Dataset Information

Blinded, randomized trial of sonographer versus AI cardiac function assessment.

ABSTRACT: Artificial intelligence (AI) has been developed for echocardiography^1-3, although it has not yet been tested with blinding and randomization. Here we designed a blinded, randomized non-inferiority clinical trial (ClinicalTrials.gov ID: NCT05140642; no outside funding) of AI versus sonographer initial assessment of left ventricular ejection fraction (LVEF) to evaluate the impact of AI in the interpretation workflow. The primary end point was the change in the LVEF between initial AI or sonographer assessment and final cardiologist assessment, evaluated by the proportion of studies with substantial change (more than 5% change). From 3,769 echocardiographic studies screened, 274 studies were excluded owing to poor image quality. The proportion of studies substantially changed was 16.8% in the AI group and 27.2% in the sonographer group (difference of -10.4%, 95% confidence interval: -13.2% to -7.7%, P < 0.001 for non-inferiority, P < 0.001 for superiority). The mean absolute difference between final cardiologist assessment and independent previous cardiologist assessment was 6.29% in the AI group and 7.23% in the sonographer group (difference of -0.96%, 95% confidence interval: -1.34% to -0.54%, P < 0.001 for superiority). The AI-guided workflow saved time for both sonographers and cardiologists, and cardiologists were not able to distinguish between the initial assessments by AI versus the sonographer (blinding index of 0.088). For patients undergoing echocardiographic quantification of cardiac function, initial assessment of LVEF by AI was non-inferior to assessment by sonographers.

SUBMITTER: He B

PROVIDER: S-EPMC10115627 | biostudies-literature | 2023 Apr

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Blinded, randomized trial of sonographer versus AI cardiac function assessment.

He Bryan B Kwan Alan C AC Cho Jae Hyung JH Yuan Neal N Pollick Charles C Shiota Takahiro T Ebinger Joseph J Bello Natalie A NA Wei Janet J Josan Kiranbir K Duffy Grant G Jujjavarapu Melvin M Siegel Robert R Cheng Susan S Zou James Y JY Ouyang David D

Nature 20230405 7957

Artificial intelligence (AI) has been developed for echocardiography<sup>1-3</sup>, although it has not yet been tested with blinding and randomization. Here we designed a blinded, randomized non-inferiority clinical trial (ClinicalTrials.gov ID: NCT05140642; no outside funding) of AI versus sonographer initial assessment of left ventricular ejection fraction (LVEF) to evaluate the impact of AI in the interpretation workflow. The primary end point was the change in the LVEF between initial AI or ...[more]

PMID: 37020027

Similar Datasets

Project description:ObjectiveTo determine whether robotic ventral hernia repair is associated with fewer days in the hospital 90 days after surgery compared with laparoscopic repair.DesignPragmatic, blinded randomized controlled trial.SettingMultidisciplinary hernia clinics in Houston, USA.Participants124 patients, deemed appropriate candidates for elective minimally invasive ventral hernia repair, consecutively presenting from April 2018 to February 2019.InterventionsRobotic ventral hernia repair (n=65) versus laparoscopic ventral hernia repair (n=59).Main outcome measuresThe primary outcome was number of days in hospital within 90 days after surgery. Secondary outcomes included emergency department visits, operating room time, wound complications, hernia recurrence, reoperation, abdominal wall quality of life, and costs from the healthcare system perspective. Outcomes were pre-specified before data collection began and analyzed as intention to treat.ResultsPatients from both groups were similar at baseline. Ninety day follow-up was completed in 123 (99%) patients. No evidence was seen of a difference in days in hospital between the two groups (median 0 v 0 days; relative rate 0.90, 95% confidence interval 0.37 to 2.19; P=0.82). For secondary outcomes, no differences were noted in emergency department visits, wound complications, hernia recurrence, or reoperation. However, robotic repair had longer operative duration (141 v 77 min; mean difference 62.89, 45.75 to 80.01; P≤0.001) and increased healthcare costs ($15 865 (£12 746; €14 125) v $12 955; cost ratio 1.21, 1.07 to 1.38; adjusted absolute cost difference $2767, $910 to $4626; P=0.004). Among patients with robotic ventral hernia repair, two had an enterotomy compared none with laparoscopic repair. The median one month postoperative improvement in abdominal wall quality of life was 3 with robotic ventral hernia repair compared with 15 following laparoscopic repair.ConclusionThis study found no evidence of a difference in 90 day postoperative hospital days between robotic and laparoscopic ventral hernia repair. However, robotic repair increased operative duration and healthcare costs.Trial registrationClinicaltrials.gov NCT03490266.

