Digital therapeutic platform

1 . A method for determining whether an update to one or more machine learning models is needed, the method comprising:

receiving, using at least one processor, a plurality of data, wherein the plurality of data comprises first input data;

initiating, using the at least one processor, a probabilistic network comprising a plurality of conditional probabilities;

assigning, using the at least one processor and the probabilistic network, metric-based information to the plurality of data and thereby generate weighted first probability data and weighted second probability data, the weighted first probability data and the weighted second probability data indicating one or more optical quantities associated with one or more treatment recommendations;

processing, using the at least one processor and the weighted first probability data and the weighted second probability data, the plurality of data based on the probabilistic network, wherein processing the plurality of data comprises combining the weighted first probability data and the weighted second probability data to generate processed data associated with the plurality of data;

generating, using the at least one processor and the processed data associated with the plurality of data, one or more machine learning models for producing a knowledge base for pattern recognition in at least one of the plurality of data or the processed data associated with the plurality of data, wherein the one or more machine learning models is created by a model builder, the one or more machine learning models comprising:

a feature learning component, wherein the feature learning component allows for pattern recognition;

one or more training data sets, wherein the one or more training data sets comprise a plurality of training data for training the knowledge base for pattern recognition;

the model builder, wherein the model builder comprises a file or a group of files for pattern recognition related to defined parameters using the one or more training data sets; and

an evaluator, wherein the evaluator determines if an update to the one or more machine learning models created by the model builder is needed by continuously monitoring if data outputs associated with the one or more machine learning models are outside a data range;

generating, using the at least one processor and the knowledge base, one or more first classifications for recommending the one or more treatment recommendations;

generating, using the at least one processor and the one or more first classifications, the one or more treatment recommendations, wherein the at least one processor and the one or more first classifications generate the one or more treatment recommendations at least in part by using the file or the group of files comprised in the model builder, the one or more training data sets, and the knowledge base;

receiving, using the at least one processor, second input data, wherein the second input data is captured by a first computing device, wherein the first computing device is communicatively coupled to a remote server, and wherein the second input data comprises remote monitored data, the remote monitored data is associated with a stability or instability of a disease state of a patient and comprises data indicating: computer-generated self-testing of visual fields, visual acuity, including optic nerve photography, self-testing for intraocular pressure, app usage, educational content usage, medication and testing protocol adherence, responses to provocations, or an indicator of mental health of the patient; and

updating, using the at least one processor and the evaluator, the knowledge base, wherein the knowledge base is updated according to a determination by the evaluator that the update to the one or more machine learning models created by the model builder based on the second input data is needed.

2 . The method of claim 1 , wherein at least one of the one or more training data sets comprises one or more second classifications associated with the plurality of training data.

3 . The method of claim 1 , wherein the knowledge base is updated based on the second input data.

4 . The method of claim 2 , wherein at least one of the one or more training data sets comprises the second input data.

5 . The method of claim 1 , wherein at least one of the one or more training data sets comprises the first input data.

6 . The method of claim 1 , further comprising:

aggregating, using the at least one processor, at least one of the plurality of data or the processed data;

generating, using the at least one processor, at least one data pattern associated with the plurality of data or the processed data; and

training, using the at least one processor, the knowledge base to recognize the at least one data pattern associated with the plurality of data or the processed data.

7 . The method of claim 1 , further comprising classifying, using the at least one processor, at least one of the first input data or the second input data.

8 . The method of claim 7 , wherein the at least one processor classifies the at least one of the first input data or the second input data using one or more of a random decision forest, a linear classifier, support vector machine, recurrent neural network, feedforward neural network, radial basis function network, self-organizing map, learning vector quantization, Hopfield network, Boltzmann machine, echo state network, long short term memory, bi-directional recurrent neural network, hierarchical recurrent neural network, stochastic neural network, modular neural network, associative neural network, deep neural network, deep belief network, convolutional neural network, convolutional deep belief network, large memory storage and retrieval neural network, deep Boltzmann machine, deep stacking network, tensor deep stacking network, spike and slab restricted Boltzmann machine, compound hierarchical-deep model, deep coding network, multilayer kernel machine, or deep Q-network.

9 . The method of claim 1 , wherein at least the intraocular pressure comprised in the remote monitored data comprises feature determinants that are unsupervised.

10 . The method of claim 1 , wherein the generating of the one or more first classifications for recommending the one or more treatment recommendations happens subsequent to the combining of the weighted first probability data and the weighted second probability data to generate the processed data.

11 . A method for determining whether an update to one or more machine learning models is needed, the method comprising:

receiving, using at least one processor, first data, wherein the first data is based on first input data;

initiating, using the at least one processor, a connection to a remote monitoring service;

receiving, from the remote monitoring service, second data;

initiating, using the at least one processor, a probabilistic network comprising a plurality of conditional probabilities;

assigning, using the at least one processor and the probabilistic network, metric-based information to the first data and the second data and thereby generate weighted first probability data and weighted second probability data, the weighted first probability data and the weighted second probability data indicating one or more optical quantities associated with one or more treatment recommendations;

processing, using the at least one processor and the weighted first probability data and the weighted second probability data, the first data and the second data based on the probabilistic network, wherein processing the first data and the second data comprises combining the weighted first probability data and the weighted second probability data to generate processed data;

generating, using the at least one processor and the processed data, one or more machine learning models for producing a knowledge base for pattern recognition in at least one of the first data or the second data or the processed data, wherein the one or more machine learning models is created by a model builder, the one or more machine learning models comprising:

