Methods and systems for processing data via an executable file on a monitor to reduce the dimensionality of the data and encrypting the data being transmitted over the wireless network
Some embodiments include processing data via an executable file on a monitor to reduce the dimensionality of the data being transmitted over the wireless network. The output of the executable file also encrypts the data before being transmitted wireless to a remote server. The remote server receives the transmitted data and makes likelihood inferences based on the recorded data.
1. A monitor to infer a likelihood of a characteristic of a user, the monitor comprising:
a sensor positioned to detect continuous physiological signals of a user while the monitor is engaged to the user; and
a hardware processor configured to process the detected physiological signals through an encoder to generate data output, wherein the encoder comprises a first subset of layers of a neural network;
wherein an external computing system is configured to infer a likelihood of an occurrence of arrhythmia by processing the data output through a decoder, wherein the decoder comprises a second subset of layers of the neural network.
2. The monitor of claim 1 , wherein the monitor includes a transmitter configured to transmit the data output of the encoder to the external computing system.
3. The monitor of claim 2 , wherein the transmitter transmits the data output to the external computing system via a wireless communication channel.
4. The monitor of claim 1 , wherein the monitor is a wearable patch.
5. The monitor of claim 1 , wherein the monitor is a patch that is applied on the chest of the user.
6. The monitor of claim 1 , wherein the monitor is an implantable device.
7. The monitor of claim 1 , wherein the monitor comprises another sensor configured to detect accelerometer configured to gather motion data, wherein the external computing system is configured to match motion data with the detected signals to infer the likelihood of the occurrence.
8. The monitor of claim 1 , wherein the sensor includes one or more electrodes and the physiological signals comprise electrocardiography (ECG) data.
9. The monitor of claim 1 , wherein the sensor includes an optical sensor and the physiological signals comprise photoplethysmography (PPG) data.
10. The monitor of claim 1 , wherein the first subset of layers of the neural network and the second subset of layers of the neural network are trained together.
11. The monitor of claim 10 , wherein the monitor includes a watertight or water resistant housing.
12. The monitor of claim 10 , wherein the monitor includes a surface on a housing configured to be engaged to the user.
13. The monitor of claim 10 , wherein the sensor is permanently disposed within a housing.
14. A monitor to infer a likelihood of a characteristic of a user, the monitor comprising:
a sensor positioned to detect continuous physiological signals of a user while the monitor is engaged to the user; and
a hardware processor configured to process the detected physiological signals through a first subset of layers of a neural network to generate data output;
wherein an external computing system is configured to infer a likelihood of an occurrence of arrhythmia by processing the data output through a second subset of layers of the neural network.
15. A monitor to infer a likelihood of a characteristic of a user, the monitor comprising:
a sensor positioned to detect physiological signals of a user while the monitor is engaged to the user; and
a hardware processor configured to process the detected physiological signals through a first subset of layers of a neural network to generate data output;
wherein an external computing system is configured to infer a likelihood of an occurrence of arrhythmia by processing the data output through a second subset of layers of the neural network.
16. The monitor of claim 15 , wherein the dimensionality of the data output of the first subset of layers of the neural network is smaller than the data of the detected physiological signals from the sensor.
17. The monitor of claim 15 , wherein the data output of the first subset of layers of the neural network is encrypted, wherein the external computing system processes the encrypted data output through the second subset of layers of the neural network.
18. The monitor of claim 15 , further comprising a receiver configured to receive an updated first subset of layers of the neural network from the external computing system and updating the first subset of the layers of the neural network to the updated first subset of layers of the neural network, wherein the hardware processor is further configured to process signals through the updated first subset of layers of the neural network.
19. The monitor of claim 15 , wherein the monitor includes a cardiac monitor, and wherein the continuous physiological signals are cardiac signals.
20. The monitor of claim 15 , wherein to infer a likelihood of an occurrence of cardiac arrhythmia comprises processing the data output of the first subset through the second subset, wherein the first subset processes at least 24 hours of continuously detected, stored physiological signals.
21. The monitor of claim 15 , wherein the monitor further comprises a patient trigger configured to depress and initiate recordation of an instance in time of a perceived cardiac event.
22. The monitor of claim 15 , wherein the hardware processor is configured to select the neural network from a plurality of neural networks based on a characteristic of the monitor.
23. The monitor of claim 22 , wherein the characteristic of the monitor comprises one or more of: a remaining amount of battery, a network characteristic between the monitor and the external computing system, or a wear duration.
24. The monitor of claim 22 , wherein the characteristic includes one or more of: a characteristic of the user or a severity of cardiac arrhythmia.
25. The monitor of claim 15 , wherein the hardware processor is further configured to compress the data output of the first subset of layers of the neural network, wherein the external computing system is configured to decompress the compressed data; and wherein processing the data output through the second subset of layers comprises processing the decompressed data.
26. The monitor of claim 15 , wherein the hardware processor is further configured to quantize the data output of the first subset of layers of the neural network.
27. The monitor of claim 26 , wherein quantizing comprises rounding, truncating, or reducing a number of bits for the data output of the first subset of layers of the neural network.
28. The monitor of claim 26 , wherein the hardware processor is further configured to determine an amount of quantization based on one or more of: a characteristic of the monitor or a lossless compression performance.
29. The monitor of claim 26 , wherein the hardware processor is further configured to determine an amount of quantization based on at least one of: a processing power, a storage capacity, an amount of remaining storage capacity, or a network characteristic.
30. The monitor of claim 26 , wherein the hardware processor is further configured to determine an amount of quantization based on an accuracy of the neural network.