A stroke detection system analyzes images of a person's face over time to detect asymmetric changes in the position of certain reference points that are consistent with sagging or drooping that may be symptomatic of a stroke or TIA. On detecting possible symptoms of a stroke or TIA, the system may alert caregivers or others, and log the event in a database. Identifying stroke symptoms automatically may enable more rapid intervention, and identifying TIA symptoms may enable diagnostic and preventative care to reduce the risk of a future stroke.

A system and method for determining patient risk stratification is provided based on body composition derived from computed tomography images using segmentation with machine learning. The system may enable real-time segmentation for facilitating clinical application of body morphological analysis sets. A fully-automated deep learning system may be used for the segmentation of skeletal muscle cross sectional area (CSA). Whole-body volumetric analysis may also be performed. The fully-automated deep segmentation model may be derived from an extended implementation of a Fully Convolutional Network with weight initialization of a pre-trained model, followed by post processing to eliminate intra-muscular fat for a more accurate analysis.

Systems and methods for a urinalysis home testing kit are provided. In one implementation, a system may include a container configured to contain a urine sample, a dipstick including a plurality of test reagent pads thereon for measuring differing urinary properties, a blot pad, and a colorized surface containing a dipstick placement region and a plurality of colored reference elements greater than a number of the plurality of test reagent pads. The blot pad may be for removing excess urine from the dipstick after being dipped in urine, to thereby enable non-distorted image capture of the plurality of reagent pads by an image sensor. The colorized surface may be for enabling color normalization of the plurality of test reagent pads using the plurality of colored reference elements.

Systems and methods for tracking healing progress of multiple adjacent wounds are provided. In one embodiment, a system may include a processor configured to receive a first image of a plurality of adjacent wounds near a form of colorized surface having colored reference elements, determine colors of the plurality of wounds, correct for local illumination conditions, receive a second image of the plurality of wounds near the form of colorized surface, to determine second colors of the plurality of wounds in the second image, match each of the plurality of wounds in the second image to a wound of the plurality of wounds in the first image, and determine an indicator of the healing progress for each of the plurality of wounds based on changes between the first image and the second image.

Apparatus, systems, and methods to improve automated identification, monitoring, processing, and control of a condition impacting a patient using image data and artificial intelligence classification are disclosed. An example image processing apparatus includes an artificial intelligence classifier to: process first image data for a patient from a first time to determine a first classification result indicating a first severity of a condition for the patient; and process second image data for the patient from a second time to determine a second classification result indicating a second severity of the condition for the patient. The example image processing apparatus includes a comparator to compare the first classification result and the second classification result to determine a change and a progression of the condition associated with the change. The example image processing apparatus includes an output generator to trigger an action when the progression corresponds to a worsening of the condition.

Systems and methods for a color board for use in reagent strip testing are disclosed. One implementation may include a color board surface, a first colored reference element printed on the color board surface, and a second colored reference element printed on the color board surface. The color board may also include a test region on the color board surface configured to receive at least one reagent pad. The color board may also include a unique code, and the code may reflect specific chromatic properties associated with each of the first colored reference element and the second color reference element at a time of printing. The unique code may be machine readable to enable a machine to later normalize a comparison color, for determining chromatic properties of the at least one reagent pad.

Systems and methods automatically populate an electronic medical record of a patient with the results of image analysis. A token is generated for a specific patient in need of a medical test. The token is transmitted to a mobile communications device associated with the specific patient. Once a token-based communications session is initiated between the mobile communications device and a remote server, image-related information is transmitted to the remote server from the mobile communications device to perform an analysis of the image-related data. Upon verification that the transmitted image-related information is associated with the specific patient, an electronic medical record of the specific patient is updated to reflect a test result.

A method of updating an electronic medical record based on patient generated image data includes providing a test kit and a verification code to a patient. The patient performs a procedure associated with the test kit, then captures a medical image. The verification code is used to verify that the image was received from the patient. Upon verification, a notification is sent to a healthcare provider for updating an electronic medical record of the patient with data associated with the new image.

A method of updating the status of an insurance customer includes identifying a plurality of individuals with a first insurance status and delivering home testing kits to the plurality of individuals. Upon completion of the home testing kits, medical image information is received from a mobile communications device and processed to determine a state of a medical analysis region. Individuals with medical analysis regions in a differing state of criticality are identified. Healthcare providers may be provided with information indicating that there is a likelihood that the identified individuals are entitled to a second insurance status.

In a first aspect, the current invention concerns a computer-implemented method, system and computer program product for identifying a zone in a blood vessel system with a risk level for stasis, comprising the following steps: a) providing an angiogram of a blood vessel system, said angiogram comprising a time series of images of said blood vessel system, at least some of said images showing a contrast agent present in said blood vessel system; b) identifying at least one zone within said blood vessel system on a multitude of images of said time series; c) characterising variations in greyscale intensity in said zone across at least part of said time series of images; d) characterising an outflow of said contrast agent from said zone on the basis of said variations in intensity in said zone; and e) providing a local risk level for stasis in said zone. In further aspects, the current invention also concerns a computer-implemented method, system and computer program product for identifying a zone in a blood vessel with a risk level for stenosis and stent malpositioning, and for measuring the coronary flow reserve (CFR).