Study design:

• Direction of data collection: retrospective
• Number of gates (sets of eligibility criteria): double gate (AI, human)
• Participant sampling method: Consecutive
• Method of allocating participants to index tests: Each participant received all index tests
• Number of reference standards: Single test standard
• Limited verification: Full verification (not limited)

Dental X-rays taken in patients with indications confirmed by a written referral.

Sensitivity (also known as recall or true positive rate) is the proportion of actual positive cases that are correctly predicted as positive. It evaluates the performance of an AI algorithm. Formally it can be calculated with the following equation:

Sensitivity = TP / (TP+FN)

True positive (TP) - a test result that correctly indicates the presence of a condition or characteristic

False Negative (FN) - a test result which wrongly indicates that a particular condition or characteristic is absent

Specificity (also known as true negative rate) - is the proportion of actual negative cases that are correctly predicted as negative. It evaluates the performance of an AI algorithm. Formally it can be calculated by the equation below:

Specificity = TN / (TN + FP)

True negative (TN) - a test result that correctly indicates the absence of a condition or characteristic

False positive (FP) - a test result which wrongly indicates that a particular condition or characteristic is present

Precision is an evaluation metric used to assess the performance of machine learning algorithm for AI. It measures how accurate the algorithm is. We will use the number of true positives (TP) and false positives (FP) to calculate precision using the following formula:

Precision = TP / (TP + FP)

True positive (TP) - a test result that correctly indicates the presence of a condition or characteristic

False positive (FP) - a test result that wrongly indicates that a particular condition or characteristic is present