Browsing by Author "Alhanti, Brooke"
Now showing 1 - 8 of 8
Results Per Page
Sort Options
Item Open Access Evaluation of ML-Based Clinical Decision Support Tool to Replace an Existing Tool in an Academic Health System: Lessons Learned.(Journal of personalized medicine, 2020-08-27) Woo, Myung; Alhanti, Brooke; Lusk, Sam; Dunston, Felicia; Blackwelder, Stephen; Lytle, Kay S; Goldstein, Benjamin A; Bedoya, ArmandoThere is increasing application of machine learning tools to problems in healthcare, with an ultimate goal to improve patient safety and health outcomes. When applied appropriately, machine learning tools can augment clinical care provided to patients. However, even if a model has impressive performance characteristics, prospectively evaluating and effectively implementing models into clinical care remains difficult. The primary objective of this paper is to recount our experiences and challenges in comparing a novel machine learning-based clinical decision support tool to legacy, non-machine learning tools addressing potential safety events in the hospitals and to summarize the obstacles which prevented evaluation of clinical efficacy of tools prior to widespread institutional use. We collected and compared safety events data, specifically patient falls and pressure injuries, between the standard of care approach and machine learning (ML)-based clinical decision support (CDS). Our assessment was limited to performance of the model rather than the workflow due to challenges in directly comparing both approaches. We did note a modest improvement in falls with ML-based CDS; however, it was not possible to determine that overall improvement was due to model characteristics.Item Open Access Impact of Wildfire Smoke on Acute Illness.(Anesthesiology, 2024-10) Hughes, Fintan; Parsons, Luke; Levy, Jerrold H; Shindell, Drew; Alhanti, Brooke; Ohnuma, Tetsu; Kasibhatla, Prasad; Montgomery, Hugh; Krishnamoorthy, VijayClimate change increases wildfire smoke exposure. Inhaled smoke causes inflammation, oxidative stress, and coagulation, which exacerbate cardiovascular and respiratory disease while worsening obstetric and neonatal outcomes.Item Open Access Patterns of Referral and Postdischarge Utilization of Cardiac Rehabilitation Among Patients Hospitalized With Heart Failure: An Analysis From the GWTG-HF Registry.(Circulation. Heart failure, 2023-08) Keshvani, Neil; Subramanian, Vinayak; Wrobel, Christopher A; Solomon, Nicole; Alhanti, Brooke; Greene, Stephen J; DeVore, Adam D; Yancy, Clyde W; Allen, Larry A; Fonarow, Gregg C; Pandey, AmbarishBackground
Coverage for cardiac rehabilitation (CR) for patients with heart failure with reduced ejection fraction was expanded in 2014, but contemporary referral and participation rates remain unknown.Methods
Patients hospitalized for heart failure with reduced ejection fraction (≤35%) in the American Heart Association Get With The Guidelines-Heart Failure registry from 2010 to 2020 were included, and CR referral status was described as yes, no, or not captured. Temporal trends in CR referral were assessed in the overall cohort. Patient and hospital-level predictors of CR referral were assessed using multivariable-adjusted logistic regression models. Additionally, CR referral and proportional utilization of CR within 1-year of referral were evaluated among patients aged >65 years with available Medicare administrative claims data who were clinically stable for 6-weeks postdischarge. Finally, the association of CR referral with the risk of 1-year death and readmission was evaluated using multivariable-adjusted Cox models.Results
Of 69,441 patients with heart failure with reduced ejection fraction who were eligible for CR (median age 67 years; 33% women; 30% Black), 17,076 (24.6%) were referred to CR, and referral rates increased from 8.1% in 2010 to 24.1% in 2020 (Ptrend<0.001). Of 8310 patients with Medicare who remained clinically stable 6-weeks after discharge, the CR referral rate was 25.8%, and utilization of CR among referred patients was 4.1% (mean sessions attended: 6.7). Patients not referred were more likely to be older, of Black race, and with a higher burden of comorbidities. In adjusted analysis, eligible patients with heart failure with reduced ejection fraction who were referred to CR (versus not referred) had a lower risk of 1-year death (hazard ratio, 0.84 [95% CI, 0.70-1.00]; P=0.049) without significant differences in 1-year readmission.Conclusions
