Publications by authors named "Heather E Hsu"

Objective: To develop an Artificial Intelligence (AI)-based anomaly detection model as a complement of an "astute physician" in detecting novel disease cases in a hospital and preventing emerging outbreaks.

Methods: Data included hospitalized patients (n = 120,714) at a safety-net hospital in Massachusetts. A novel Generative Pre-trained Transformer (GPT)-based clinical anomaly detection system was designed and further trained using Empirical Risk Minimization (ERM), which can model a hospitalized patient's Electronic Health Records (EHR) and detect atypical patients.

View Article and Find Full Text PDF

Objective: To examine the influence of having a baseline metabolic disorder (diabetes, hypertension, and/or obesity) on the risk of developing new clinical sequelae potentially related to SARS-CoV-2 in a large sample of commercially insured adults in the US.

Design Setting And Participants: Deidentified data were collected from the IBM/Watson MarketScan Commercial Claims and Encounters (CCAE) Databases and Medicare Supplemental and Coordination of Benefits (MDCR) Databases from 2019 to 2021. A total of 839,344 adults aged 18 and above with continuous enrollment in the health plan were included in the analyses.

View Article and Find Full Text PDF
Article Synopsis
  • - Nia, a first-grade student with a traumatic background, frequently visited emergency departments for severe behavioral issues, leading to hospitalization and the use of physical restraints, illustrating the challenges faced by children in crisis and the healthcare system's responses.
  • - Her experiences reveal how structural racism and adultification bias unfairly label Black youth, misinterpreting their behaviors as problematic rather than as typical responses to trauma, poverty, and domestic violence.
  • - The text discusses the broader issues of racism in health care and education, highlighting racial disparities in mental health treatment, school discipline, and the role of these systems in perpetuating the school-to-prison pipeline, while also proposing strategies to address these inequalities.
View Article and Find Full Text PDF

Importance: Current disease risk-adjustment formulas in the US rely on diagnostic classification frameworks that predate the .

Objective: To develop an -based classification framework for predicting diverse health care payment, quality, and performance outcomes.

Design Setting And Participants: Physician teams mapped all diagnoses into 3 types of diagnostic items (DXIs): main effect DXIs that specify diseases; modifiers, such as laterality, timing, and acuity; and scaled variables, such as body mass index, gestational age, and birth weight.

View Article and Find Full Text PDF

Background: Despite increasing vaccination rates, coronavirus disease 2019 (COVID-19) continues to overwhelm heath systems worldwide. Few studies follow outpatients diagnosed with COVID-19 to understand risks for subsequent admissions. We sought to identify hospital admission risk factors in individuals with COVID-19 to guide outpatient follow-up and prioritization for novel therapeutics.

View Article and Find Full Text PDF

Among 287 US hospitals reporting data between 2015 and 2018, annual pediatric surgical site infection (SSI) rates ranged from 0% for gallbladder to 10.4% for colon surgeries. Colon, spinal fusion, and small-bowel SSI rates did not decrease with greater surgical volumes in contrast to appendix and ventricular-shunt SSI rates.

View Article and Find Full Text PDF

Background: The coronavirus disease 2019 (COVID-19) pandemic disrupted access to and uptake of hepatitis C virus (HCV) care services in the United States. It is unknown how substantially the pandemic will impact long-term HCV-related outcomes.

Methods: We used a microsimulation to estimate the 10-year impact of COVID-19 disruptions in healthcare delivery on HCV outcomes including identified infections, linkage to care, treatment initiation and completion, cirrhosis, and liver-related death.

View Article and Find Full Text PDF

To determine the association between immunosuppression and time to severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) polymerase chain reaction (PCR) clearance, we studied 3758 adults retested following initial SARS-CoV-2 infection. Cox proportional hazards models demonstrated delayed PCR clearance with older age, multiple comorbidities, and solid organ transplant but not by degree of immunocompromise. These findings challenge current retesting practices.

View Article and Find Full Text PDF

This cross-sectional study uses national claims data to assess trends in well-child care visits with out-of-pocket costs before and after passage of the Affordable Care Act.

View Article and Find Full Text PDF

Importance: Central catheter-associated bloodstream infections (CLABSIs) and catheter-associated urinary tract infections (CAUTIs) increase morbidity, mortality, and health care costs in pediatric patients.

Objective: To examine changes over time in CLABSI and CAUTI rates between 2013 and 2018 in neonatal intensive care units (NICUs) and pediatric intensive care units (PICUs) using prospective surveillance data from community hospitals, children's hospitals, and pediatric units within general hospitals.

Design, Setting, And Participants: This time series study included 176 US hospitals reporting pediatric health care-associated infection surveillance data to the National Healthcare Safety Network from January 1, 2013, to June 30, 2018.

View Article and Find Full Text PDF
Article Synopsis
  • As of July 2020, the U.S. reported about 2.8 million COVID-19 cases and 130,000 related deaths, disproportionately affecting racial and ethnic minorities as well as individuals experiencing homelessness.
  • Boston Medical Center treated 2,729 COVID-19 patients from March to May 2020, with a majority being managed as outpatients (56.5%), while 3.6% of patients died during this period.
  • The patient demographics revealed that 44.6% were non-Hispanic Black and 30.1% Hispanic, with higher hospitalization rates among Hispanic patients (46.5%) compared to Black (
View Article and Find Full Text PDF

Importance: In the US, federal value-based incentive programs are more likely to penalize safety-net institutions than non-safety-net institutions. Whether these programs differentially change the rates of targeted health care-associated infections in safety-net vs non-safety-net hospitals is unknown.

Objective: To assess the association of Hospital-Acquired Condition Reduction Program (HACRP) and Hospital Value-Based Purchasing (HVBP) implementation with changes in rates of targeted health care-associated infections and disparities in rates among safety-net and non-safety-net hospitals.

View Article and Find Full Text PDF

Importance: On October 1, 2015, the US transitioned to the International Classification of Diseases, Tenth Revision, Clinical Modification (ICD-10-CM) for recording diagnoses, symptoms, and procedures. It is unknown whether this transition was associated with changes in diagnostic category prevalence based on diagnosis classification systems commonly used for payment and quality reporting.

Objective: To assess changes in diagnostic category prevalence associated with the ICD-10-CM transition.

View Article and Find Full Text PDF

Most states prohibit utility companies from terminating service to low-income households when occupants present a medical letter confirming a household member has a chronic serious illness. It is unclear how many patients receive these letters and whether screening for health-related social needs (HRSN) identifies these patients. We analyzed characteristics of adult patients at a safety-net hospital with a utility shut-off protection letter 2009-2018.

View Article and Find Full Text PDF

Pediatric sepsis is a major public health concern, and robust surveillance tools are needed to characterize its incidence, outcomes, and trends. The increasing use of electronic health records (EHRs) in the United States creates an opportunity to conduct reliable, pragmatic, and generalizable population-level surveillance using routinely collected clinical data rather than administrative claims or resource-intensive chart review. In 2015, the US Centers for Disease Control and Prevention recruited sepsis investigators and representatives of key professional societies to develop an approach to adult sepsis surveillance using clinical data recorded in EHRs.

View Article and Find Full Text PDF