 20.0 to 9.85 during the 24-month post-AMS period. The observed post-AMS mean monthly reduction of the RR for the patients using any AA was 0.38 (95% CI, 0.23–0.53, P<0.001) with the level and slope change of 0.33 (95% CI, 0.14–0.51, P=0.02) and 0.37 (95% CI, 0.16–0.58, P=0.001), respectively. Conclusion: The AMS program of a Malaysian tertiary care hospital was a coordinated set of interventions implemented by the AMS team of the hospital that comprised of the infectious diseases (ID) physician, clinical pharmacists and microbiologist. The successful implementation of the AMS program from May, 2014 to April, 2016 within the medical ward resulted in the drop of the number of AA prescriptions that sequentially resulted in the significant (P<0.05) post-AMS reduction of the LOS and the RR.

Abstract 16688: Trans-Satellite Wireless 12 Lead ECG Transmission From the Ambulance to the Primary PCI Facility as Part of Nationwide Primary PCI Program for ST-Elevation Myocardial Infarction

Circulation ◽  
2014 ◽  
Vol 130 (suppl_2) ◽  
Author(s):  
Abdurrazzak Gehani ◽  
Jassim Al Suwaidi ◽  
Omer Tamimi ◽  
Salah Arafa ◽  
Awad Al Qahtani ◽  
...  
Keyword(s):  
Length Of Stay ◽  
Hospital Mortality ◽  
Ethnic Difference ◽  
Primary Pci ◽  
Emergency Rooms ◽  
Total Delay ◽  
St Elevation ◽  
Door To Balloon ◽  
The Impact ◽  
Heart Hospital

Introduction: Time is recognized as a crucial factor in the success of Primary PCI (PPCI). We have installed a “Nationwide” Trans-Satellite Wireless ECG Transfer (W-ECG) which enables swift identification of STEMI and direct transfer to the PPCI facility in Heart Hospital (HH). It also initiates PPCI staff to be ready even before patient arrives, and eliminates delays in Emergency rooms. Methods: Of 510 patients who had PPCI for STEMI, 282 (55%) were transferred directly to the Heart Hospital (HH). These were compared with 228 patients (45%) who went to other hospitals first (OH) before transfer to the HH. Age was similar 50.2 vs 50 years and there was no Ethnic difference (73% Asians and 26% Arabs) in both groups. We compared the two with regard to achieving the optimal Door to Balloon Time (DBT) of 90min for PPCI facility (HH), versus 120min for the OH group, as per guidelines. Results: The DBT was 53±23min for HH group vs 104±55min in OH group (p<0.001). However, while 88% achieved <90min in HH group, only 70% achieved <120min in OH group, p<0.001. Furthermore, Out of Hospital Delay ( OHD i.e delay from symptoms until arrival to hospital) was also different. Patients who had W-ECG arrived faster to HH and thus had shorter OHD (198±183min) than those using own transport to HH (287±276min). Although OHD was longer in HH group (216±212) than OH group (201±172min), the combined OHD+DBT= (Total delay from symptoms to Balloon) was still shorter in HH (W-ECG) group (269min) than similar group going to OH (305min), thus saving 36 vital minutes. Although initial TIMI-0 flow was similar (HH 46% vs OH 44%), TIMI-III flow was achieved more often in HH (97%) than in OH group (92%). Peak Troponin (ng/ml) was also higher in OH group (71251) vs (6576) in HH, p<0.05. While Ejection fraction was similar (HH 45% vs OH 43%), in-hospital mortality was higher in OH group (3.5%) vs (2.5%) in HH, p=0.05. Length of stay was also longer in OH (4.3±4.7) compared to 3.4±3.1 in HH group, p=0.005. Conclusion: Trans-satellite wireless ECG from the ambulance to Primary PCI facility results in significantly shorter DBT, total symptoms to balloon time, and length of stay, as well lower peak Troponin and a trend towards lower in-hospital mortality. Continued study and wider use will further confirm the impact of this technology.

scholarly journals The Integration of Adult Acute Care Surgeons into Pediatric Surgical Care Models Supplements the Workforce without Compromising Quality of Care

2015 ◽  
Vol 81 (9) ◽  
pp. 854-858 ◽  
Author(s):  
Rudy J. Judhan ◽  
Raquel Silhy ◽  
Kristen Statler ◽  
Mija Khan ◽  
Benjamin Dyer ◽  
...  
Keyword(s):  
Length Of Stay ◽  
Acute Care ◽  
Tertiary Care ◽  
Disease Process ◽  
Pediatric Care ◽  
Care Hospital ◽  
Late Night ◽  
General Surgeons ◽  
The Impact

Acute care of children remains a challenge due to a shortage of pediatric surgeons, particularly in rural areas. In our institutional norm, all cases in patients age six and older are managed by dedicated general surgeons. The provision of care to these children by these surgeons alleviates the impact of such shortages. We conducted a five-year retrospective analysis of all acute care pediatric surgical cases performed in patients aged 6 to 17 years by a dedicated group of adult general surgeons in a rural tertiary care hospital. Demographics, procedure, complications, outcomes, length of stay, and time of consultation/operation were obtained via chart review. Elective, trauma related, or procedures performed by a pediatric surgeon were excluded. Descriptive statistics are reported. A total of 397 cases were performed by six dedicated general surgeons during the study period. Mean age was 11.5 ± 3.1 years. In all, 100 (25.2%) were transferred from outlying facilities and 52.6 per cent of consultations/operations occurred at night (7P–7A), of which 33.2 per cent occurred during late night hours (11P–7A). On weekends, 34.0 per cent occurred. Appendectomy was the most commonly performed operation (n = 357,89.9%), of which 311 were laparoscopic (87.1%). Others included incision/drainage (4.5%), laparoscopic cholecystectomy (2.0%), bowel resection (1.5%), incarcerated hernia (0.5%), small bowel obstruction (0.5%), intraabdominal abscess drainage (0.3%), resection of intussusception (0.3%), Graham patch (0.3%), and resection omental torsion (0.3%). Median length of stay was two days. Complications occurred in 23 patients (5.8%), of which 22(5.5%) were the result of the disease process. These results parallel those published by pediatric surgeons in this age group and for the diagnoses treated. Models integrating dedicated general surgeons into pediatric call rotations can be designed such that quality of pediatric care is maintained while providing relief to an overburdened pediatric surgical workforce.

Sign in / Sign up

Export Citation Format

Share Document