With recent developments in medical and psychiatric research surrounding pupillary response, cheap and accessible pupillometers could enable medical benefits from early neurological disease detection to measurements of cognitive load. In this paper, we introduce a novel smartphone-based pupillometer to allow for future development in clinical research surrounding at-home pupil measurements. Our solution utilizes a NIR front-facing camera for facial recognition paired with the RGB selfie camera to perform tracking of absolute pupil dilation with sub-millimeter accuracy. In comparison to a gold standard pupillometer during a pupillary light reflex test, the smartphone-based system achieves a median MAE of 0.27mm for absolute pupil dilation tracking and a median error of 3.52% for pupil dilation change tracking. Additionally, we remotely deployed the system to older adults as part of a usability study that demonstrates promise for future smartphone deployments to remotely collect data in older, inexperienced adult users operating the system themselves.

There is a vision for smartphone-based medical tricorders, in which a software application can be downloaded to smartphones around the world in people's pockets to use for medical sensing at the point of care. The power of this vision lies in quick software updates that could allow any phone to count coughs, track anemia, detect sleep apnea, and much more. It has the potential to enable remote healthcare effectively and equalize the reach of care. However, there is a need for further discussion around the implicit difficulties to developing and deploying medical sensing applications. The reality is that every smartphone is different, and that an application developed for one phone has no guarantee of working for the next phone or even the next OS update. In this paper, our goal is to draw out motifs around the challenges that are inherent to realizing this vision of smartphone-based medical sensing solutions. We further expound on this by juxtaposing the challenges with potential futures that we organize as tenets for how we could achieve more sustainable and universal development towards smartphone-based medical tricorders. CCS CONCEPTS• Human-centered computing → Smartphones; Ubiquitous and mobile computing; Ubiquitous and mobile devices; Mobile phones; Mobile devices.

We propose an ultra-low-cost at-home blood pressure monitor that leverages a plastic clip with a spring-loaded mechanism to enable a smartphone with a flash LED and camera to measure blood pressure. Our system, called BPClip, is based on the scientific premise of measuring oscillometry at the fingertip to measure blood pressure. To enable a smartphone to measure the pressure applied to the digital artery, a moveable pinhole projection moves closer to the camera as the user presses down on the clip with increased force. As a user presses on the device with increased force, the spring-loaded mechanism compresses. The size of the pinhole thus encodes the pressure applied to the finger. In conjunction, the brightness fluctuation of the pinhole projection correlates to the arterial pulse amplitude. By capturing the size and brightness of the pinhole projection with the built-in camera, the smartphone can measure a user’s blood pressure with only a low-cost, plastic clip and an app. Unlike prior approaches, this system does not require a blood pressure cuff measurement for a user-specific calibration compared to pulse transit time and pulse wave analysis based blood pressure monitoring solutions. Our solution also does not require specialized smartphone models with custom sensors. Our early feasibility finding demonstrates that in a validation study with N = 29 participants with systolic blood pressures ranging from 88 to 157 mmHg, the BPClip system can achieve a mean absolute error of 8.72 and 5.49 for systolic and diastolic blood pressure, respectively. In an estimated cost projection study, we demonstrate that in small-batch manufacturing of 1000 units, the material cost is an estimated $0.80, suggesting that at full-scale production, our proposed BPClip concept can be produced at very low cost compared to existing cuff-based monitors for at-home blood pressure management.

Pupillometry is a measurement of pupil dilation commonly performed as part of neurological assessments. Prior work have demonstrated the potential for pupillometry in screening or diagnosing a number of neurological disorders including Alzheimer's Disease, Schizophrenia, and Traumatic Brain Injury. Unfortunately, the expense and inaccessibility of specialized pupilometers that image in the near infrared spectrum limit the measurement to high resource clinics or institutions. Ideally, this measurement could be available via ubiquitous devices like smartphones or tablets with integrated visible spectrum imaging systems. In the visible spectrum of RGB cameras, the melanin in the iris absorbs light such that it is difficult to distinguish the pupil aperature that appears black. In this paper, we propose a novel pupillometry technique to enable smartphone RGB cameras to effectively differentiate the pupil from the iris. The proposed system utilizes a 630nm long-pass filter to image in the red to far red spectrum, where the melanin in the iris reflects light to appear brighter in constrast to the dark pupil. Using a convolutional neural network, the proposed system measures pupil diameter as it dynamically changes in a frame by frame video. Comparing across 4 different smartphone models, the pupil-iris contrast of N=12 participants increases by an average of 451% with the proposed system. In a validation study of N=11 participants comparing the relative pupil change in the proposed system to a Neuroptics PLR-3000 Pupillometer during a pupillary light response test, the prototype system acheived a mean absolute error of 2.4%.

We propose BPClip, a less than $ 1 USD blood pressure monitor that leverages a plastic clip with a spring-loaded mechanism to enable any smartphone with a flash LED and a camera to measure blood pressure. Unlike prior approaches, our system measured systolic, mean, and diastolic blood pressure using oscillometric measurements that avoid cumbersome per-user calibrations and does not require specialized smartphone models with custom sensors.