Improved compliance with reporting standards: A retrospective analysis of Intersocietal Accreditation Commission Nuclear Cardiology Laboratories

Automated abstraction of myocardial perfusion imaging reports using natural language processing

BACKGROUND

Findings and interpretations of myocardial perfusion imaging (MPI) studies are documented in free-text MPI reports. MPI results are essential for research, but manual review is prohibitively time consuming. This study aimed to develop and validate an automated method to abstract MPI reports.

METHODS

We developed a natural language processing (NLP) algorithm to abstract MPI reports. Randomly selected reports were double-blindly reviewed by two cardiologists to validate the NLP algorithm. Secondary analyses were performed to describe patient outcomes based on abstracted-MPI results on 16,957 MPI tests from adult patients evaluated for suspected ACS.

RESULTS

The NLP algorithm achieved high sensitivity (96.7%) and specificity (98.9%) on the MPI categorical results and had a similar degree of agreement compared to the physician reviewers. Patients with abnormal MPI results had higher rates of 30-day acute myocardial infarction or death compared to patients with normal results. We identified issues related to the quality of the reports that not only affect communication with referring physicians but also challenges for automated abstraction.

CONCLUSION

NLP is an accurate and efficient strategy to abstract results from the free-text MPI reports. Our findings will facilitate future research to understand the benefits of MPI studies but requires validation in other settings.

Impact of accreditation on health care services performance in Kiryandongo district, Uganda: a longitudinal study

Background

The COVID-19 pandemic has emphasised the need for quality laboratory services worldwide. There is renewed focus to strengthen country capacities and laboratories to effectively respond to public health emergencies and patient outcomes. Uganda launched the accreditation program for public health facilities in 2016 with sixteen laboratories. As of June 2021, twenty-three public laboratories have attained ISO 15189:2012 accreditation status. Despite the tremendous achievements of accrediting laboratories in Uganda, laboratory services still face challenges like stock out of commodities and limited testing scopes. We conducted this study to evaluate the impact of accreditation on health care services performance in Kiryandongo district, Uganda.

Methods

We conducted a longitudinal study from January 1, 2020- April 30, 2021 at ten health facilities in Kiryandongo district. We collected health care services performance data from the MoH dhis-2 on selected indicators for HIV, TB, Malaria, Laboratory, Maternal & child health and dhis-2 reporting. We used Generalized Estimating Equations to estimate the impact of accreditation on health care services performance at the different health facilities.

Results

The odds at the accredited facility in comparison to the non-accredited public facilities were; 14% higher for ART enrolment (OR = 1.14, 95% CI: 1.04–1.25), 9% lower for determine testing kits stock out (OR = 0.91, 95% CI: 0.85–0.97), 28% higher for TB case diagnosis (OR = 1.28, 95% CI: 1.10–1.49), 19% higher for TB case enrolment (OR = 1.19, 95% CI: 1.04–1.36), 104% higher for maternity admissions (OR = 2.04, 95% CI: 1.60–2.59), 63% higher for maternity deliveries (OR = 1.63, 95% CI: 1.39–1.90) and 17% higher for reporting hmis 10:01 data to dhis-2 (OR = 1.17, 95% CI: 1.04–1.31).

The odds at the accredited facility in comparison to the non-accredited PNFP facilities were; 26% higher for ART enrolment (OR = 1.26, 95% CI: 1.17–1.36), 33% higher for TB case diagnosis (OR = 1.33, 95% CI: 1.15–1.55), 24% higher for TB case enrolment (OR = 1.24, 95% CI: 1.09–1.42), 136% higher for maternity admissions (OR = 2.36, 95% CI: 1.89–2.94), 76% higher for maternity deliveries (OR = 1.76, 95% CI: 1.51–2.04) and 2% higher for reporting of hmis-10:01 data to dhis-2 (OR = 1.02, 95% CI: 1.01–1.03).

Conclusions

HIV, TB, laboratory, MCH, and reporting to dhis-2 selected indicators were positively impacted by accreditation. This impact translated into increased health care services performance at the accredited facility as compared to the non-accredited facilities.

Insights into Nuclear Cardiology in the United States from the first 3 years of the ImageGuide Registry

BACKGROUND

Data registries facilitate knowledge acquisition and quality improvement. ImageGuide is a registry developed by the American Society of Nuclear Cardiology collecting data since 2015, providing insight into current nuclear cardiology practice.

METHODS AND RESULTS

HIPAA de-identified data on > 100 practice- and patient-related variables from 19 US practices were obtained from ImageGuide. Continuous variables are reported as the mean ± standard deviation; discrete variables are reported as N (%). Practices were from 12 states; 9520 studies were submitted. The average patient was a 66-year-old man. Chest pain was the most common indication; 96% of studies were appropriate. Rest/stress 1-day studies were most common; stress/rest 1- and 2-day studies comprised < 5%. Tc-99 m was the most common radiopharmaceutical. Tl-201 was used in 14% of rest studies. Most studies were not corrected for attenuation. 89% were of good or better quality. 62% of studies were normal.

CONCLUSIONS

Practice diversity is limited, but patient demographics are reflective of reported current practice. Most studies are appropriate and may obviate the need for invasive testing. Radiation dosimetry could be decreased with wider adoption of stress/rest studies and avoidance of Tl-201. ImageGuide will be an important tool to guide non-invasive cardiac imaging in the future.