Abstract: A system for treating a patient in a medical procedure includes a computer and a medical apparatus. The computer includes a memory that stores instructions and a processor that executes the instructions. The medical apparatus is configured to apply a medical treatment to the patient when instructed to do so by the computer. The instructions cause the system to obtain medical data of the patient indicative of a medical condition to be treated, and select an algorithm and apply the algorithm to the medical data to identify the medical treatment to remedy the medical condition. The instructions also cause the system to determine whether it is authorized to apply the medical treatment to the patient and, if so, instruct the medical apparatus to apply the medical treatment to the patient. The medical apparatus applies the medical treatment to the patient when instructed to do so.

Abstract: Techniques disclosed herein relate to monitoring changes in conditions of multiple individuals in areas. In some embodiments, a patient monitoring queue may be established (504) that includes a plurality of patients in an area (104, 304) such as a waiting room. The area may be capturable by vital sign acquisition camera(s) (276. 376, 476) mounted in or near the area. Updated vital sign(s) may be unobtrusively acquired (510) by the vital sign acquisition camera(s) from a given patient selected (506) from the patient monitoring queue. Based on the updated vital sign(s) and prior vital signs acquired previously from the given patient, deterioration of the given patient may be detected (512). Output may be provided (514) alerting medical personnel of the deterioration of the given patient.

Abstract: A method for training a model, the method including: defining a primary model for identifying a class of input data based on a first characteristic of the input data; defining a secondary model for detecting a change to a second characteristic between multiple input data captured at different times; defining a forward link from an output of an intermediate layer of the secondary model to an input of an intermediate layer of the primary model; and training the primary model and the secondary model in parallel based on a training set of input data.

Abstract: A method for providing one or more customized alarm setting recommendations for a patient includes the steps of: providing a patient monitor configured to monitor the patient, the patient monitor comprising a patient sensor and a processor configured to receive the sensor data from the patient sensor, receiving, by the patient monitor, information about a patient; analyzing, by the processor using an alarm setting recommendation classifier, the received information about the patient to generate one or more alarm setting recommendations customized to the patient; providing the one or more alarm setting recommendations to the user, and receiving input from the user accepting, rejecting, and/or modifying the alarm setting recommendations.

Abstract: The capillary refill time (CRT) of a patient is an important feature in the determination of cardiovascular system health. Quick re-perfusion of the microcirculation (namely, the capillaries) is a good indication that the cardiovascular system is able to efficiently distribute blood throughout the body. Current systems use unreliable or subjective methods to test the CRT. Additionally, the calculation of CRT is not generally used in the adult medical space as it is more commonly used in pediatrics. The present application describes a system and method for calculating a patient's CRT using a mobile device with an integrated camera and light source, or an optical head-mounted display using a light source in combination with ambient light to calculate the CRT. Once a patient's CRT is calculated, an integrated application classifies the data and sends it to the treating clinician for review.

Abstract: Methods and systems for detecting false alarms. Methods and systems described herein may receive data associated with an alarm signal using an interface, extract at least one artifact feature from the received data, and then receive a classification of the alarm signal as a true positive or false positive based on the at least one extracted artifact feature. The classifier may be configured to execute an ensemble of decision trees.

Abstract: Methods and systems for adaptive clinical decision support (CDS). The system may include a CDS score calculator configured to calculate a plurality of patient CDS scores, a detector configured to determine at least one clinician location or resource location, a scheduler configured to receive the plurality of CDS scores, receive the at least one clinician location or resource location, generate a patient priority list based on the plurality of CDS scores and the at least one clinician location or resource location, and generate, using the patient priority list, a patient schedule for at least one recipient, and a transmitter configured to transmit an alert to the at least one recipient if the generated schedule is different from a previously generated schedule.

Abstract: A method for allocating and activating healthcare resources includes receiving an automated clinical decision from an automated clinical decision-making (ACDM) engine, determining that an action based on the automated clinical decision should performed during a time-critical period, identifying a clinician available within the time-critical period, determining a rank of the clinician relative to the automated clinical decision for the patient condition, and selecting the action to be performed by the at least one clinician or based on the automated clinical decision. The selection operation is performed based on the rank within the time-critical period, and all or a portion of the aforementioned operations are automatically performed using at least one machine-implemented algorithm.

Abstract: Disclosed techniques relate to identifying subjects in digital images. In various embodiments, a first camera (276, 376, 476, 976) may acquire (1002) digital images (420) depicting a subject in an area. Portion(s) of the digital image(s) that depict a face of the subject may be detected (1004) as detected face image(s). Features of the detected face image(s) may be compared (1006) with features of subject reference templates associated with subject(s) in a subject reference database (412). The subject reference database stores subject reference templates that are associated with multiple subjects and that are generated based on data received from a second camera (256, 456). Based on the comparing, an identity of the subject may be determined (1014) and the features of the detected face image(s) may be stored (1016) in the subject reference database in association with the subject, e.g., as an auxiliary template feature vector for later use.

Abstract: In various embodiments, a first plurality of digital images captured by a first camera (256, 456, 1156) of a first area may be categorized (1202-1210) into multiple predetermined categories based on visual attribute(s) of the first plurality of digital images. A second plurality of digital images captured by a second camera (276, 376, 476, 1176) of a second area may be categorized (1302-1310) into the same predetermined categories based on visual attribute(s) of the second plurality of digital images. After the second camera acquires (1402) a subsequent digital image depicting an unknown subject in the second area, the subsequent digital image may be categorized (1404-1406) into a given one of the predetermined categories based on its visual attribute(s), and then adjusted (1408) based on a relationship between the first plurality of digital images categorized into the given category and the second plurality of digital images categorized into the given category.