Project description:BackgroundDespite decades of investigation, the balance of clinical risks and benefits of fluid supplementation with starch remain unresolved. Patient-centered outcomes have not been well explored in a "real-world" trial in cardiac surgery.ObjectiveWe sought to compare a starch-based fluid strategy with a saline-based fluid strategy in the cardiac surgery patient.DesignA pragmatic blinded randomized controlled trial comparing starch-based with saline-based fluid strategy.SettingA large tertiary academic center in London Ontario between September 2009 and February 2011.ParticipantsPatients undergoing planned, isolated coronary revascularization.MeasurementsSerum creatinine and patient weight were measured daily postoperatively.MethodsPatients were randomized to receive 6% hydroxyethyl starch (Voluven) or saline for perioperative fluid requirements. Fluid administration was not protocolized. Co-primary outcomes were incidence of acute kidney injury (AKI) and maximum postoperative weight gain. Secondary outcomes included bleeding, transfusion, inotropic and ventilator support, and fluid utilization.ResultsThe study was prematurely terminated due to resource limitations. A total of 69 patients (19% female, mean age = 65) were randomized. Using RIFLE criteria for AKI, "risk" occurred in 12 patients in each group (risk ratio [RR] = 1.0; 95% confidence interval [CI] = 0.5-1.9; P = 1.00), whereas "injury" occurred in 7 of 35 (20%) and 3 of 34 (9%) of patients in the starch and saline groups, respectively (RR = 2.3; 95% CI = 0.6-8.1; P = .31). Maximum weight gain, bleeding and blood product usage, and overall fluid requirement were similar between groups.LimitationsThe study had to be prematurely terminated due to resource limitations which led to a small sample size which was not sufficiently powered to detect a difference in the primary outcomes.ConclusionsThis pragmatic double-blinded randomized controlled trial revealed a number of interesting hypothesis-generating trends and confirmed the feasibility of undertaking a logistically complex trial in a pragmatic fashion.

Project description:The purpose of this study was to compare the efficacy and safety of dexmedetomidine versus remifentanil for sedation during awake intubation using a Shikani optical stylet (SOS).Sixty-eight patients with cervical trauma or severe cervical spondylosis undergoing cervical spinal surgery were enrolled in this prospective study. They were randomly assigned to receive dexmedetomidine (Group D) or remifentanil (Group R). In Group D, the patients received an intravenous loading dose of dexmedetomidine 1 μg · kg(-1) over 10 min followed by a continuous infusion of 0.7 μg · kg(-1) · h(-1). In Group R, a target-controlled infusion of remifentanil was administered to achieve a plasma concentration of 2.5 ng · ml(-1), increased to 3 ng · ml(-1) 10 min later. An endotracheal tube was inserted using a SOS under dexmedetomidine or remifentanil sedation after topical anesthesia to the airway. Midazolam was given as rescue sedation. We recorded the first attempt intubation success rate, the dose of midazolam, duration of intubation, Ramsay Sedation Scale (RSS) score, tracheal tube tolerance score, duration of drug infusion, adverse events and patient satisfaction score.The RSS score was significantly higher in Group D than in Group R. First attempt success rate, rescue midazolam dose and the duration of intubation did not differ between the groups. Patients in Group R were significantly more tolerant of the tracheal tube. The incidence of hypoxia was significantly higher in Group R than Group D, but there was no significant difference in the incidence of other adverse events between the groups. The hemodynamic responses of the two groups were similar, but more patients in Group R were able to recall airway instrumentation.Both dexmedetomidine and remifentanil are effective sedatives for awake intubation using an SOS. Although the first attempt success rates were similar, patients sedated with remifentanil tolerated the tracheal tube better after intubation with moderately increased risk of desaturation.www.chictr.org.cn ; ChiCTR-TRC-13003052 (February 4th, 2013).

Project description:Patients with end-stage kidney disease (ESKD) have a high rate of mortality and specifically an increased risk of sudden cardiac death (SCD). Impaired cardiac autonomic tone is associated with elevated risk of SCD. Moreover, patients with ESKD are often vitamin D deficient, which we have shown may be linked to autonomic dysfunction in humans. To date, it is not known whether vitamin D supplementation normalizes cardiac autonomic function in the high-risk ESKD population. The VITamin D supplementation and cardiac Autonomic tone in Hemodialysis (VITAH) randomized trial will determine whether intensive vitamin D supplementation therapies improve cardiac autonomic tone to a greater extent than conventional vitamin D supplementation regimens in ESKD patients requiring chronic hemodialysis.A total of 60 subjects with ESKD requiring thrice weekly chronic hemodialysis will be enrolled in this 2x2 crossover, blinded, randomized controlled trial. Following a 4-week washout period from any prior vitamin D therapy, subjects are randomized 1:1 to intensive versus standard vitamin D therapy for 6 weeks, followed by a 12-week washout period, and finally the remaining treatment arm for 6 weeks. Intensive vitamin D treatment includes alfacalcidiol (activated vitamin D) 0.25 mcg orally with each dialysis session combined with ergocalciferol (nutritional vitamin D) 50 000 IU orally once per week and placebo the remaining two dialysis days for 6 weeks. The standard vitamin D treatment includes alfacalcidiol 0.25 mcg orally combined with placebo each dialysis session per week for 6 weeks. Cardiac autonomic tone is measured via 24 h Holter monitor assessments on the first dialysis day of the week every 6 weeks throughout the study period. The primary outcome is change in the low frequency: high frequency heart rate variability (HRV) ratio during the first 12 h of the Holter recording at 6 weeks versus baseline. Secondary outcomes include additional measures of HRV. The safety of intensive versus conventional vitamin D supplementation is also assessed.VITAH will determine whether an intensive vitamin D supplementation regimen will improve cardiac autonomic tone compared to conventional vitamin D supplementation and will assess the safety of these two supplementation regimens in ESKD patients receiving chronic hemodialysis.ClinicalTrials.gov, NCT01774812.

Dataset Information

Blinded, randomized trial of sonographer versus AI cardiac function assessment.

Publications

Blinded, randomized trial of sonographer versus AI cardiac function assessment.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets