| CPC A61B 5/4815 (2013.01) [A61B 5/0022 (2013.01); A61B 5/0205 (2013.01); A61B 5/7267 (2013.01); A61B 5/742 (2013.01); G16H 40/67 (2018.01); G16H 50/20 (2018.01); H04L 9/3242 (2013.01); A61B 2560/0475 (2013.01)] | 20 Claims |
|
1. A computer-implemented system for diagnosing sleep disorders comprising:
a hardware processor;
a polysomnography recording device is configured to interface with a patient to record a sleep data wherein the sleep data comprises at least one of an eye motion, a muscle activity, respiratory patterns, blood oxygen saturation, heart rhythms, and blood flow;
a memory coupled to the hardware processor and the polysomnography recording device, wherein the memory comprises a set of instructions in the form of a processing subsystem, configured to be executed by the hardware processor, wherein the processing subsystem is hosted on a server, and configured to execute on a network to control bidirectional communications among a plurality of modules wherein the plurality of modules comprises:
a sleep score analysis module configured as a series of analytical blocks for automatically processing a data format to produce a standardized format of a sleep score, wherein the sleep score analysis module uses a license and a plurality of montage specifications;
an evaluation module operatively connected to the sleep score analysis module and configured to review and edit the sleep score for quality control by a physician;
a scanning module operatively connected to the sleep score analysis module and configured to scan the record of the sleep score within a repository on a workstation to extract names of a plurality of channels and display the extracted channels to the physician,
wherein the plurality of channels comprises a plurality of signals generated from physical part of a patient, wherein, the scanning module enables the physician to align the plurality of channels with corresponding channel names present in recordings, and
wherein, the scanning module enables the physician to input a criteria for an automated scoring process detect a sleep disorder, wherein the criteria comprises a format for saving a sleep score, a predetermined demographic details, and a plurality of guidelines required for sleep scoring;
a montage specification module operatively coupled to the scanning module and the sleep score analysis module, wherein the montage specification module is configured to store the plurality of montage specifications as a predefined notation dictionary;
a tokenization module operatively connected with the montage specification module, wherein the tokenization module is configured to:
grant a pre-determined a plurality of distributed credits in at least one of the analytical blocks, to a user, wherein each block of credit comprises an expiration date;
provide a plurality of scoring methods for providing an analysis service, each service is designed for a specific scoring aspect and a predefined types of recordings;
associate the analysis service with a cost multiplier, wherein the analysis service is disabled by assigning a negative cost multiplier;
register the tokenization as a tokenization license comprising a credit block, the expiration date, a license type, and the cost multiplier table, wherein the tokenization license is stored in a cryptographic storage device connected directly to the workstation or on a cloud authentication server, allow a key-based authentication for offline setting and enforce the tokenization in an offline setting, the tokenization licenses and a credit accounting and are carried out in a hardware security module with a real-time clock and a unique identifier;
sign the license and a communication between the sleep scoring analysis via an asymmetric key cryptography on the workstation and the cloud authentication server;
update the license using over-the-air mechanism, wherein the updating is irrespective of the workstation connection with Internet;
a container format module operatively connected with the tokenization module and configured for handling physiological sleep data, wherein a container format comprises a signature, a header, and a payload, wherein, the signature comprises a predetermined bytes to inform an operating system about the container format and a byte indicating payload compression, and
wherein, the header is of fixed length and carries a string representing a dictionary that includes version, revision, record duration, start date and time for the recording, unique identifier, and a plurality of field listing keys, wherein, the plurality of field listing keys is defined in header is present in payload; and
an authentication module operatively connected with montage specification module, wherein the authentication module is configured to:
protect a plurality of machine learning models by using a symmetric encryption method;
compile a code into machine code to protect a source code;
and serialize the plurality of machine learning models, encrypt the plurality of machine learning models using a key and deploy into an analytics application, wherein the analytics application requests an encryption key to decrypt and deserialize the machine learning models for performing analysis.
|