Chest最新文献

Background: Echocardiography is central when assessing pulmonary hypertension (PH), but manual interpretation can be time-consuming and prone to error.

Research question: Is a fully automated deep learning (DL) workflow in echocardiography reliable when assessing PH?

Study design and methods: This study had 2 parts: the first determined the bias and precision of DL reads by using Us2.ai software version 1.4.5 with core laboratory readers as the reference; the second part assessed the ability of DL to discriminate milder PH in patients referred for right heart catheterization (mean pulmonary artery pressure between 20 and 35 mm Hg). The first cohort (case-control) included 213 healthy individuals and 221 patients with pulmonary arterial hypertension. Parameters included peak tricuspid regurgitation velocity (TRV), right ventricular basal diameter, tricuspid annular plane systolic excursion, right atrial area, and right ventricular fractional area change (RVFAC). The referral cohort included 196 patients, with 171 patients having measurable peak TRV signals. Robust measures of bias and precision were reported, and area under the curve (AUC) analysis assessed discrimination.

Results: In patients with pulmonary arterial hypertension, mean age was 48 years, 78% were female, and mean pulmonary artery pressure was 52 mm Hg. No significant bias was observed for peak TRV (0.90%; 95% CI, -0.17 to 1.57), right atrial area (1.71%; 95% CI, 0.59 to 3.34), and tricuspid annular plane systolic excursion (1.28%; 95% CI, -0.51 to 3.18), while RVFAC exhibited a significant bias of 11.46% (95% CI, 8.43 to 14.74). For all measurements except RVFAC, robust percentile precision remained below 15%. In the case-control cohort, peak TRV had AUCs of 0.99 and 0.98 for core laboratory and DL reads, respectively. The AUC for PH detection in the referral cohort was 0.79 for clinical laboratory reads and 0.75 for DL reads (P = .068).

Interpretation: A fully automated DL workflow for echocardiography in PH is promising and likely to improve efficiency in clinical practice.

Background: Thoracoscopy guidelines recommend inducing artificial pneumothorax before medical thoracoscopy in patients with minimal or absent pleural effusion. Single-arm studies have demonstrated that nonartificial pneumothorax approaches reduce operative time and complication rates compared with artificial pneumothorax techniques in these patients. However, there is a lack of trials comparing the effectiveness and safety of performing artificial pneumothorax vs not performing it in these cases.

Research question: For patients with minimal or absent pleural effusion, is nonartificial pneumothorax (non-AP) noninferior to artificial pneumothorax (AP) in terms of the pleural access success rate?

Study design and methods: In this multicenter randomized noninferiority trial, patients with minimal or absent pleural effusion requiring medical thoracoscopy were randomized 1:1 to either an AP group or a non-AP group. The primary outcome was the pleural access success rate, with a noninferiority margin of -10% (non-AP group minus AP group). Secondary outcomes included pathological confirmation rates, complication rates, operation length, air leak duration, drain removal time, chest pain scores, and 90-d mortality.

Results: A total of 204 participants were equally allocated to the AP group (n = 102) and the non-AP group (n = 102). The pleural access success rate was 95.0% in the non-AP group and 78.4% in the AP group (difference, 16.6% [one-sided lower 97.5% CI, 7.6%]; P < .001 for noninferiority). Complications occurred in 14.9% of non-AP patients and 17.6% of AP patients (difference, 2.7% [95% CI, -12.9% to 7.3%]; P = 0.589).

Interpretation: For patients with minimal or absent pleural effusion, artificial pneumothorax is not necessary before performing medical thoracoscopy.

Clinical trial registration: This study has been prospectively registered in the Chinese Clinical Trial Register, No. ChiCTR2000038708.