CR referral rates have increased from 2010 to 2020. However, only 1 in 4 patients are referred to CR. Among eligible patients who received CR referral, participation was low, with <1 of 20 participating in CR.Item Open Access Prevalence and predictors of no-shows to physical therapy for musculoskeletal conditions.(PloS one, 2021-01) Bhavsar, Nrupen A; Doerfler, Shannon M; Giczewska, Anna; Alhanti, Brooke; Lutz, Adam; Thigpen, Charles A; George, Steven ZObjectives
Chronic pain affects 50 million Americans and is often treated with non-pharmacologic approaches like physical therapy. Developing a no-show prediction model for individuals seeking physical therapy care for musculoskeletal conditions has several benefits including enhancement of workforce efficiency without growing the existing provider pool, delivering guideline adherent care, and identifying those that may benefit from telehealth. The objective of this paper was to quantify the national prevalence of no-shows for patients seeking physical therapy care and to identify individual and organizational factors predicting whether a patient will be a no-show when seeking physical therapy care.Design
Retrospective cohort study.Setting
Commercial provider of physical therapy within the United States with 828 clinics across 26 states.Participants
Adolescent and adult patients (age cutoffs: 14-117 years) seeking non-pharmacological treatment for musculoskeletal conditions from January 1, 2016, to December 31, 2017 (n = 542,685). Exclusion criteria were a primary complaint not considered an MSK condition or improbable values for height, weight, or body mass index values. The study included 444,995 individuals.Primary and secondary outcome measures
Prevalence of no-shows for musculoskeletal conditions and predictors of patient no-show.Results
In our population, 73% missed at least 1 appointment for a given physical therapy care episode. Our model had moderate discrimination for no-shows (c-statistic:0.72, all appointments; 0.73, first 7 appointments) and was well calibrated, with predicted and observed no-shows in good agreement. Variables predicting higher no-show rates included insurance type; smoking-status; higher BMI; and more prior cancellations, time between visit and scheduling date, and between current and previous visit.Conclusions
The high prevalence of no-shows when seeking care for musculoskeletal conditions from physical therapists highlights an inefficiency that, unaddressed, could limit delivery of guideline-adherent care that advocates for earlier use of non-pharmacological treatments for musculoskeletal conditions and result in missed opportunities for using telehealth to deliver physical therapy.Item Open Access Risk of obstetric anal sphincter injuries at the time of admission for delivery: A clinical prediction model.(BJOG : an international journal of obstetrics and gynaecology, 2022-11) Luchristt, Douglas; Meekins, Ana Rebecca; Zhao, Congwen; Grotegut, Chad; Siddiqui, Nazema Y; Alhanti, Brooke; Jelovsek, John EricObjective
To develop and validate a model to predict obstetric anal sphincter injuries (OASIS) using only information available at the time of admission for labour.Design
A clinical predictive model using a retrospective cohort.Setting
A US health system containing one community and one tertiary hospital.Sample
A total of 22 873 pregnancy episodes with in-hospital delivery at or beyond 21 weeks of gestation.Methods
Thirty antepartum risk factors were identified as candidate variables, and a prediction model was built using logistic regression predicting OASIS versus no OASIS. Models were fit using the overall study population and separately using hospital-specific cohorts. Bootstrapping was used for internal validation and external cross-validation was performed between the two hospital cohorts.Main outcome measures
Model performance was estimated using the bias-corrected concordance index (c-index), calibration plots and decision curves.Results
Fifteen risk factors were retained in the final model. Decreasing parity, previous caesarean birth and cardiovascular disease increased risk of OASIS, whereas tobacco use and black race decreased risk. The final model from the total study population had good discrimination (c-index 0.77, 95% confidence interval [CI] 0.75-0.78) and was able to accurately predict risks between 0 and 35%, where average risk for OASIS was 3%. The site-specific model fit using patients only from the tertiary hospital had c-stat 0.74 (95% CI 0.72-0.77) on community hospital patients, and the community hospital model was 0.77 (95%CI 0.76-0.80) on the tertiary hospital patients.Conclusions
