Data security in an electronic data capture system

A data processing system for detecting personally identifiable information (PII) in clinical trial data before the clinical trial data is committed to a hardware storage device to improve data security, comprising:

• one or more processing devices;
• and
• one or more machine-readable hardware storage devices storing instructions that are executable by the one or more processing devices to perform operations comprising:
• causing rendering of a graphical user interface with one or more input portions for input of clinical trial data and one or more controls;
• responsive to selection of at least one of the one or more controls, receiving, through the graphical user interface, clinical trial data input into at least one of the one or more input portions of the graphical user interface;
• prior to committing the clinical trial data to a hardware storage device, associating, in memory, the clinical trial data input into at least one of the one or more input portions of the graphical user interface with a pending state;
• training a machine learning model to detect personally identifiable information (PII) using a learning technique based on training data received as input, wherein the machine learning model is configured to receive as input clinical trial data and to process the input clinical trial data to generate an output that specifies whether the clinical trial data includes PII, wherein the machine learning model comprises a plurality of artificial neurons that are connected through edges and are aggregated into a plurality of layers comprising at least an input layer and an output layer, wherein each of the edges is configured to transmit a signal from one artificial neuron to another artificial neuron, and wherein an output of each of the plurality of artificial neurons is computed by a specified function of a sum of inputs of the artificial neuron in accordance with a plurality of weights;
• adjusting values of the plurality of weights based on the training of the machine learning model;
• processing clinical trial data using the plurality of artificial neurons in the trained machine learning model in accordance with the values of the plurality of weights to detect, by the trained machine learning model, whether the clinical trial data includes PII;
• at least partly based on an output of the machine learning model, determining whether the clinical trial data includes PII;
• upon determining that the clinical trial data does not include PII, accessing, from memory, the clinical trial data input into at least one of the one or more input portions of the graphical user interface and associated with the pending state;
• releasing the clinical trial data from the pending state;
• and
• committing the clinical trial data released to the hardware storage device.

A non-transitory computer readable medium for detecting personally identifiable information (PII) in clinical trial data before the clinical trial data is committed to a hardware storage device to improve data security, the non-transitory computer readable medium storing instructions that are executable by one or more processing devices to perform operations comprising:

• causing rendering of a graphical user interface with one or more input portions for input of clinical trial data and one or more controls;
• responsive to selection of at least one of the one or more controls, receiving, through the graphical user interface, clinical trial data input into at least one of the one or more input portions of the graphical user interface;
• prior to committing the clinical trial data to a hardware storage device, associating, in memory, the clinical trial data input into at least one of the one or more input portions of the graphical user interface with a pending state;
• training a machine learning model to detect personally identifiable information (PII) using a learning technique based on training data received as input, wherein the machine learning model is configured to receive as input clinical trial data and to process the input clinical trial data to generate an output that specifies whether the clinical trial data includes PII, wherein the machine learning model comprises a plurality of artificial neurons that are connected through edges and are aggregated into a plurality of layers comprising at least an input layer and an output layer, wherein each of the edges is configured to transmit a signal from one artificial neuron to another artificial neuron, and wherein an output of each of the plurality of artificial neurons is computed by a specified function of a sum of inputs of the artificial neuron in accordance with a plurality of weights;
• adjusting values of the plurality of weights based on the training of the machine learning model;
• processing, by the computer system, clinical trial data using the plurality of artificial neurons in the trained machine learning model in accordance with the values of the plurality of weights to detect, by the trained machine learning model, whether the clinical trial data includes PII;
• at least partly based on an output of the machine learning model, determining whether the clinical trial data includes PII;
• upon determining that the clinical trial data does not include PII, accessing, from memory, the clinical trial data input into at least one of the one or more input portions of the graphical user interface and associated with the pending state;
• releasing the clinical trial data from the pending state;
• and
• committing the clinical trial data released to the hardware storage device.