scholarly journals Implementation of Machine Learning Software on the Radiology Worklist Decreases Scan View Delay for the Detection of Intracranial Hemorrhage on CT

2021 ◽  
Vol 11 (7) ◽  
pp. 832
Author(s):  
Daniel Ginat

Background and Purpose: Prompt identification of acute intracranial hemorrhage on CT is important. The goal of this study was to assess the impact of artificial intelligence software for prioritizing positive cases. Materials and Methods: Cases analyzed by Aidoc (Tel Aviv, Israel) software for triaging acute intracranial hemorrhage cases on non-contrast head CT were retrospectively reviewed. The scan view delay time was calculated as the difference between the time the study was completed on PACS and the time the study was first opened by a radiologist. The scan view delay was stratified by scan location, including emergency, inpatient, and outpatient. The scan view delay times for cases flagged as positive by the software were compared to those that were not flagged. Results: A total of 8723 scans were assessed by the software, including 6894 cases that were not flagged and 1829 cases that were flagged as positive. Although there was no statistically significant difference in the scan view time for emergency cases, there was a significantly lower scan view time for positive outpatient and inpatient cases flagged by the software versus negative cases, with a reduction of 604 min on average, 90% in the scan view delay (p-value < 0.0001) for outpatients, and a reduction of 38 min on average, and 10% in the scan view delay (p-value <= 0.01) for inpatients. Conclusion: The use of artificial intelligence triage software for acute intracranial hemorrhage on head CT scans is associated with a significantly shorter scan view delay for cases flagged as positive than cases not flagged among outpatients and inpatients at an academic medical center.

2020 ◽  
Vol 54 (8) ◽  
pp. 767-774
Author(s):  
Kwabena Nimarko ◽  
Aiman Bandali ◽  
Tiffany E. Bias ◽  
Sharon Mindel

Background: Numerous interventions have been used to reduce medication errors related to antiretroviral (ARV) therapy for hospitalized patients with HIV. Objective: This study assessed the impact of an antimicrobial stewardship (ASP) team intervention on reducing the rate of ARV therapy errors in patients admitted to an academic medical center. Methods: This observational, retrospective study included patients who received ARV therapy from June 2016 to December 2017. The primary outcome was evaluation of ASP team performance in detecting ARV medication errors in the inpatient setting. Errors were further categorized by type (interaction, dosing, regimen). The Mann-Whitney U test and χ2 tests were utilized to analyze continuous and categorical data, respectively. Results: Medication errors occurred in 51% of patients in the preintervention group (n = 152) and 48% of patients in the postintervention group (n = 203; P = 0.43). The most frequent medication error type was drug interactions in both groups, involving integrase strand transfer inhibitors and polyvalent cations (64% vs 67%). There was a significant difference between preintervention and postintervention groups regarding number of errors detected (13 vs 106, P < 0.001), corrected (12 vs 86, P < 0.001), and persisting at discharge (106 vs 18, P < 0.001). Conclusion and Relevance: Review of ARV regimens by an ASP team significantly decreased medication errors. Drug interactions are the most common medication error found in HIV-positive patients admitted to our academic center.


2018 ◽  
Vol 16 (2) ◽  
pp. 138-146 ◽  
Author(s):  
Carlito Lagman ◽  
Daniel T Nagasawa ◽  
Daniel Azzam ◽  
John P Sheppard ◽  
Cheng Hao Jacky Chen ◽  
...  

