US 12,259,864 B1
Apparatus and method for training a machine learning model
Murali Aravamudan, Andover, MA (US); and Ajit Rajasekharan, West Windsor, NJ (US)
Assigned to nference, Inc., Cambridge, MA (US)
Filed by nference, Inc., Cambridge, MA (US)
Filed on Aug. 5, 2024, as Appl. No. 18/795,107.
Int. Cl. G06F 16/22 (2019.01); G06F 16/25 (2019.01); G16H 10/60 (2018.01)
CPC G06F 16/22 (2019.01) [G06F 16/256 (2019.01); G16H 10/60 (2018.01)] 18 Claims
OG exemplary drawing
 
1. An apparatus for training a machine learning model, the apparatus comprising:
at least a processor; and a memory communicatively connected to the at least processor, wherein the memory contains instructions configuring the at least processor to:
receive, from databases via a network, a corpus of data containing entries corresponding to a plurality of subjects;
extract a plurality of entries with identifier within the corpus corresponding to a first subject of the plurality of subjects and represents medical history of the first subject;
execute a temporal attribute machine learning model to determine a plurality of temporal attributes of the plurality of entries from the plurality of entries, wherein at least a temporal attribute of the plurality of temporal attributes is a temporal attribute of an entry of the plurality of entries, wherein the temporal attribute of the plurality of temporal attributes represents time within the medical history, wherein the determining the plurality of temporal attributes comprises:
training, by executing a machine learning process, the temporal attribute machine learning model on a training dataset including the plurality of entries correlated to the plurality of temporal attributes;
generating a temporal attribute as a function of the entry using the trained temporal attribute machine learning model; and
altering the temporal attribute while preserving the temporal attribute's chronological order relative to other temporal attributes of entries having a same subject;
generate automatically, based on the determined plurality of temporal attributes, a plurality of tokens as a function of the plurality of entries, wherein the plurality of tokens comprises tokens of different modalities;
generate a chronological data structure segment comprising the plurality of entries and the plurality of tokens, as a function of the plurality of temporal attributes;
train a multimodal machine learning model on a training dataset including the chronological data structure segment to produce model output including a medical prediction as a medical state of the first subject, wherein the training the multimodal machine learning model comprises computing co-occurrences of the tokens of different modalities to compute degree similarity for the tokens; and
receive, from the trained multimodal machine learning model run on a computing device, the model output.