Trial Outcomes & Findings for Evaluation of TaiHao Breast Ultrasound Diagnosis Software (NCT NCT04551105)

NCT ID: NCT04551105

Last Updated: 2022-11-02

Results Overview

The area under the LROC curve (AUC\_LROC) on the diagnosis of benign and malignant lesions was computed and compared for Aim 1 (baseline) and Arm 2 (with BU-CAD assistance) studies.

Recruitment status

COMPLETED

Study phase

NA

Target enrollment

16 participants

Primary outcome timeframe

10 weeks

Results posted on

2022-11-02

Participant Flow

Six hundred and twenty-eight cases were randomized and split into two groups (A and B) with the same number of cases (314) in each group. Sixteen readers were randomized and split into two groups (X and Y) with the same number of readers (8) in each group.

628 cases were randomly split into study datasets A and B. Each dataset had 314 cases. For each session, sub-datasets A and B were randomized within the group. Then, a reader read each sub-dataset either unaided or aided by the BU-CAD system.

Unit of analysis: cases

Participant milestones

Participant milestones
Measure
Arm 1
Group X readers read group A cases first unaided and then group B cases aided. At least 5 weeks later, group X readers read group B cases unaided, then group A cases aided.
Arm2
Group Y readers read group B cases first unaided and then group A cases aided. At least 5 weeks later, group Y readers read group A cases unaided, then group B cases aided.
The 1st Study Sessions
STARTED
8 314
8 314
The 1st Study Sessions
COMPLETED
8 314
8 314
The 1st Study Sessions
NOT COMPLETED
0 0
0 0
The 2st Study Sessions (5 Weeks Later)
STARTED
8 314
8 314
The 2st Study Sessions (5 Weeks Later)
COMPLETED
8 314
8 314
The 2st Study Sessions (5 Weeks Later)
NOT COMPLETED
0 0
0 0

Reasons for withdrawal

Withdrawal data not reported

Baseline Characteristics

Race and Ethnicity were not collected from any participant.

Baseline characteristics by cohort

Baseline characteristics by cohort
Measure
Without BU-CAD Decision Support Assistance
n=8 Participants
Group X readers read group A cases(314) first unaided and then group B cases(314) aided. At least 5 weeks later, group X readers read group B cases(314) unaided, then group A cases(314) aided.
With BU-CAD Decision Support Assistance
n=8 Participants
Group Y readers read group B cases(314) first unaided and then group A cases(314) aided. At least 5 weeks later, group Y readers read group A cases(314) unaided, then group B(314) cases aided.
Total
n=16 Participants
Total of all reporting groups
Age, Categorical
<=18 years
0 Participants
n=8 Participants
0 Participants
n=8 Participants
0 Participants
n=16 Participants
Age, Categorical
Between 18 and 65 years
8 Participants
n=8 Participants
8 Participants
n=8 Participants
16 Participants
n=16 Participants
Age, Categorical
>=65 years
0 Participants
n=8 Participants
0 Participants
n=8 Participants
0 Participants
n=16 Participants
Sex/Gender, Customized
Female
6 Participants
n=8 Participants
5 Participants
n=8 Participants
11 Participants
n=16 Participants
Sex/Gender, Customized
Male
2 Participants
n=8 Participants
3 Participants
n=8 Participants
5 Participants
n=16 Participants
Race and Ethnicity Not Collected
0 Participants
Race and Ethnicity were not collected from any participant.
Region of Enrollment
United States
8 Participants
n=8 Participants
8 Participants
n=8 Participants
16 Participants
n=16 Participants

PRIMARY outcome

Timeframe: 10 weeks

Population: Of the study breast ultrasound cases, some contained malignant lesions and some contained breast contained benign lesions.

The area under the LROC curve (AUC\_LROC) on the diagnosis of benign and malignant lesions was computed and compared for Aim 1 (baseline) and Arm 2 (with BU-CAD assistance) studies.