Abstract BACKGROUND Survival outcomes for patients with liver disease who suffer an intracranial hemorrhage (ICH) have not been thoroughly investigated. OBJECTIVE To understand survival outcomes for 3 groups: (1) patients with an admission diagnosis of liver disease (end-stage liver disease [ESLD] or non-ESLD) who developed an ICH in the hospital, (2) patients with ESLD who undergo either operative vs nonoperative management, and (3) patients with ESLD on the liver transplant waitlist who developed an ICH in the hospital. METHODS We retrospectively reviewed hospital charts from March 2006 through February 2017 of patients with liver disease and an ICH evaluated by the neurosurgery service at a single academic medical center. The primary outcome was survival. RESULTS We included a total of 53 patients in this study. The overall survival for patients with an admission diagnosis of liver disease who developed an ICH (n = 29, 55%) in the hospital was 22%. Of those patients with an admission diagnosis of liver disease, 27 patients also had ESLD. Kaplan–Meier analysis found no significant difference in survival for ESLD patients (n = 33, 62%) according to operative status. There were 11 ESLD patients on the liver transplant waitlist. The overall survival for patients with ESLD on the liver transplant waitlist who suffered an in-hospital ICH (n = 7, 13%) was 14%. CONCLUSION ICH in the setting of liver disease carries a grave prognosis. Also, a survival advantage for surgical hematoma evacuation in ESLD patients is not clear.


2019 ◽  
Vol 66 (1) ◽  
pp. 29-33
Author(s):  
Priyam Mithawala ◽  
Edo-abasi McGee

Objective The primary objectives were to evaluate the prescriber acceptance rate of Antimicrobial Stewardship Program (ASP) pharmacist recommendation to de-escalate/discontinue meropenem, and estimate the difference in duration of meropenem therapy. The secondary objective was to determine incidence of adverse events in the two groups. Methods It was a retrospective study. All patients admitted to Gwinnett Medical Center and receiving meropenem from January–November 2015 were included in the study. Exclusion criteria were: patients admitted to intensive care unit, one-time dose, infectious disease consultation, and age <18 years. Electronic medical records were reviewed for data collection. The control group consisted of patients from January–July 2015 when there was no ASP pharmacist. The intervention group consisted of patients from August–November 2015 during which period the ASP pharmacist recommended de-escalation/discontinuation of meropenem based on culture and sensitivity results. Results A total of 41 patients were studied, 21 in the control group and 20 in the intervention group. There was no significant difference in baseline characteristics in the two groups and in terms of prior hospitalization or antibiotic use (within 90 days) and documented or suspected MDRO infection at the time of admission. De-escalation/discontinuation was suggested in 16/20 patients in the intervention group (80%), and intervention was accepted in 68%. The mean duration of therapy was significantly decreased in the intervention group (5.6 days vs. 8.1 days, p =0.0175). Two patients had thrombocytopenia (unrelated to meropenem), and none of the patients had seizure. Conclusion Targeted antibiotic review is an effective ASP strategy, which significantly decreases the duration of meropenem therapy.


2019 ◽  
Vol 37 (15_suppl) ◽  
pp. e18007-e18007
Author(s):  
Noah Xavier Tocci ◽  
Jim Doolin ◽  
Daniel Aaron Roberts ◽  
Christina Cibotti ◽  
Rebekah A Hartwell ◽  
...  

e18007 Background: Patients on oral chemotherapy (OC) often lack consistent education and monitoring, risking toxicity and poor adherence. We developed an OC management program including education and an online tool for active outreach. Methods: In November 2017, we initiated pharmacist-led education for patients newly prescribed OC at a community practice and in the gastrointestinal oncology group at an academic medical center (AMC). An online tool assessing adherence, symptoms, and financial toxicity was emailed to patients three days after starting OC. Non-responders were contacted for phone interviews. A random sample of 28 patients newly started on OC at both sites before the intervention in 2017 was analyzed at baseline. A retrospective chart analysis was done to collect time to symptom assessment, identification and action. A report generated date of first emergency department (ED) visit or hospitalization within the AMC. We conducted a Mann Whitney U-Test, using a one-sided p value of 0.025 with Bonferroni correction. Results: Sixty-nine of 106 eligible patients (66%) received education, of whom 36 (52.1%) received the online tool, and 13 (36.1%) responded. There was a significant difference between the intervention and baseline median times to first new/worsening symptoms (p = 0.0105) but otherwise there were no outcome improvements. Eight of 23 patients who did not respond to the electronic tool were interviewed and indicated that their illness impeded their ability to check email (n = 2), and that they never check email (n = 2). Conclusions: This OC management program improved time to detect new/worsening symptoms and could potentially improve outcomes after further patient accrual. Future investigation should examine ways to improve patient responsiveness to electronic patient-reported symptom tools. [Table: see text]


