Item 6 — Study goal

Describe the study’s design and goals, such as model creation, exploratory study, feasibility study, or noninferiority trial. For classification systems, state the intended use, such as risk assessment, triage, diagnosis, screening, staging, monitoring, surveillance, prediction, or prognosis. Describe the type of predictive modeling to be performed, the target of predictions, and how it will solve the clinical or scientific question.

Explanation and Elaboration: The study design and goal is the bridge between the broader context of the study and its specific execution, ensuring clarity about what the research seeks to achieve and how the research will help accomplish the stated problem. For example, a classification model for triaging chest X-rays requires different design and testing considerations than a segmentation model for delineating tumors. A well-defined study design ensures transparency, guides appropriate methodological decisions, and establishes the criteria against which the research’s success will be evaluated.

Examples
A prospective real-life clinical trial was conducted to assess the diagnostic performance of the smartphone app Dermalyser® (AI Medical Technology, Stockholm, Sweden), an AI-based decision support tool (henceforth ‘the app’) to detect melanoma. The study was performed in accordance with the STARD 2015 guidelines for diagnostic accuracy studies and approved by the Swedish Medical Products Agency and the Swedish Ethical Review Authority. The trial was registered with ClinicalTrials.gov (NCT05172232). The machine learning algorithm behind the decision support had been trained in silico prior to the start of the study on an extensive number of dermoscopic images of skin lesions, showing an area under the receiver operating characteristics (ROC) curve (AUROC) of 0.94. The algorithm was fixed prior to the start of data collection (i.e. no further training or modification of its performance was done during the study). When applied on a dermoscopic image, the algorithm produces a value between 0 and 1, corresponding to a calculated probability (or risk) of the lesion being a melanoma, but in its communication with the user, the intention of the decision support is to be presented as a dichotomous outcome (‘evidence of melanoma detected’ or ‘no evidence of melanoma detected’) based on this probability. Thus, prior to data inclusion we decided on a cutoff level for the dichotomy that would entail a reasonable risk of false negatives without leading to an extensive proportion of false positives, which from the ROC curve in the aforementioned in silico pretrial corresponded to a sensitivity and specificity of 95% and 78%, respectively. [Material and Methods (16), CC-BY 4.0]
This study is a prognostic accuracy cohort study utilizing prospectively collected multicenter hospital-based stroke registries. The objective of this study is to develop, validate, and interpret a machine learning system for predicting 3-month functional outcomes after stroke. We utilized a derivation dataset for model training and internal validation, while external datasets were used for external validation. [Material and Methods (17), CC-BY 4.0]
This retrospective study utilized deep convolutional neural network models to assess endodontic case difficulty from periapical radiographs based on AAE guidelines. In our research paper, we examined five pre-trained and state-of-the-art convolutional neural network (CNN) architectures, namely ResNet50, ResNet18, Inception V2, VGG16 (with batch normalization layers), and ResNext50. Additionally, we explored four self-supervised learning (SSL) approaches, namely SimCLR, MoCo, BYOL, and DINO. All models were employed to categorize endodontic case difficulty for binary classification analysis. Additionally, the top performing model was leveraged to predict overall difficulty scores through regression. The Ethics Committee of the Hamadan University of Medical Sciences approved this study (IR.UMSHA.REC.1402.026). The study results were reported in accordance with the Checklist of Artificial intelligence in Medical imaging.…. [Material and Methods (18), CC-BY 4.0]