The value of standards for health datasets in artificial intelligence-based applications

Artificial intelligence as a medical device is increasingly being applied to healthcare for diagnosis, risk stratification and resource allocation. However, a growing body of evidence has highlighted the risk of algorithmic bias, which may perpetuate existing health inequity. This problem arises in part because of systemic inequalities in dataset curation, unequal opportunity to participate in research and inequalities of access. This study aims to explore existing standards, frameworks and best practices for ensuring adequate data diversity in health datasets. Exploring the body of existing literature and expert views is an important step towards the development of consensus-based guidelines. The study comprises two parts: a systematic review of existing standards, frameworks and best practices for healthcare datasets; and a survey and thematic analysis of stakeholder views of bias, health equity and best practices for artificial intelligence as a medical device. We found that the need for dataset diversity was well described in literature, and experts generally favored the development of a robust set of guidelines, but there were mixed views about how these could be implemented practically. The outputs of this study will be used to inform the development of standards for transparency of data diversity in health datasets (the STANDING Together initiative).

Cardiovascular Subphenotypes in Acute Respiratory Distress Syndrome

OBJECTIVES

To use clustering methods on transthoracic echocardiography (TTE) findings and hemodynamic parameters to characterize circulatory failure subphenotypes and potentially elucidate underlying mechanisms in patients with acute respiratory distress syndrome (ARDS) and to describe their association with mortality compared with current definitions of right ventricular dysfunction (RVD).

DESIGN

Retrospective, single-center cohort study.

SETTING

University Hospital ICU, Birmingham, United Kingdom.

PATIENTS

ICU patients that received TTE within 7 days of ARDS onset between April 2016 and December 2021.

INTERVENTIONS

None.

MEASUREMENTS AND MAIN RESULTS

Latent class analysis (LCA) of TTE/hemodynamic parameters was performed in 801 patients, 62 years old (interquartile range, 50-72 yr old), 63% male, and 40% 90-day mortality rate. Four cardiovascular subphenotypes were identified: class 1 (43%; mostly normal left and right ventricular [LV/RV] function), class 2 (24%; mostly dilated RV with preserved systolic function), class 3 (13%, mostly dilated RV with impaired systolic function), and class 4 (21%; mostly high cardiac output, with hyperdynamic LV function). The four subphenotypes differed in their characteristics and outcomes, with 90-day mortality rates of 19%, 40%, 78%, and 59% in classes 1-4, respectively ( p < 0.0001). Following multivariable logistic regression analysis, class 3 had the highest odds ratio (OR) for mortality (OR, 6.9; 95% CI, 4.0-11.8) compared with other RVD definitions. Different three-variable models had high diagnostic accuracy in identifying each of these latent subphenotypes.

CONCLUSIONS

LCA of TTE parameters identified four cardiovascular subphenotypes in ARDS that more closely aligned with circulatory failure mechanisms and mortality than current RVD definitions.

Cardiovascular subphenotypes in patients with COVID-19 pneumonitis whose lungs are mechanically ventilated: a single-centre retrospective observational study

Unsupervised clustering methods of transthoracic echocardiography variables have not been used to characterise circulatory failure mechanisms in patients with COVID‐19 pneumonitis. We conducted a retrospective, single‐centre cohort study in ICU patients with COVID‐19 pneumonitis whose lungs were mechanically ventilated and who underwent transthoracic echocardiography between March 2020 and May 2021. We performed latent class analysis of echocardiographic and haemodynamic variables. We characterised the identified subphenotypes by comparing their clinical parameters, treatment responses and 90‐day mortality rates. We included 305 patients with a median (IQR [range]) age 59 (49–66 [16–83]) y. Of these, 219 (72%) were male, 199 (65%) had moderate acute respiratory distress syndrome and 113 (37%) did not survive more than 90 days. Latent class analysis identified three cardiovascular subphenotypes: class 1 (52%; normal right ventricular function); class 2 (31%; right ventricular dilation with mostly preserved systolic function); and class 3 (17%; right ventricular dilation with systolic impairment). The three subphenotypes differed in their clinical characteristics and response to prone ventilation and outcomes, with 90‐day mortality rates of 22%, 42% and 73%, respectively (p < 0.001). We conclude that the identified subphenotypes aligned with right ventricular pathophysiology rather than the accepted definitions of right ventricular dysfunction, and these identified classifications were associated with clinical outcomes.

