In one embodiment, a cognitive load driving assistant increases driving safety based on cognitive loads. In operation, the cognitive load driving assistant computes a current cognitive load of a driver based on sensor data. If the current cognitive load exceeds a threshold cognitive load, then the cognitive load driving assistant modifies the driving environment to reduce the cognitive load required to perform the primary driving task and/secondary task(s), such as texting via a cellular phone. The cognitive load driving assistant may modify the driving environment indirectly via sensory feedback to the driver or directly through reducing the complexity of the primary driving task and/or secondary tasks. In particular, if the driver is exhibiting elevated cognitive loads typically associated with distracted driving, then the cognitive load driving assistant modifies the driving environment to allow the driver to devote appropriate mental resources to the primary driving task, thereby increasing driving safety.

Accurate measurement of pupillary distance, PD, is necessary to make prescription eye glasses as well as configuring VR headsets, and using other binocular optical devices. Today, many people are ordering eyeglasses on line and obtaining their PD is often problematic for a number of reasons as the prior art fails to provide consumer friendly PD measurement systems. A disclosed eyeglass frame system comprises reference marks of known locations upon the frames. A smart phone may be used to locate the consumer's pupils, while the consumer is wearing the frames. The consumer's pupils may be marked or tagged upon a digital image of the consumer wearing the frames. By use of angles in the sight lines of the camera lens and other variable values and the known relative distances of the frame markings, a consumer's pupillary distance can be quickly and accurately derived.

A screening platform enables comprehensive ocular evaluations. The screening platform includes a harness that is configured to fit a head of a patient and that includes one or more electronic components that are operable to power an interchangeable module, a central processing unit (CPU) with a graphical processing unit (GPU), and the interchangeable module with communication capabilities to external computational devices, multiple display output devices, and several types of input devices from both an operator and a patient at-hand, wherein the interchangeable module is separable from the screening platform.

Embodiments pertain to a method for characterizing a droopy upper eyelid performed on a computer having a processor, memory, and one or more code sets stored in the memory and executed in the processor. The method may comprise capturing an image of a patient's facial features comprising an eye and a droopy upper eyelid; identifying at least one geometric feature of a pupil of the eye within the image; and determining, based on the at least one geometric feature, whether the droopy upper eyelid is vision impairing or not, or whether the droopy upper eyelid is more likely vision impairing than not vision-impairing.

Disclosed are methods and medical device systems for automated delivery of therapies for pain and determination of need for and safety of treatment. In one embodiment, such a medical device system may comprise a sensor configured to sense at least one body signal from a patient; and a medical device configured to receive a first sensed body signal from the sensor; determine a patient pain index based at least in part on said first sensed body signal; determine whether said patient pain index is above at least a first pain index threshold; determine a safety index based at least in part on a second sensed body signal; select a pain treatment regimen based on at least one of said safety index and or a determination that said pain index is above said first pain index threshold; and deliver said pain treatment regimen.

In some embodiments, techniques for using machine learning to enable visible light pupilometry are provided. In some embodiments, a smartphone may be used to create a visible light video recording of a pupillary light reflex (PLR). A machine learning model may be used to detect a size of a pupil in the video recording over time, and the size over time may be presented to a clinician. In some embodiments, a system that includes a smartphone and a box that holds the smartphone in a predetermined relationship to a subject's face is provided. In some embodiments, a sequential convolutional neural network architecture is used. In some embodiments, a fully convolutional neural network architecture is used.

In some embodiments, techniques for using machine learning to enable visible light pupilometry are provided. In some embodiments, a smartphone may be used to create a visible light video recording of a pupillary light reflex (PLR). A machine learning model may be used to detect a size of a pupil in the video recording over time, and the size over time may be presented to a clinician. In some embodiments, a system that includes a smartphone and a box that holds the smartphone in a predetermined relationship to a subject's face is provided. In some embodiments, a sequential convolutional neural network architecture is used. In some embodiments, a fully convolutional neural network architecture is used.

Accommodating ophthalmic devices including an ambient light sensor and an accommodation sensor and related methods of use are described. In an example, the accommodation sensor is configured to measure a biological accommodation signal of an eye on or in which the accommodating ophthalmic device is mounted. In an embodiment, the accommodating ophthalmic device is configured to measure the biological accommodation signals based on ambient light, such as based on an intensity or amount of ambient light, incident on the accommodating ophthalmic device. Such ambient light may be measured with the ambient light sensor.

The invention relates to an examination device (1), a method for an automated examination of at least one eye (4, 4′) of a person, a computer program product and the various uses of the examination device (1).

Computer implemented methods and devices for determining dimensions or distances of head features are provided. The method includes identifying a plurality of features in an image of a head of a person. A real dimension of at least one target feature of the plurality of features or a real distance between at least one target feature of the plurality features and a camera device used for capturing the image is estimated based on probability distributions for real dimensions of at least one feature of the plurality of features and a pixel dimension of the at least one feature of the plurality of features.