2021 ◽  
Vol 13 (02) ◽  
pp. e234-e241
Author(s):  
Joshua Cole ◽  
Tiffany A. Chen ◽  
Tessnim Ahmad ◽  
Neeti Parikh

Abstract Objective This study aimed to evaluate the impact of an ophthalmic microsurgery laboratory on medical students' intrinsic motivation, explicit interest in ophthalmology, and comfort with microsurgical skills. Design In this noncontrolled trial, medical students attended a Zoom-based lecture on corneal suturing, watched an instructional video on operating microscopes, and attended a wet laboratory on corneal suturing. Participants completed pre- and posttest surveys assessing comfort with microsurgical skills and explicit interest in ophthalmology. Additionally, the posttest survey included items from the Intrinsic Motivation Inventory (IMI). Setting This study was conducted at a single academic medical center. Participants A total of 20 students enrolled in the MD program at the University of California, San Francisco School of Medicine. Results Pre- and posttest response rates were 100% (n = 20) and 90% (n = 18), respectively. Comfort with microsurgical skills increased significantly between pre- and posttest surveys with large effect sizes (95% confidence interval [CI]; p-value): loading a needle, 1.67 (1.04–2.29; p < 0.001); passing a suture, 1.72 (1.04–2.40; p < 0.001); knot tying, 1.05 (0.34–1.76; p = 0.004); using a microscope, 0.83 (0.04–1.63; p = 0.040); and suturing under a microscope, 1.44 (0.88–2.00; p < 0.001). Comparing pre- and posttest surveys, students reporting moderate to extreme interest in ophthalmology increased from 44 to 61%. Intrinsic motivation was high, indicated by the mean IMI Interest score reaching 93% of the maximum score. Multiple linear regression analyses predicted that IMI Interest scores increased with higher scores of familiarity (p = 0.002), explicit interest in ophthalmology (p = 0.042), and comfort with microscopes (p = 0.005), knot tying (p = 0.026), and performing surgical maneuvers under a microscope (p = 0.032). Conclusion Ophthalmic microsurgery laboratories may increase medical students' explicit interest in ophthalmology, comfort with microsurgical skills, and intrinsic motivation. Future studies are needed to evaluate the impact of microsurgical electives on students' objective skills and specialty selection.


2021 ◽  
Vol 8 (Supplement_1) ◽  
pp. S140-S141
Author(s):  
Vidya Atluri ◽  
Frank Tverdek ◽  
Sarah Elsayed ◽  
Beverly Chan ◽  
Catherine Liu ◽  
...  