Right Ventricular Dysfunction and Its Association With Mortality in Coronavirus Disease 2019 Acute Respiratory Distress Syndrome

OBJECTIVES

To assess whether right ventricular dilation or systolic impairment is associated with mortality and/or disease severity in invasively ventilated patients with coronavirus disease 2019 acute respiratory distress syndrome.

DESIGN

Retrospective cohort study.

SETTING

Single-center U.K. ICU.

PATIENTS

Patients with coronavirus disease 2019 acute respiratory distress syndrome undergoing invasive mechanical ventilation that received a transthoracic echocardiogram between March and December 2020.

INTERVENTION

None.

MEASUREMENTS AND MAIN RESULTS

Right ventricular dilation was defined as right ventricular:left ventricular end-diastolic area greater than 0.6, right ventricular systolic impairment as fractional area change less than 35%, or tricuspid annular plane systolic excursion less than 17 mm. One hundred seventy-two patients were included, 59 years old (interquartile range, 49-67), with mostly moderate acute respiratory distress syndrome (n = 101; 59%). Ninety-day mortality was 41% (n = 70): 49% in patients with right ventricular dilation, 53% in right ventricular systolic impairment, and 72% in right ventricular dilation with systolic impairment. The right ventricular dilation with systolic impairment phenotype was independently associated with mortality (odds ratio, 3.11 [95% CI, 1.15-7.60]), but either disease state alone was not. Right ventricular fractional area change correlated with Pao2:Fio2 ratio, Paco2, chest radiograph opacification, and dynamic compliance, whereas right ventricular:left ventricle end-diastolic area correlated negatively with urine output.

CONCLUSIONS

Right ventricular systolic impairment correlated with pulmonary pathophysiology, whereas right ventricular dilation correlated with renal dysfunction. Right ventricular dilation with systolic impairment was the only right ventricular phenotype that was independently associated with mortality.

Effects of ageing and hormonal manipulations on the level of oestrogen receptors in the guinea-pig prostate

Cytosolic oestrogen receptor levels in guinea-pig prostate tissue were found to decrease with increasing age, irrespective of whether the binding was expressed relative to cytosolic protein or cellular DNA. This decrease in oestrogen receptor levels was also observed using enriched fibromuscular stromal tissue prepared by mechanical fractionation of the prostate. The most pronounced change in cytosolic oestrogen receptor levels (from 133 to 35 fmol/mg protein) occurred at the onset of puberty. The pubertal decrease in receptor levels could not be attributed to an increase in the level of proteolytic activity in prostatic cytosol fractions derived from mature animals, a change in the affinity of the receptor for oestradiol or an increase in oestrogen receptor levels in salt-extracted nuclear fractions. Administration of tamoxifen (1 mg/day) to intact guinea-pigs throughout the transpubertal growth phase did not influence the age-related decrease in cytosolic and nuclear oestrogen receptor levels. In contrast, the decrease in oestrogen receptor levels was prevented by castration. Administration of dihydrotestosterone (DHT; 1 mg/day) to intact prepubertal animals for 4 days before study resulted in diminished cytosolic oestrogen receptor levels; this effect of DHT was blocked by the non-steroidal antiandrogen flutamide (2 mg/day). Furthermore, elimination of testicular hormones by castration during the late-pubertal growth phase resulted in a greater than twofold increase in prostatic oestrogen receptor levels. Collectively, these observations suggest an age-related decrease in oestrogen receptor levels in the guinea-pig prostate which, in part, may be due to increased testicular function at puberty.