Determining a relative cognitive capability of a subject
A method and system for determining an indicator for a subject that is responsive to changes in a relative cognitive capability of that subject. At least two separate machine-learning algorithms are used to generate a respective number of intermediate indicators based on one or more outputs of one or more sensors monitoring the subject. The intermediate indicators are subsequently processed to thereby generate an indicator of a relative cognitive capability of the subject.
1 . A method of generating an output indicator of a relative cognitive capability of a monitored subject carrying out an intellectual task of reading a medical image through a computing system, the method comprising:
sensing with at least one sensorobtaining at least one physiological signal of a subject, wherein the at least sensor includes at least one of a pulse oximeter, a blood pressure cuff, electroencephalogram and an electrocardiogram, the at least one physiological signal includes a numerical measure of a pulse rate, a blood pressure, a brain activity and a heart rate in response to the intellectual task, and the at least one sensor generates at least one output indicative of the at least one sensed physiological signal;
processing the at least one output using a first machine-learning algorithm, to thereby generate a first intermediate indicator of either a factor able to impair a subject's relative cognitive capability or a characteristic affected by impairments to a subject's relative cognitive capability based on the numerical measure of the at least one physiological signal, wherein the first intermediate indicator includes a first numerical measure of at least one of a distraction level, an attention level, an emotional level and a fatigue level of the subject;
processing the at least one output using a second, different machine-learning algorithm, to thereby generate a second, different intermediate indicator of either a factor able to impair a subject's relative cognitive capability or a characteristic affected by impairments to a-the subject's relative cognitive capability based on the numerical measure of the at least one physiological signal, wherein the second intermediate indicator includes a second numerical measure of the at least one of the distraction level, the attention level, the emotional level and the fatigue level of the subject; and
processing the first and second intermediate indicators to thereby generate an output indicator of the subject's relative cognitive capability;
detecting information entered into an input interface of the computing system during an event of the intellectual task may be inaccurate based on the at least one output of the at least one sensor;
preventing the computing device from saving the entered information; and
preventing the input interface of the computing device from receiving further user input.
2 . The method of claim 1 , wherein the step of processing the first and second intermediate indicators comprises processing the first and second intermediate indicators, using a third, different machine-learning algorithm, to generate an output indicator of a level of the subject's relative cognitive capability.
3 . The method of claim 1 , wherein the at least one sensor comprises at least two sensors, and the at least one output comprises at least one output from each sensor.
4 . The method of claim 1 , wherein the processing includes determining a weighted sum of the first and second intermediate indicators and passing the weighted sum through a sigmoid function.
5 . The method of claim 1 , wherein the first and second machine-learning algorithms are trained independently from one another.
6 . The method of claim 1 , wherein at least one of the first and second machine-learning algorithms includes one or more layers, each layer including a plurality of neurons, each neuron configured to perform an operation on input data to produce a numerical output, wherein an output of each of the one or more layers is an input of a subsequent layer, and a final layer provides at least one of the first and second intermediate indicators.
7 . The method of claim 1 , further comprising:
processing the output indicator to determine whether the relative cognitive capability of the subject is below a predetermined threshold; and
in response to determining that the relative cognitive capability of the subject is below the predetermined threshold, generating an alert.
8 . The method of claim 7 , wherein the step of generating an alert comprises generating a user perceptible output via a user interface.
9 . TheA method of claim 1 , further comprising:
changing a flag of the input user interface of the computing system in response to the detecting.
10 . The method of claim 1 , further comprising:
changing a state of the input user interface of the computing system in response to the detecting.
11 . The method of claim 1 , wherein the monitored subject is a clinician, and the intellectual task includes diagnosing subjects, wherein the first intermediate indicator or the second intermediate indicator is a measure in response to an intellectual task related to assessing the medical images.