a feature learning component, wherein the feature learning component allows for pattern recognition;

one or more training data sets, wherein the one or more training data sets comprise a plurality of training data for training the knowledge base for pattern recognition;

the model builder, wherein the model builder comprises a file or a group of files for pattern recognition related to defined parameters using the one or more training data sets; and

an evaluator, wherein the evaluator determines if an update to the one or more machine learning models created by the model builder is needed by continuously monitoring if data outputs associated with the one or more machine learning models are outside a data range;

generating, using the at least one processor and the knowledge base, one or more classifications for recommending the one or more treatment recommendations;

generating, using the at least one processor and the one or more classifications, the one or more treatment recommendations, wherein the at least one processor and the one or more classifications generate the one or more treatment recommendations at least in part by using the file or the group of files comprised in the model builder, the one or more training data sets, and the knowledge base;

receiving, using the at least one processor, third data, wherein the third data is captured by a first computing device, wherein the first computing device is communicatively coupled to a first remote server, and wherein the third data comprises remote monitored data, the remote monitored data is associated with a stability or instability of a disease state of a patient and comprises data indicating: computer-generated self-testing of visual fields, visual acuity, including optic nerve photography, self-testing for intraocular pressure, app usage, educational content usage, medication and testing protocol adherence, responses to provocations, or an indicator of mental health of the patient; and

updating, using the at least one processor and the evaluator, the knowledge base, wherein the knowledge base is updated according to a determination by the evaluator that the update to the one or more machine learning models created by the model builder based on the third data is needed.

12 . The method of claim 11 , wherein the first data comprises first historic patient data.

13 . The method of claim 11 , wherein the second data further comprises patient data.

14 . The method of claim 11 , wherein the third data further comprises remote monitored diagnostic data.

15 . The method of claim 14 , wherein the third data further comprises at least one result of at least one determination made by the first computing device or the first remote server.

16 . The method of claim 11 , wherein the remote monitoring service comprises a second remote server.

17 . The method of claim 16 , wherein the remote monitoring service further comprises the first computing device, wherein the first computing device is communicatively coupled to the second remote server.

18 . The method of claim 17 , wherein the remote monitoring service further comprises a second computing device, wherein the second computing device is communicatively coupled to at least one of the first computing device or the first remote server.

19 . The method of claim 11 , further comprising:

aggregating, using the at least one processor, at least one of the first data and the second data or the processed data;

generating, using the at least one processor, at least one data pattern associated with at least one of an aggregated first and second data or an aggregated processed data; and

training, using the at least one processor, the knowledge base to recognize the at least one data pattern associated with at least one of the aggregated first and second data or the aggregated processed data, wherein the at least one data pattern associated with the at least one of the aggregated first and second data or the aggregated processed data is used to generate the one or more classifications.

20 . The method of claim 11 , wherein generating the one or more treatment recommendations comprises analyzing at least one data pattern identified by the one or more machine learning models in the first data, the second data, and the third data.

21 . The method of claim 11 , wherein generating the one or more treatment recommendations comprises analyzing at least one data pattern identified by the one or more machine learning models in the processed data.

22 . A system for determining whether an update to one or more machine learning models is needed, the system comprising:

one or more computing device processors; and

one or more computing device memories, coupled to the one or more computing device processors, the one or more computing device memories storing instructions for execution by the one or more computing device processors, wherein the one or more computing device processors are configured to:

receive first data, wherein the first data is based on first input data;

initiate a connection to a remote monitoring service;

receive, from the remote monitoring service, second data;

initiate a probabilistic network comprising a plurality of conditional probabilities;

assign, using the probabilistic network, metric-based information to the first data and the second data and thereby generate weighted first probability data and weighted second probability data, the weighted first probability data and the weighted second probability data indicating one or more optical quantities associated with treatment recommendations;

process the first data and the second data using the weighted first probability data and the weighted second probability data based on the probabilistic network, wherein processing the first data and the second data comprises combining the weighted first probability data and the weighted second probability data to generate processed data;

generate, using the processed data, one or more machine learning models for producing a knowledge base for pattern recognition in at least one of the first data or the second data or the processed data, wherein the one or more machine learning models is created by a model builder, the one or more machine learning models comprising:

a feature learning component, wherein the feature learning component allows for pattern recognition;

one or more training data sets, wherein the one or more training data sets comprise a plurality of training data for training the knowledge base for pattern recognition;

the model builder, wherein the model builder comprises a file or group of files for pattern recognition related to defined parameters using the one or more training data sets; and

an evaluator, wherein the evaluator determines if an update to the one or more machine learning models created by the model builder is needed by continuously monitoring if data outputs associated with the one or more machine learning models are outside a data range;

generate one or more classifications for recommending one or more treatment recommendations;

generate, using the one or more classifications, the one or more treatment recommendations, wherein the one or more classifications generate the one or more treatment recommendations at least in part by using the file or the group of files comprised in the model builder, the one or more training data sets, and the knowledge base;

receive third data, wherein the third data is captured by a first computing device, wherein the first computing device is communicatively coupled to a first remote server, and wherein the third data comprises remote monitored data, the remote monitored data is associated with a stability or instability of a disease state of a patient and comprises data indicating: computer- generated self-testing of visual fields, visual acuity, including optic nerve photography, self- testing for intraocular pressure, app usage, educational content usage, medication and testing protocol adherence, responses to provocations, or an indicator of mental health of the patient; and

update the knowledge base, wherein the knowledge base is updated according to a determination by the evaluator that the update to the one or more machine learning models created by the model builder based on the third data is needed.