Abstract: Techniques disclosed herein relate to inferring a type of multiple sclerosis and determining whether to output an alert based on codes detected within noisy assessment data corresponding to a subject. The noisy assessment data includes content originating from a care provider that identifies a characteristic of the subject or of a treatment for the subject, and the subject has been diagnosed with multiple sclerosis. A temporal dynamic or distribution is determined based on instances of the code detection, and a modulation is determined based on the temporal dynamic or the distribution. It is determined whether an alert criterion is satisfied based on whether the modulation is above a threshold so as to represent noise or a predicted transition across types of multiple sclerosis. The inferred type of multiple sclerosis is output. When the alert criterion is satisfied, an alert is output as well.

Abstract: Embodiments disclosed herein generally relate to connected machine learning models with joint training for lesion detection. Particularly, aspects of the present disclosure are directed to accessing a three-dimensional magnetic resonance imaging (MRI) image, wherein the three-dimensional MRI image depicts a region of a brain of a subject, wherein the region of the brain includes at least a first type of lesions and a second type of lesions; inputting the three-dimensional MRI image into a machine-learning model comprising a first convolutional neural network and a second convolutional neural network; generating a first segmentation mask for the first type of lesions using the first convolutional neural network that takes as input the three-dimensional MRI image; generating a second segmentation mask for the second type of lesions using the second convolutional neural network that takes as input the three-dimensional MRI image; and outputting the first segmentation mask and the second segmentation mask.

Abstract: Embodiments disclosed herein generally relate to multi-arm machine learning models for lesion detection. Particularly, aspects of the present disclosure are directed to accessing a three-dimensional magnetic resonance imaging (MRI) images. Each of the three-dimensional MRI images depict a same volume of a brain of a subject. The volume of the brain includes at least part of one or more lesions. Each three-dimensional MRI image of the three-dimensional MRI images is processed using one or more corresponding encoder arms of a machine-learning model to generate an encoding of the three-dimensional MRI image. The encodings of the three-dimensional MRI images are concatenated to generate a concatenated representation. The concatenated representation is processed using a decoder arm of the machine-learning model to generate a prediction that identifies one or more portions of the volume of the brain predicted to depict at least part of a lesion.