19 October 2022 in BMJ Open Quality
Objective In our public health system, a survey of reproductive-aged women identified lack of childcare as the most common reason for missing or delaying healthcare. Community-based organisations (CBOs) in our county identified a similar need, so we partnered to develop a hospital-based childcare centre for patients to use during appointments. Methods In a large academic public health system, a partnership with a non-profit childcare CBO was formed to address lack of childcare as a barrier to accessing healthcare. Pilot clinics where no-cost childcare would be offered included obstetrics, gynaecology and medical oncology. Transparent communication from the CBO within the electronic medical record was built to minimally impact clinic workflows. Visual and electronic outreach, including patient portal questionnaires, were created to introduce patients to the services. Personalised clinic staff in-services were performed to introduce the service to clinics and leadership. Continual assessments of workflow were conducted and adjusted based on patient and staff feedback and quality checks. At 12 months, overall utilisation of the service was collected. Results In the first 12 months that no-cost childcare was offered, 175 patients enrolled 271 children into the programme. Ninety-seven percent were women, primarily Hispanic (87/175 (50%)) or black (64/175 (37%)), with an average age of 31.8 years. Of the enrollees, 142/175 (81%) patients made 637 childcare appointments and 119/175 (68%) patients used at least one reservation for 191 children. Most patients were verbally referred by clinic staff for childcare or self-referred for childcare from clinic signage or paperwork. Childcare was requested most frequently for obstetrics and gynaecology appointments.
1 September 2024 in JAIDS Journal of Acquired Immune Deficiency Syndromes
Background: Effective measures exist to prevent the spread of HIV. However, the identification of patients who are candidates for these measures can be a challenge. A machine learning model to predict risk for HIV may enhance patient selection for proactive outreach. Setting: Using data from the electronic health record at Parkland Health, 1 of the largest public healthcare systems in the country, a machine learning model is created to predict incident HIV cases. The study cohort includes any patient aged 16 or older from 2015 to 2019 (n = 458,893). Methods: Implementing a 70:30 ratio random split of the data into training and validation sets with an incident rate <0.08% and stratified by incidence of HIV, the model is evaluated using a k-fold cross-validated (k = 5) area under the receiver operating characteristic curve leveraging Light Gradient Boosting Machine Algorithm, an ensemble classifier. Results: The light gradient boosting machine produces the strongest predictive power to identify good candidates for HIV PrEP. A gradient boosting classifier produced the best result with an AUC of 0.88 (95% confidence interval: 0.86 to 0.89) on the training set and 0.85 (95% confidence interval: 0.81 to 0.89) on the validation set for a sensitivity of 77.8% and specificity of 75.1%. Conclusions: A gradient boosting model using electronic health record data can be used to identify patients at risk of acquiring HIV and implemented in the clinical setting to build outreach for preventative interventions.
24 January 2025 in Applied Clinical Informatics
Global efforts aimed at ending human immunodeficiency virus (HIV) incidence have adapted and evolved since the turn of the century. The utilization of machine learning incorporated into an electronic health record (EHR) can be refined into prediction models that identify when an individual is at greater HIV infection risk. This can create a novel and innovative approach to identifying patients eligible for preventative therapy.This study's aim was to evaluate the effectiveness of an HIV prediction model in clinical workflows. Outcomes included preexposure prophylaxis (PrEP) prescriptions generated and the model's ability to identify eligible patients.A prediction model was developed and implemented at the safety-net hospital in Dallas County. Patients seen in primary care clinics were evaluated between July 2020 and June 2022. The prediction model was incorporated into an existing best practice advisory (BPA) used to identify potentially eligible PrEP patients. The prior, basic BPA (bBPA) displayed if a prior sexually transmitted infection was documented, and the enhanced BPA (eBPA) incorporated the HIV prediction model.A total of 3,218 unique patients received the BPA during the study time period, with 2,346 ultimately included for evaluation. There were 678 patients in the bBPA group and 1,666 in the eBPA group. PrEP prescriptions generated increased in the postimplementation group within the 90-day follow-up period (bBPA:1.48 vs. eBPA:3.67 prescriptions per month, p < 0.001). Patient demographics also differed between groups, resulting in a higher median age (bBPA: 36[interquartile range (IQR): 24] vs. eBPA: 52[QR: 19] years, p < 0.001) and an even distribution between birth sex in the postimplementation group (female sex at birth bBPA: 62.2% vs. eBPA:50.2%, p ≤ 0.001).The implementation of an HIV prediction model yielded a higher number of PrEP prescriptions generated and was associated with the identification of twice the number of potentially eligible patients.