Abstract Background Vancomycin and piperacillin-tazobactam (VPT) combination therapy is associated with nephrotoxicity and provides broad-spectrum coverage that may be unnecessary. We conducted a pre-post implementation study to assess the impact of an audit and feedback program for VPT at our academic medical center. Methods Automated alerts were used to identify patients on VPT at the University of Washington Medical Center (UWMC)-Montlake (ML) and UWMC-Seattle Cancer Care Alliance (SCCA) hospitals. Baseline data was collected on patients from 1/20/20-6/2/20: electronic medical records were reviewed for antibiotic indication, duration, renal function, and presence of Infectious Disease (ID) consult. From 6/25/20-10/31/20, all patients on combination therapy without an ID consult were reviewed by the antimicrobial stewardship programs at ML and SCCA, respectively. If intervention was warranted, the ML steward discussed the case with the provider then documented the conversation. The SCCA steward, instead, discussed the case with the team pharmacist. The primary outcome was change in VPT duration post intervention. Secondary outcomes included nephrotoxicity rates and carbapenem escalation. Results Prior to the intervention, 66 ML and 33 SCCA patients were started on the combination compared to 110 ML and 50 SCCA patients post-intervention. Overall, 50% of ML and 14% of SCCA patients were on surgical primary services. Amongst ML patients, there was a decrease in patients on VPT for &gt; 4 days (22 % to 8%), incidence of renal injury (30.3% to 10%), and percentage of ID consults (53.0% to 43.6%). Escalation to a carbapenem was stable (4.5% to 4.5%). In SCCA patients the percentage of patients on VPT for &gt; 4 days decreased slightly (18.2% to 15.2%), incidence of renal injury was stable (18.2% to 18%), percentage of ID consults increased (45.5% to 50.0%), and escalation to a carbapenem was stable (12.1% vs 13.5%). Conclusion Prospective audit and feedback of VPT was associated with a decrease in duration and nephrotoxicity in ML but not SCCA patients. The difference in outcomes could be due to the patient populations, primary services, or intervention process. This study highlights the importance of tailoring interventions even within the same medical system. Disclosures All Authors: No reported disclosures


2018 ◽  
Vol 39 (07) ◽  
pp. 788-796 ◽  
Author(s):  
Elise M. Martin ◽  
Brandy Bryant ◽  
Tristan R. Grogan ◽  
Zachary A. Rubin ◽  
Dana L. Russell ◽  
...  

OBJECTIVETo evaluate the impact of discontinuing routine contact precautions (CP) for endemic methicillin-resistantStaphylococcus aureus(MRSA) and vancomycin-resistantEnterococcus(VRE) on hospital adverse events.DESIGNRetrospective, nonrandomized, observational, quasi-experimental study.SETTINGAcademic medical center with single-occupancy rooms.PARTICIPANTSInpatients.METHODSWe compared hospital reportable adverse events 1 year before and 1 year after discontinuation of routine CP for endemic MRSA and VRE (preintervention and postintervention periods, respectively). Throughout the preintervention period, daily chlorhexidine gluconate bathing was expanded to nearly all inpatients. Chart reviews were performed to identify which patients and events were associated with CP for MRSA/VRE in the preintervention period as well as the patients that would have met prior criteria for MRSA/VRE CP but were not isolated in the postintervention period. Adverse events during the 2 periods were compared using segmented and mixed-effects Poisson regression models.RESULTSThere were 24,732 admissions in the preintervention period and 25,536 in the postintervention period. Noninfectious adverse events (ie, postoperative respiratory failure, hemorrhage/hematoma, thrombosis, wound dehiscence, pressure ulcers, and falls or trauma) decreased by 19% (12.3 to 10.0 per 1,000 admissions,P=.022) from the preintervention to the postintervention period. There was no significant difference in the rate of infectious adverse events after CP discontinuation (20.7 to 19.4 per 1,000 admissions,P=.33). Patients with MRSA/VRE showed the largest reduction in noninfectious adverse events after CP discontinuation, with a 72% reduction (21.4 to 6.08 per 1,000 MRSA/VRE admissions;P&lt;.001).CONCLUSIONAfter discontinuing routine CP for endemic MRSA/VRE, the rate of noninfectious adverse events declined, especially in patients who no longer required isolation. This suggests that elimination of CP may substantially reduce noninfectious adverse events.Infect Control Hosp Epidemiol2018;788–796


2021 ◽  
Vol 8 (Supplement_1) ◽  
pp. S297-S298
Author(s):  
Caroline Hamilton ◽  
Deepak Nag Ayyala ◽  
David Walsh ◽  
Christian-Jevon Bramwell ◽  
Christopher Walker ◽  
...  