Outcome measures

Outcome measures
Measure
Arm 1
n=628 case
read each breast ultrasound case without the BU-CAD decision support assistance referred to as the unaided (or baseline) study
Arm 2
n=628 case
read each breast ultrasound case with the aid of BU-CAD decision support referred to as 'aided study
Comparing the Area Under the LROC Curve
0.7786 probability
Interval 0.7463 to 0.8109
0.8160 probability
Interval 0.7862 to 0.8458

SECONDARY outcome

Timeframe: 10 weeks

Population: Of the study breast ultrasound cases, some contained malignant lesions and some contained breast contained benign lesions.

Each reader's reading time of a case was automatically recorded by the BU-CAD system. the average reading times of 16 readers with and without outlier reading times were compared between the aided and unaided sessions using the paired t-test.

Outcome measures

Outcome measures
Measure
Arm 1
n=628 case
read each breast ultrasound case without the BU-CAD decision support assistance referred to as the unaided (or baseline) study
Arm 2
n=628 case
read each breast ultrasound case with the aid of BU-CAD decision support referred to as 'aided study
The Reading Time Was Computed and Compared for Aim 1 (Baseline) and Arm 2 (With BU-CAD Assistance) Studies.
31.75 second
Interval 11.24 to 52.25
18.96 second
Interval 3.25 to 34.67

SECONDARY outcome

Timeframe: 10 weeks

Population: Of the study breast ultrasound cases, some contained malignant lesions and some contained breast contained benign lesions.

The mean sensitivity, specificity, PPV, and NPV of 16 readers were calculated and compared between the aided and unaided sessions using McNemar's test.

Outcome measures

Outcome measures
Measure
Arm 1
n=628 case
read each breast ultrasound case without the BU-CAD decision support assistance referred to as the unaided (or baseline) study
Arm 2
n=628 case
read each breast ultrasound case with the aid of BU-CAD decision support referred to as 'aided study
The Sensitivity, Specificity, PPV, and NPV Were Computed and Compared for Aim 1 (Baseline) and Arm 2 (With BU-CAD Assistance) Studies.
Sensitivity
0.9225 proportion
Interval 0.8896 to 0.9554
0.9353 proportion
Interval 0.905 to 0.9655
The Sensitivity, Specificity, PPV, and NPV Were Computed and Compared for Aim 1 (Baseline) and Arm 2 (With BU-CAD Assistance) Studies.
Specificity
0.3165 proportion
Interval 0.2694 to 0.3636
0.3611 proportion
Interval 0.3124 to 0.4098
The Sensitivity, Specificity, PPV, and NPV Were Computed and Compared for Aim 1 (Baseline) and Arm 2 (With BU-CAD Assistance) Studies.
PPV
0.4876 proportion
Interval 0.4433 to 0.5319
0.5056 proportion
Interval 0.4607 to 0.5505
The Sensitivity, Specificity, PPV, and NPV Were Computed and Compared for Aim 1 (Baseline) and Arm 2 (With BU-CAD Assistance) Studies.
NPV
0.8623 proportion
Interval 0.8048 to 0.9198
0.8945 proportion
Interval 0.8456 to 0.9434

Adverse Events

First Session: Manual Review First and Then Review With CADx

Serious events: 0 serious events
Other events: 0 other events
Deaths: 0 deaths

First Session: Review With CADx First and Then Manual Review

Serious events: 0 serious events
Other events: 0 other events
Deaths: 0 deaths

Second Session: Manual Review First and Then Review With CADx

Serious events: 0 serious events
Other events: 0 other events
Deaths: 0 deaths

Second Session: Review With CADx First and Then Manual Review

Serious events: 0 serious events
Other events: 0 other events
Deaths: 0 deaths

Serious adverse events

Adverse event data not reported

Other adverse events

Adverse event data not reported

Additional Information

Study Director of Clinical Trials

Virginia Tech

Phone: +1 (301) 820-5225

Results disclosure agreements

  • Principal investigator is a sponsor employee
  • Publication restrictions are in place