Micro-mechanical blood clot testing using smartphones

Abstract

Frequent prothrombin time (PT) and international normalized ratio (INR) testing is critical for millions of people on lifelong anticoagulation with warfarin. Currently, testing is performed in hospital laboratories or with expensive point-of-care devices limiting the ability to test frequently and affordably. We report a proof-of-concept PT/INR testing system that uses the vibration motor and camera on smartphones to track micro-mechanical movements of a copper particle. The smartphone system computed the PT/INR with inter-class correlation coefficients of 0.963 and 0.966, compared to a clinical-grade coagulation analyzer for 140 plasma samples and demonstrated similar results for 80 whole blood samples using a single drop of blood (10 μl). When tested with 79 blood samples with coagulopathic conditions, the smartphone system demonstrated a correlation of 0.974 for both PT/INR. Given the ubiquity of smartphones in the global setting, this proof-of-concept technology may provide affordable and effective PT and INR testing in low-resource environments.

Fig. 1. Blood coagulation testing using a smartphone.

a Schematic of the system: a plastic attachment containing a cup with 10 μl of whole blood, 20 μl of tissue factor, and a copper particle. The smartphone’s vibration motor is coupled to the attachment and vibrates the particle, which is captured with the camera. b A workflow (from left to right) showing how whole blood is added to the cup in our system. c The phone captures the motion of the particle starting from when the tissue factor is added to the blood (t_start). The particle moves freely in the blood when it is in a liquid state. When the blood coagulates, the particle’s motion reduces (t_end).

Fig. 2. Workflow to compute PT from the smartphone video.

a Color thresholding and image processing techniques are applied to identify the cup holder and to create a mask that captures the motion of the capillary tube or pipette, M_tube,t. We then isolate the interior of the cup containing the particle, M_particle,t. b The L1 norm is applied between masked images to quantify the amount of 2D motion between video frames. c The most prominent peak in the motion curve d_tube[t] marks the start of the PT measurement, t_start. The knee of the particle’s motion curve d_particle[t] denotes the particle’s transition from motion to stasis, and marks the end of the PT measurement, t_end.

Fig. 3. Plasma clinical testing results.

a–d Correlation and Bland-Altman plots comparing plasma PT/INR values from the smartphone system and the clinical-grade coagulation analyzer. In the Bland-Altman plot, μ is the mean error and σ is the standard deviation (SD) of the errors, the solid line represents the mean error and the dotted lines represent the 95% limits of agreement. Source data are provided as a Source Data file.

Fig. 4. Coagulopathy testing results.

a–d Correlation and Bland-Altman plots comparing coagulopathic plasma PT/INR values from the smartphone system and the clinical-grade coagulation analyzer. In the Bland-Altman plot, μ is the mean error and σ is the standard deviation (SD) of the errors, the solid line represents the mean error and the dotted lines represent the 95% limits of agreement. Source data are provided as a Source Data file.

Fig. 5. Whole blood clinical testing results.

a–d Correlation and Bland-Altman plots comparing whole blood PT/INR values from the smartphone system and the commercial POCT coagulometer. In the Bland-Altman plot, μ is the mean error and σ is the standard deviation (SD) of the errors, the solid line represents the mean error and the dotted lines represent the 95% limits of agreement. Source data are provided as a Source Data file.

Fig. 6. Benchmark testing across different scenarios.

The system was evaluated across (a) different vibration strengths, b different particle materials, c different smartphone models, d illuminance levels, and e, f different volumes of plasma in a small and large cup. The figure shows the mean and SD computed across three measurements. Source data are provided as a Source Data file.