Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
This study investigates ways of improving radiologists performance of the classification of CT-scans as cancerous or non-cancerous. Participants interact with an AI to classify CT-scans under three different conditions.
The three conditions are as follows: "probabilistic classification", where the radiologist diagnoses scans using an AI cancer likelihood score; "classification plus detection", where the radiologist see detecting lung nodules in addition to the AI's probabilistic classification score before making her own examination of the CT-scan; and "classification with delayed detection", where the radiologist identifies regions of interest independently of the AI and then sees the AI's detected ROIs.
Not provided
Not provided
Not provided
Not provided
Not provided
| Label | Type | Description | Intervention Names |
|---|---|---|---|
| Probabilistic Classification | Experimental | Radiologists see a "score" from 1-100 that represents the AI's prediction of whether the CT-scan comes from a patient with cancer or not before beginning their analysis of the scan. |
|
| Classification Plus Detection | Experimental | Radiologists see a "score" from 1-100 that represents the AI's prediction of whether the CT-scan comes from a patient with cancer or not before beginning their analysis of the scan. They also see ROIs identified by the AI that represent lung nodules. |
|
| Classification With Delayed Detection | Experimental | Radiologists see a "score" from 1-100 that represents the AI's prediction of whether the CT-scan comes from a patient with cancer or not before beginning their analysis of the scan. After identifying their own ROIs, the radiologist then can see ROIs identified by the AI that represent lung nodules before making final decisions. |
|
| Name | Type | Description | Arm Group Labels | Other Names |
|---|---|---|---|---|
| AI-human interaction | Behavioral | Exploring what kinds of AI-human interaction improve radiologists detection accuracy. |
|
| Measure | Description | Time Frame |
|---|---|---|
| Classification accuracy | This compares radiologists' classifications with the ground truth in the tested cases. | up to 4 months after initiation of evaluation of the test set |
| Measure | Description | Time Frame |
|---|---|---|
| detection concordance | Evaluation of concordance between radiologists in the tested cases in detection of lung nodules > 4 mm | up to 4 months after initiation of evaluation of the test set |
Not provided
Inclusion Criteria:
Exclusion Criteria:
-
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
| Facility | Status | City | State | ZIP | Country | Contacts |
|---|---|---|---|---|---|---|
| University of Hong Kong | Hong Kong | Hong Kong |
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
| ID | Term |
|---|---|
| D008175 | Lung Neoplasms |
| ID | Term |
|---|---|
| D012142 | Respiratory Tract Neoplasms |
| D013899 | Thoracic Neoplasms |
| D009371 | Neoplasms by Site |
| D009369 | Neoplasms |
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
| D008171 |
| Lung Diseases |
| D012140 | Respiratory Tract Diseases |