12 . A non-transitory computer readable medium storing instructions that, when executed by one or more processors, cause the one or more processors to:
sense with at least one sensor at least one physiological signal of a subject, wherein the at least one sensor includes at least one of a pulse oximeter, a blood pressure cuff, electroencephalogram and an electrocardiogram, the at least one physiological signal includes a numerical measure of a pulse rate, a blood pressure, a brain activity and a heart rate in response to the intellectual task, and the at least one sensor generates at least one output indicative of the at least one sensed physiological signal;
process, with an application specific integrated circuit (ASIC), the at least one output and generate a first intermediate indicator of either a factor able to impair a subject's relative cognitive capability or a characteristic affected by impairments to a subject's relative cognitive capability based on the numerical measure of the at least one physiological signal, wherein the first intermediate indicator includes a first numerical measure of at least one of a distraction level, an attention level, an emotional level and a fatigue level of the subject;
process, with the ASIC, the at least one output using a second, different machine-learning algorithm, and generate a second, different intermediate indicator of either a factor able to impair a subject's relative cognitive capability or a characteristic affected by impairments to the subject's relative cognitive capability based on the numerical measure of the at least one physiological signal, wherein the second intermediate indicator includes a second numerical measure of the at least one of the distraction level, the attention level, the emotional level and the fatigue level of the subject; and
process, with the ASIC, the first and second intermediate indicators and generate an output indicator of the subject's relative cognitive capability based on a combination of the first and second intermediate indicators;
detect, with one or more processors, information entered into an input interface of the computing system during an event of the intellectual task may be inaccurate based on the at least one output of the at least one sensor, prevent the computing device from saving the entered information, and prevent the input interface of the computing device from receiving further user input.
13 . The non-transitory computer readable medium of claim 12 , wherein at least one of the first and second intermediate indicators indicate a change to a predetermined baseline level.
14 . The non-transitory computer readable medium of claim 12 , wherein at least one of the first and second intermediate indicators indicate a difference from a predetermined normal level.
15 . A system for determining a relative cognitive capability of a monitored subject carrying out an intellectual task of reading a medical image, the system comprising:
at least one sensor configured to sense at least one physiological signal of a subject, wherein the at least one sensor includes at least one of a pulse oximeter, a blood pressure cuff, electroencephalogram and an electrocardiogram, the at least one physiological signal includes a numerical measure of a pulse rate, a blood pressure, a brain activity and a heart rate in response to the intellectual task, and the at least one sensor generates at least one output indicative of the at least one sensed physiological signal;
a neural network including at least one machine-learning algorithm, each of the at least one machine-learning algorithms including one or more layers, each of the one or more layers including a plurality of neurons, each of the plurality of neurons configured to perform an operation on input data to produce a numerical output, wherein an output of each of the one or more layers is an input of a subsequent layer, and a final layer provides at least one of a first intermediate indicator and a second intermediate indicator,
wherein a first machine-learning algorithm is configured to process the at least one output and generate the first intermediate indicator of either a factor able to impair a subject's relative cognitive capability or a characteristic affected by impairments to a subject's relative cognitive capability based on the numerical measure of the at least one physiological signal, wherein the first intermediate indicator includes a first numerical measure of at least one of a distraction level, an attention level, an emotional level and a fatigue level of the subject;
wherein the second machine-learning algorithm is configured to process the at least one output using a second, different machine-learning algorithm, and generate the second intermediate indicator of either a factor able to impair a subject's relative cognitive capability or a characteristic affected by impairments to the subject's relative cognitive capability based on the numerical measure of the at least one physiological signal, wherein the second intermediate indicator includes a second numerical measure of the at least one of the distraction level, the attention level, the emotional level and the fatigue level of the subject, and
one or more processors configured to generate an output indicator of the subject's relative cognitive capability based on a combination of the first and second intermediate indicators.
16 . The system of claim 15 , further comprising:
an input user interface adapted to receive a user input representing an outcome of an intellectual task performed by the subject; and
at least one of the one or more processors adapted to flag the user input provided by the subject based on the output indicator.
17 . The system of claim 15 , further comprising:
an input user interface adapted to receive a user input representing an outcome of an intellectual task performed by a-the subject; and
at least one of the one or more processor configured to determine whether a relative cognitive capability of the subject is below a predetermined threshold,; and, in response to determining that the relative cognitive capability of the subject is below the predetermined threshold, prevent the subject from providing a user input.
18 . The system of claim 15 , wherein at least one of the one or more processors is further configured to change a flag on an input user interface in response to determining the subject's cognitive capability is impaired.
19 . The system of claim 15 , wherein at least one of the one or more processors is further configured to change a state of an input user interface of the computing system to prevent entry of a user input corresponding to the reading of the medical image in response to determining the subject's cognitive capability is impaired.
20 . The method of claim 15 , further comprising:
an application specific integrated circuit (ASIC) including the neural network.