INTRODUCTION: Anorectal manometry (ARM) is the gold standard for the evaluation of anorectal functional disorders, prevalent in the population. Nevertheless, the accessibility to this examination is limited, and the complexity of data analysis and report is a significant drawback. This pilot study aimed to develop and validate an artificial intelligence model to automatically differentiate motility patterns of fecal incontinence (FI) from obstructed defecation (OD) using ARM data. METHODS: We developed and tested multiple machine learning algorithms for the automatic interpretation of ARM data. Four models were tested: k-nearest neighbors, support vector machines, random forests, and gradient boosting (xGB). These models were trained using a stratified 5-fold strategy. Their performance was assessed after fine-tuning of each model's hyperparameters, using 90% of data for training and 10% of data for testing. RESULTS: A total of 827 ARM examinations were used in this study. After fine-tuning, the xGB model presented an overall accuracy (84.6% ± 2.9%), similar to that of random forests (82.7% ± 4.8%) and support vector machines (81.0% ± 8.0%) and higher that of k-nearest neighbors (74.4% ± 3.8%). The xGB models showed the highest discriminating performance between OD and FI, with an area under the curve of 0.939. DISCUSSION: The tested machine learning algorithms, particularly the xGB model, accurately differentiated between FI and OD manometric patterns. Subsequent development of these tools may optimize the access to ARM studies, which may have a significant impact on the management of patients with anorectal functional diseases.

The present work analyses displacement field computations for several digital image correlation test cases obtained through the application of image registration in the Fourier domain. The applied method relies on the properties of the discrete Fourier transform with regard to the cross-correlation function to find the rigid displacement between two subsets. The computed displacement fields were compared to their analogous values obtained through a commercial digital image correlation code. The test cases cover both two-dimensional and three-dimensional digital image correlation and make use of the ability of the developed method to calculate the translation and rotation between subsets from images at different loading states, as well as its capacity to match subsets from two cameras of a stereo rig. The presented analysis aims to contribute to the investigation of the use of correlation in the frequency domain as the basis for an alternative to conventional digital image correlation which could provide advantages in terms of robustness and efficiency, particularly in field measurements, where the lack of control over lighting and other factors impacting image quality requires a system which is optimised towards low dependence on the optimal quality of these conditions.