Abstract Background More than half of all hospitals in the U.S. are rural hospitals. Frequently understaffed and resource limited, community hospitals serve a population that tends to be older and have less access to care with increased poverty and medical co-morbidities. There is a lack of data surrounding the impact of COVID-19 among rural minority communities. This study seeks to determine rural and urban disparities among hospitalized individuals with COVID-19. Methods This is a descriptive, retrospective analysis of the first 155 adult patients admitted to a tertiary hospital with a positive COVID-19 nasopharyngeal PCR test. Augusta University Medical Center serves the surrounding rural and urban counties of the Central Savannah River Area. Rural and urban categories were determined using patient address and county census data. Demographics, comorbidities, admission data and 30-day outcomes were evaluated. Results Of the patients studied, 62 (40%) were from a rural county and 93 (60%) were from an urban county. No difference was found when comparing the number of comorbidities of rural vs urban individuals; however, African Americans had significantly more comorbidities compared to other races (p-value 0.02). In a three-way comparison, race was not found to be significantly different among admission levels of care. Rural patients were more likely to require an escalation in the level of care within 24 hours of admission (p-value 0.02). Of the patients that were discharged or expired at day 30, there were no differences in total hospital length of stay or ICU length of stay between the rural and urban populations. Baseline Characteristics of Hospitalized Patients with COVID-19 Day 30 Outcomes and Characteristics Level of Care at Time of Admission Conclusion This study suggests that patients in rural communities may be more critically ill or are at a higher risk of early decompensation at time of hospitalization compared to patients from urban communities. Nevertheless, both populations had similar lengths of stay and outcomes. Considering this data is from an academic medical center with a large referral area and standardized inpatient COVID-19 management, these findings may prompt further investigations into other disparate outcomes. Disclosures All Authors: No reported disclosures


2018 ◽  
Vol 1 (2) ◽  
pp. 114
Author(s):  
Wahdaniah Wahdaniah ◽  
Sri Tumpuk

Abstract: Routine blood examination is the earliest blood test or screening test to determine the diagnosis of an abnormality. Blood easily froze if it is outside the body and can be prevented by the addition of anticoagulants, one of which Ethylene Diamine Tetra Acetate (EDTA). Currently available vacuum tubes containing EDTA anticoagulants in the form of K2EDTA and K3EDTA. K3EDTA is usually a salt that has better stability than other EDTA salts because it shows a pH approaching a blood pH of about 6.4. The purpose of this research is to know the difference of erythrocyte index results include MCH, MCV and MCHC using K3EDTA anticoagulant with K2EDTA. This research is a cross sectional design. This study used venous blood samples mixed with K2EDTA anticoagulant and venous blood mixed with K3EDTA anticoagulants, each of 30 samples. Data were collected and analyzed using paired different test. Based on data analysis that has been done on MCH examination, p value <0,05 then there is a significant difference between samples with K3EDTA anticoagulant with K2EDTA to erythrocyte index value. Then on the examination of MCV and MCHC obtained p value <0.05 then there is no significant difference between samples with K3EDTA anticoagulant with K2EDTA to erythrocyte index value.Abstrak: Pemeriksaan darah rutin merupakan pemeriksaan darah yang paling awal atau screening test untuk mengetahui diagnosis suatu kelainan. Darah mudah membeku jika berada diluar tubuh dan bisa dicegah dengan penambahan antikoagulan, salah satunya Ethylene Diamine Tetra Acetate (EDTA). Dewasa ini telah tersedia tabung vakum yang sudah berisi antikoagulan EDTA dalam bentuk  K2EDTA dan  K3EDTA. K3EDTA  biasanya berupa garam yang mempunyai stabilitas yang lebih baik dari garam EDTA yang lain karena menunjukkan pH yang mendekati pH darah yaitu sekitar 6,4. Tujuan dari penelitian ini adalah untuk mengetahui perbedaan hasil indeks eritrosit meliputi MCH, MCV dan MCHC menggunakan antikoagulan K3EDTA dengan K2EDTA. Penelitian ini merupakan penelitian dengan desain cross sectional. Penelitian ini menggunakan sampel darah vena yang dicampur dengan antikoagulan K2EDTA dan darah vena yang dicampur dengan antikoagulan K3EDTA, masing-masing sebanyak 30 sampel. Data dikumpulkan dan dianalisis menggunakan uji beda berpasangan. Berdasarkan analisis data yang telah dilakukan pada pemeriksaan MCH didapatkan nilai p < 0,05 maka ada perbedaan yang signifikan antara sampel dengan antikoagulan K3EDTA dengan K2EDTA terhadap nilai indeks eritrosit. Kemudian pada pemeriksaan MCV dan MCHC didapatkan nilai p < 0,05 maka tidak ada perbedaan yang signifikan antara sampel dengan antikoagulan K3EDTA dengan K2EDTA terhadap nilai indeks eritrosit.