OASIS can be accurately predicted based on variables known at the time of admission for labour. These predictions could be useful for selectively implementing OASIS prevention strategies.Item Open Access Shorter Door-to-Needle Times Are Associated With Better Outcomes After Intravenous Thrombolytic Therapy and Endovascular Thrombectomy for Acute Ischemic Stroke.(Circulation, 2023-07) Man, Shumei; Solomon, Nicole; Mac Grory, Brian; Alhanti, Brooke; Uchino, Ken; Saver, Jeffrey L; Smith, Eric E; Xian, Ying; Bhatt, Deepak L; Schwamm, Lee H; Hussain, Muhammad Shazam; Fonarow, Gregg CBackground
Existing data and clinical trials could not determine whether faster intravenous thrombolytic therapy (IVT) translates into better long-term functional outcomes after acute ischemic stroke among those treated with endovascular thrombectomy (EVT). Patient-level national data can provide the required large population to study the associations between earlier IVT, versus later, with longitudinal functional outcomes and mortality in patients receiving IVT+EVT combined treatment.Methods
This cohort study included older US patients (age ≥65 years) who received IVT within 4.5 hours or EVT within 7 hours after acute ischemic stroke using the linked 2015 to 2018 Get With The Guidelines-Stroke and Medicare database (38 913 treated with IVT only and 3946 with IVT+EVT). Primary outcome was home time, a patient-prioritized functional outcome. Secondary outcomes included all-cause mortality in 1 year. Multivariate logistic regression and Cox proportional hazards models were used to evaluate the associations between door-to-needle (DTN) times and outcomes.Results
Among patients treated with IVT+EVT, after adjusting for patient and hospital factors, including onset-to-EVT times, each 15-minute increase in DTN times for IVT was associated with significantly higher odds of zero home time in a year (never discharged to home) (adjusted odds ratio, 1.12 [95% CI, 1.06-1.19]), less home time among those discharged to home (adjusted odds ratio, 0.93 per 1% of 365 days [95% CI, 0.89-0.98]), and higher all-cause mortality (adjusted hazard ratio, 1.07 [95% CI, 1.02-1.11]). These associations were also statistically significant among patients treated with IVT but at a modest degree (adjusted odds ratio, 1.04 for zero home time, 0.96 per 1% home time for those discharged to home, and adjusted hazard ratio 1.03 for mortality). In the secondary analysis where the IVT+EVT group was compared with 3704 patients treated with EVT only, shorter DTN times (≤60, 45, and 30 minutes) achieved incrementally more home time in a year, and more modified Rankin Scale 0 to 2 at discharge (22.3%, 23.4%, and 25.0%, respectively) versus EVT only (16.4%, P<0.001 for each). The benefit dissipated with DTN>60 minutes.Conclusions
Among older patients with stroke treated with either IVT only or IVT+EVT, shorter DTN times are associated with better long-term functional outcomes and lower mortality. These findings support further efforts to accelerate thrombolytic administration in all eligible patients, including EVT candidates.Item Open Access Time to Anticoagulation Reversal and Outcomes After Intracerebral Hemorrhage.(JAMA neurology, 2024-02) Sheth, Kevin N; Solomon, Nicole; Alhanti, Brooke; Messe, Steven R; Xian, Ying; Bhatt, Deepak L; Hemphill, J Claude; Frontera, Jennifer A; Chang, Raymond C; Danelich, Ilya M; Huang, Joanna; Schwamm, Lee; Smith, Eric E; Goldstein, Joshua N; Mac Grory, Brian; Fonarow, Gregg C; Saver, Jeffrey LImportance
Intracerebral hemorrhage (ICH) is the deadliest stroke subtype, and mortality rates are especially high in anticoagulation-associated ICH. Recently, specific anticoagulation reversal strategies have been developed, but it is not clear whether there is a time-dependent treatment effect for door-to-treatment (DTT) times in clinical practice.Objective
To evaluate whether DTT time is associated with outcome among patients with anticoagulation-associated ICH treated with reversal interventions.Design, setting, and participants
This cohort study used data from the American Heart Association Get With The Guidelines-Stroke quality improvement registry. Patients with ICH who presented within 24 hours of symptom onset across 465 US hospitals from 2015 to 2021 were included. Data were analyzed from January to September 2023.Exposures
Anticoagulation-associated ICH.Main outcomes and measures
DTT times and outcomes were analyzed using logistic regression modeling, adjusted for demographic, history, baseline, and hospital characteristics, with hospital-specific random intercepts to account for clustering by site. The primary outcome of interest was the composite inpatient mortality and discharge to hospice. Additional prespecified secondary outcomes, including functional outcome (discharge modified Rankin Scale score, ambulatory status, and discharge venue), were also examined.Results
