Pneumonia
Conditions
Brief summary
A retrospective, blineded, multicenter study of the InferRead CT Pneumonia.AI to evaluate the performance in identifying non-contrast chest CT scans containing pneumonia findings.
Detailed description
This is a retrospective, blinded, multicenter study for the InferRead CT Pneumonia.AI. The primary endpoint will evaluate the software's performance in identifying non-contrast chest CT scans containing pneumonia. It will evaluate InferRead CT Pneumonia.AI in terms of sensitivity and specificity with respect to a ground truth, as established by trained thoracic radiologists, in the detection of penumonia. In addition, the study will compare time to notification for the InferRead CT Pneumonia.AI software with respect to the time to notification for the standard of care as established from available radiological reports. 1. To evaluate the performance of InferRead CT Pneumonia.AI. 2. To evaluate the effect of different factors such as CT manufacturer, CT scanning protocols and patient characteristics on the performance of InferRead CT Pneumonia.AI
Interventions
DEVICEInferRead CT Pneumonia.AI
InferRead CT Pneumonia.AI reads chest CT DICOM images from medical imaging storage devices and triages cases by detecting pneumonia lesions and then flagging suspected cases in the study list. InferRead CT Pneumonia.AI is a tool to assist clinicians and it does not replace the interpretation and diagnosis by clinicians.
Sponsors
University of Maryland, College Park
Infervision
Study design
Observational model
OTHER
Time perspective
RETROSPECTIVE
Eligibility
Sex/Gender
ALL
Age
18 Years to No maximum
Healthy volunteers
Yes
Inclusion criteria
1. Non-contrast chest CT DICOM scans 2. Contains both lung lobes 3. Slice thickness is less than 3 mm.
Exclusion criteria
1. Incomplete scan or corrupted scan 2. Irregular scanning, increased intrapulmonary density due to insufficient inspiration, and respiratory artifacts affecting the physician's judgment. 3. Altered or absent lung morphology in the postoperative patient.
Design outcomes
Primary
| Measure | Time frame | Description |
|---|---|---|
| Primary Endpoint | 1/1/2022 - 2/28/2022 | 1. The Sensitivity (SE) of InferRead CT Pneumonia.AI is higher than 0.80. H0: YSE ≤ 0.80 HA: YSE \> 0.80 2. The Specificity (SP) of InferRead CT Pneumonia.AI is higher than 0.80. H0: YSP ≤ 0.80 HA: YSP \> 0.80 |
Secondary
| Measure | Time frame | Description |
|---|---|---|
| Secondary Endpoint | 1/1/2022 - 2/28/2022 | The Average Per Case Processing Time of InferRead CT Pneumonia.AI is lower than Time-to-open-exam in the standard of care H0: Per Case Processing Time ≥ Time-to-open-exam HA: Per Case Processing Time \< Time-to-open-exam The Average Per Case Processing Time of InferRead CT Pneumonia.AI includes the time to receive the DICOM exam and the shows AI results on the studylist. The standard of care time-to-open-exam is defined as the time from the initial scan of the patient to the time when the radiologist first opens the exam for review. |
Contacts
Primary ContactFrank Wu
Outcome results
None listed