2020 ◽  
Vol 41 (S1) ◽  
pp. s114-s115
Author(s):  
Alexandra Johnson ◽  
Bobby Warren ◽  
Deverick John Anderson ◽  
Melissa Johnson ◽  
Isabella Gamez ◽  
...  

Background: Stethoscopes are a known vector for microbial transmission; however, common strategies used to clean stethoscopes pose certain barriers that prevent routine cleaning after every use. We aimed to determine whether using readily available alcohol-based hand rub (ABHR) would effectively reduce bacterial bioburden on stethoscopes in a real-world setting. Methods: We performed a randomized study on inpatient wards of an academic medical center to assess the impact of using ABHR (AlcareExtra; ethyl alcohol, 80%) on the bacterial bioburden of stethoscopes. Stethoscopes were obtained from healthcare providers after routine use during an inpatient examination and were randomized to control (no intervention) or ABHR disinfection (2 pumps applied to tubing and bell or diaphragm by study personnel, then allowed to dry). Cultures of the tubing and bell or diaphragm were obtained with premoistened cellulose sponges. Sponges were combined with 1% Tween20-PBS and mixed in the Seward Stomacher. The homogenate was centrifuged and all but ~5 mL of the supernatant was discarded. Samples were plated on sheep’s blood agar and selective media for clinically important pathogens (CIPs) including S. aureus, Enterococcus spp, and gram-negative bacteria (GNB). CFU count was determined by counting the number of colonies on each plate and using dilution calculations to calculate the CFU of the original ~5 mL homogenate. Results: In total, 80 stethoscopes (40 disinfection, 40 control) were sampled from 46 physicians (MDs) and MD students (57.5%), 13 advanced practice providers (16.3%), and 21 nurses (RNs) and RN students (26.3%). The median CFU count was ~30-fold lower in the disinfection arm compared to control (106 [IQR, 50–381] vs 3,320 [986–4,834]; P < .0001). The effect was consistent across provider type, frequency of recent usual stethoscope cleaning, age, and status of pet ownership (Fig. 1). Overall, 26 of 80 (33%) of stethoscopes harbored CIP. The presence of CIP was lower but not significantly different for stethoscopes that underwent disinfection versus controls: S. aureus (25% vs 32.5%), Enterococcus (2.5% vs 10%), and GNB (2.5% vs 5%). Conclusions: Stethoscopes may serve as vectors for clean hands to become recontaminated immediately prior to performing patient care activities. Using ABHR to clean stethoscopes after every use is a practical and effective strategy to reduce overall bacterial contamination that can be easily incorporated into clinical workflow. Larger studies are needed to determine the efficacy of ABHR at removing CIP from stethoscopes as stethoscopes in both arms were frequently contaminated with CIP. Prior cleaning of stethoscopes on the study day did not seem to impact contamination rates, suggesting the impact of alcohol foam disinfection is short-lived and may need to be repeated frequently (ie, after each use).Funding: NoneDisclosures: NoneDisclosures: NoneFunding: None


Sign in / Sign up

Export Citation Format

Share Document