9 August 2022 in Annals of Pharmacotherapy
Background: Antistaphylococcal penicillins and cefazolin are the treatments of choice for methicillin-susceptible Staphylococcus aureus (MSSA) infections, requiring multiple doses daily. At Parkland, eligible uninsured patients with MSSA bloodstream infections (BSI) receive self-administered outpatient parenteral antimicrobial therapy (S-OPAT). Ceftriaxone was used in a cohort of S-OPAT patients for ease of once-daily dosing. Objective: A retrospective study was conducted to evaluate clinical outcomes for patients discharged with ceftriaxone versus cefazolin to treat MSSA BSI. Methods: A retrospective cohort noninferiority study design was used to assess treatment efficacy of ceftriaxone versus cefazolin among Parkland S-OPAT patients treated from April 2012 to March 2020. Demographic, clinical, and treatment-related adverse events data were collected. Clinical outcomes included treatment failure as defined by repeat positive blood culture or retreatment within 6 months, all-cause 30-day readmission rates, and central line–associated bloodstream infection (CLABSI) rates. Results: Of 368 S-OPAT patients with MSSA BSI, 286 (77.7%) received cefazolin, and 82 (22.3%) received ceftriaxone. Demographics and comorbidities were similar for both groups. There were no treatment failures in the ceftriaxone group compared with 4 (1%) in the cefazolin group ( P = 0.58). No difference in 30-day readmission rate between groups was found. The CLABSI rates were lower in ceftriaxone group (2%) compared with cefazolin (11%; P = 0.02). Limitations include retrospective cohort design. Conclusions: Ceftriaxone was found to be noninferior to cefazolin in this study. Our findings suggest that ceftriaxone is a safe and effective treatment of MSSA BSI secondary to osteoarticular or skin and soft tissue infections when used in the S-OPAT setting. Poster OFID on 2018 Nov; 5(Suppl 1): S316: doi: 10.1093/ofid/ofy210.894.
14 June 2021 in Sexually Transmitted Diseases
Background: Chlamydia is the most reported bacterial sexually transmitted infection (STI). The rates of chlamydia rose by 19% between 2011 and 2018. The STI National Strategic Plan (2021–2025), encourages coordinated solutions to address STIs and reduce disparities in disadvantaged populations. Methods: We implemented institutional policy changes, clinical decision support, including a Best Practice Advisory, and defaulted SmartSet with provider and patient education for women's health clinics at a large county health system. The advisory prompted providers to follow best practices when treating Chlamydia trachomatis infections. New C. trachomatis diagnosis cohorts were compared preintervention and postintervention for 6-month reinfection rates and patient and expedited partner treatment (EPT) practices. Results: Five hundred and nineteen women were included in the final analysis. Six-month chlamydia reinfection was lower in the postintervention cohort after adjusting for age (12.3% [26/211] vs 6.5% [20/308], P = 0.02). There was an increase in directly observed therapy of primary patients (17.5% [37/211] vs 77.3% [238/308], P < 0.001), an increase in EPT prescriptions written (4.3% [9/211] vs 79.5% [245/308], P < 0.0001), and a decrease of partners referred out for treatment (61.6% [130/211] vs 5.2% [16/308], P < 0.001) when compared with the control group. The majority of EPT was patient-delivered partner therapy postintervention (3.3% [7/211] vs 69.2% [213/308], P < 0.001). Conclusions: A multifaceted, streamlined approach was effective in changing provider practices in the treatment of C. trachomatis. Increased rates of directly observed therapy for primary patient treatment and increased rates of patient-delivered partner therapy were observed postimplementation in addition to lower 6-month reinfection rates in a public women's health clinic setting.
25 November 2020 in Hospital Pharmacy
Adverse drug events (ADEs) result in excess hospitalizations. Thorough admission medication histories (AMHs) may prevent ADEs; however, the resources required oftentimes outweigh what is available in large hospital settings. Previous risk prediction models embedded into the Electronic Medical Record (EMR) have been used at hospitals to aid in targeting delivery of scarce resources. To determine if an AMH scoring tool used to allocate resources can decrease 30-day hospital readmissions. Propensity-matched cohort study, Medicine/Surgery patients in large academic safety-net hospital. Pharmacy-conducted AMHs identified by risk model versus standard of care AMH. A total of 30-day hospital readmissions and inpatient ADE prevention. The model screened 87 240 hospitalizations between June 2017 and June 2019 and 4027 patients per group were included. There were significantly less 30 day readmissions among high-risk identified patients that received a pharmacy-conducted AMH compared to controls (11% vs 15%; P = 0.004) and no significant difference in readmission rates for low-risk patients. While there was significantly higher documentation of major ADE prevention in the pharmacy-led AMH group versus control (1656 vs 12; P < 0.001), there was no difference in electronically-detected inpatient ADEs between groups. A risk tool embedded into the EMR can be used to identify patients whom pharmacy teams can easily target for AMHs. This study showed significant reductions in readmissions for patients identified as high-risk. However, the same benefit in readmissions was not seen in those identified at low-risk, which supports allocating resources to those that will benefit the most.