Abstract: Various embodiments of the present invention provide methods, apparatus, systems, computing devices, computing entities, and/or the like for generating a historically dynamic explanation data object for a dental image data object. Certain embodiments of the present invention utilize systems, methods, and computer program products that perform generating a historically dynamic explanation data object for a dental image data object using an encoder-decoder architecture, where the encoder machine learning framework of the encoder-decoder architecture comprises a current diagnosis identification machine learning model, a historical diagnosis identification machine learning model, a convolutional embedding machine learning model, a new diagnosis code inference machine learning model, and a feature vector combination machine learning model.

Abstract: Various embodiments provide methods, apparatus, systems, computing entities, and/or the like, identifying object transformations in images and determining a sufficiency measure for an image set in capturing object transformations for one or more objects. In an embodiment, an example method comprises receiving a transformation record data entity and an image set comprising a plurality of images, the transformation record data entity comprising one or more object identifiers. The method further comprises identifying each object depicted by each image using an object identification machine learning and determining a sufficiency measure for the image set based at least in part on determining a transformation state for each object associated with one of the one or more object identifiers using one or more transformation classification machine learning models.

Abstract: Embodiments utilize interpolation to smooth animation frames by generating synthetic Shapley values utilized to generate the animation. Additionally, some embodiments provide for generation of an embedding space for improved understandability of the model training based on corresponding Shapley values. The embedding space is mapped to using activations derived from a specially configured LSTM for each model, where an embedded representation of the LSTM activations is generated by a specially configured autoencoder such that the embedded representation may be mapped to the embedding space. The embedding space and animations are renderable to an interface for user investigation and may be further customizable to narrow investigation on particular data thereof.

Abstract: Various embodiments provide methods, apparatus, systems, computing entities, and/or the like, identifying object transformations in images and determining a sufficiency measure for an image set in capturing object transformations for one or more objects. In an embodiment, an example method comprises receiving a transformation record data entity and an image set comprising a plurality of images, the transformation record data entity comprising one or more object identifiers. The method further comprises identifying each object depicted by each image using an object identification machine learning and determining a sufficiency measure for the image set based at least in part on determining a transformation state for each object associated with one of the one or more object identifiers using one or more transformation classification machine learning models.

Abstract: Various embodiments of the present invention provide methods, apparatus, systems, computing devices, computing entities, and/or the like for generating a historically dynamic explanation data object for a dental image data object. Certain embodiments of the present invention utilize systems, methods, and computer program products that perform generating a historically dynamic explanation data object for a dental image data object using an encoder-decoder architecture, where the encoder machine learning framework of the encoder-decoder architecture comprises a current diagnosis identification machine learning model, a historical diagnosis identification machine learning model, a convolutional embedding machine learning model, a new diagnosis code inference machine learning model, and a feature vector combination machine learning model.