Abstract: Various embodiments relate to a programmable interface configured to connect a medical device to a main platform, including: a medical device interface configured to connect to a medical device, receive waveform data from the medical device, and to send medical device commands to the medical device; a main platform interface configured to connect to a main platform, receive platform interface commands from the main platform, and transmit waveform data from the medical device to the main platform based upon the platform interface commands; a buffer memory configured to store waveform data generated by the medical device; and a waveform processing and control unit configured to process the waveform data generated by the medical device stored in the buffer memory according to the platform interface commands.

Abstract: Techniques disclosed herein relate to automatic pan-tilt-zoom adjustment to improve vital sign acquisition. In various embodiments, a vital sign acquisition camera (176) operable to pan, tilt, and zoom (“PTZ”) may capture (402) an image of a patient (100). The image may be analyzed (404) to detect a depicted position of the patient within an image coordinate space of the image. A desired position of the patient within the image coordinate space of the image may determined (406), and a difference in the image coordinate space between the depicted position and the desired position may be calculated (408). The difference may then be mapped (410) from the image coordinate space to a PTZ space. One or more PTZ parameters of the vital sign acquisition camera may be altered (412) based on the mapping. After altering the one or more PTZ parameters, the vital sign acquisition camera may acquire (414) one or more vital signs from the patient.

Abstract: The invention discloses a computer-implemented method for monitoring an intubated patient (104), the method comprising receiving, from one or more sensors (110, 112) associated with the intubated patient, data relating to the intubated patient; determining a likelihood of self-extubation by the intubated patient based on the received data; and responsive to determining that the likelihood of self-extubation is greater than a defined threshold, generating an alert signal.

Abstract: A system configured to monitor a patient undergoing an oxygen therapy includes a housing configured to be connected to a patient interface that delivers the oxygen therapy to the patient; a plurality of sensors disposed in or on the housing and configured to generate output signals conveying information about one or more patient/system interaction attributes associated with the oxygen therapy; and a computer system that comprises one or more physical processors operatively connected with the plurality of sensors, the physical processors being programmed with computer program instructions which, when executed cause the computer system to: determine the one or more patient/system interaction attributes associated with the oxygen therapy based on the information in the output signals; and generate output information for communication to the patient and/or a caregiver based on the output signals.

Abstract: Disclosed techniques relate to identifying subjects in digital images. In some embodiments, intake digital images (404) are acquired (1002) that capture a first subject. A subset of the intake digital images is selected (1004) that depict multiple different views of the first subject's face. Based on the selected subset of intake digital images, first subject reference templates are generated and stored in a subject database (412). Later, a second subject is selected (1008) for identification within an area. Associated second subject reference templates are retrieved (1010) from the subject reference database. Digital image(s) (420) that depict the area are acquired (1012). Portion(s) of the digital image(s) that depict faces of subject(s) in the area are detected (1014) as detected face image(s). A given detected face image is compared (1016) to the second subject reference templates to identify the second subject (1018) in the digital image(s) that capture the area.

Abstract: A system and method for providing information supportive of clinical decision making. The method includes receiving a primary set of input data and producing a first output having a first performance value based upon the primary set of input data. The method then produces a second output having a second performance value based upon the primary set of input data and a supplemental set of input data, when the supplemental set of input data is available. The second performance value of the second output exceeds the first performance value of the first output.

Abstract: A method for training a model, the method including: defining a primary model for identifying a class of input data based on a first characteristic of the input data; defining a secondary model for detecting a change to a second characteristic between multiple input data captured at different times; defining a forward link from an output of an intermediate layer of the secondary model to an input of an intermediate layer of the primary model; and training the primary model and the secondary model in parallel based on a training set of input data.

Abstract: In various embodiments, a first plurality of digital images captured by a first camera (256, 456, 1156) of a first area may be categorized (1202-1210) into multiple predetermined categories based on visual attribute(s) of the first plurality of digital images. A second plurality of digital images captured by a second camera (276, 376, 476, 1176) of a second area may be categorized (1302-1310) into the same predetermined categories based on visual attribute(s) of the second plurality of digital images. After the second camera acquires (1402) a subsequent digital image depicting an unknown subject in the second area, the subsequent digital image may be categorized (1404-1406) into a given one of the predetermined categories based on its visual attribute(s), and then adjusted (1408) based on a relationship between the first plurality of digital images categorized into the given category and the second plurality of digital images categorized into the given category.

Abstract: Disclosed techniques relate to identifying subjects in digital images. In various embodiments, a first camera (276, 376, 476, 976) may acquire (1002) digital images (420) depicting a subject in an area. Portion(s) of the digital image(s) that depict a face of the subject may be detected (1004) as detected face image(s). Features of the detected face image(s) may be compared (1006) with features of subject reference templates associated with subject(s) in a subject reference database (412). The subject reference database stores subject reference templates that are associated with multiple subjects and that are generated based on data received from a second camera (256, 456). Based on the comparing, an identity of the subject may be determined (1014) and the features of the detected face image(s) may be stored (1016) in the subject reference database in association with the subject, e.g., as an auxiliary template feature vector for later use.

Abstract: Disclosed techniques relate to identifying subjects in digital images. In some embodiments, intake digital images (404) are acquired (1002) that capture a first subject. A subset of the intake digital images is selected (1004) that depict multiple different views of the first subject's face. Based on the selected subset of intake digital images, first subject reference templates are generated and stored in a subject database (412). Later, a second subject is selected (1008) for identification within an area. Associated second subject reference templates are retrieved (1010) from the subject reference database. Digital image(s) (420) that depict the area are acquired (1012). Portion(s) of the digital image(s) that depict faces of subject(s) in the area are detected (1014) as detected face image(s). A given detected face image is compared (1016) to the second subject reference templates to identify the second subject (1018) in the digital image(s) that capture the area.