Of 9492 patients with anticoagulation-associated ICH and documented reversal intervention status, 4232 (44.6%) were female, and the median (IQR) age was 77 (68-84) years. A total of 7469 (78.7%) received reversal therapy, including 4616 of 5429 (85.0%) taking warfarin and 2856 of 4069 (70.2%) taking a non-vitamin K antagonist oral anticoagulant. For the 5224 patients taking a reversal intervention with documented workflow times, the median (IQR) onset-to-treatment time was 232 (142-482) minutes and the median (IQR) DTT time was 82 (58-117) minutes, with a DTT time of 60 minutes or less in 1449 (27.7%). A DTT time of 60 minutes or less was associated with decreased mortality and discharge to hospice (adjusted odds ratio, 0.82; 95% CI, 0.69-0.99) but no difference in functional outcome (ie, a modified Rankin Scale score of 0 to 3; adjusted odds ratio, 0.91; 95% CI, 0.67-1.24). Factors associated with a DTT time of 60 minutes or less included White race, higher systolic blood pressure, and lower stroke severity.Conclusions and relevance
In US hospitals participating in Get With The Guidelines-Stroke, earlier anticoagulation reversal was associated with improved survival for patients with ICH. These findings support intensive efforts to accelerate evaluation and treatment for patients with this devastating form of stroke.Item Open Access Trends in Stroke Thrombolysis Care Metrics and Outcomes by Race and Ethnicity, 2003-2021.(JAMA network open, 2024-02) Man, Shumei; Solomon, Nicole; Mac Grory, Brian; Alhanti, Brooke; Saver, Jeffrey L; Smith, Eric E; Xian, Ying; Bhatt, Deepak L; Schwamm, Lee H; Uchino, Ken; Fonarow, Gregg CImportance
Understanding is needed of racial and ethnic-specific trends in care quality and outcomes associated with the US nationwide quality initiative Target: Stroke (TS) in targeting thrombolysis treatment for acute ischemic stroke.Objective
To examine whether the TS quality initiative was associated with improvement in thrombolysis metrics and outcomes across racial and ethnic groups.Design, setting, and participants
This retrospective cohort study included patients who presented within 4.5 hours of ischemic stroke onset at hospitals participating in the Get With The Guidelines-Stroke initiative from January 1, 2003, to December 31, 2021. The data analysis was performed between December 15, 2022, and November 27, 2023.Exposures
TS phases I (2010-2013), II (2014-2018), and III (2019-2021).Main outcomes and measures
The primary outcomes were thrombolysis rates and time metrics. Patient function and mortality were secondary outcomes.Results
Analyses included 1 189 234 patients, of whom 1 053 539 arrived to the hospital within 4.5 hours. The cohort included 50.4% female and 49.6% male patients and 2.8% Asian [median (IQR) age, 72 (61-82) years], 15.2% Black [median (IQR) age, 64 (54-75) years], 7.3% Hispanic [median (IQR) age, 68 (56-79) years], and 74.1% White [median (IQR) age, 75 (63-84) years] patients). Unadjusted thrombolysis rates increased in both the pre-TS (2003-2009) and TS periods in all racial and ethnic groups from 10% to 15% in 2003 to 43% to 46% in 2021, but disparities were observed in adjusted analyses and persisted in TS phase III, with Asian, Black, and Hispanic patients having significantly lower odds of receiving thrombolysis than White patients (adjusted odds ratio, 0.85 [95% CI, 0.81-0.90], 0.76 [95% CI, 0.74-0.78], and 0.86 [95% CI, 0.83-0.89], respectively). Door-to-needle (DTN) times improved in all racial and ethnic groups during TS, with DTN times of 60 minutes or less increasing from 26% to 28% in 2009 to 66% to 72% in 2021. However, in adjusted analyses, racial and ethnic disparities emerged. During TS phase III, compared with White patients, Asian, Black, and Hispanic patients had significantly lower odds of receiving thrombolysis with a DTN time of 60 minutes or less compared with White patients (risk-adjusted odds ratios, 0.91 [95% CI, 0.84-0.98], 0.78 [95% CI, 0.75-0.81], and 0.87 [95% CI, 0.83-0.92], respectively). During TS, clinical outcomes improved for all racial and ethnic groups from pre-TS, with TS phase III showing higher odds of ambulation at discharge among Asian, Black, Hispanic, and White patients. Asian, Black, and Hispanic patients were less likely to present within 4.5 hours.Conclusions and relevance
In this cohort study of patients with ischemic stroke, the TS quality initiative was associated with improvement in thrombolysis frequency, timeliness, and outcomes for all racial and ethnic groups. However, disparities persisted, indicating a need for further interventions.