Sample-to-answer platform for the clinical evaluation of COVID-19 using a deep learning-assisted smartphone-based assay.

Since many lateral flow assays (LFA) are tested daily, the improvement in accuracy can greatly impact individual patient care and public health. However, current self-testing for COVID-19 detection suffers from low accuracy, mainly due to the LFA sensitivity and reading ambiguities. Here, we present deep learning-assisted smartphone-based LFA (SMARTAI-LFA) diagnostics to provide accurate decisions with higher sensitivity. Combining clinical data learning and two-step algorithms enables a cradle-free on-site assay with higher accuracy than the untrained individuals and human experts via blind tests of clinical data (n = 1500). We acquired 98% accuracy across 135 smartphone application-based clinical tests with different users/smartphones. Furthermore, with more low-titer tests, we observed that the accuracy of SMARTAI-LFA was maintained at over 99% while there was a significant decrease in human accuracy, indicating the reliable performance of SMARTAI-LFA. We envision a smartphone-based SMARTAI-LFA that allows continuously enhanced performance by adding clinical tests and satisfies the new criterion for digitalized real-time diagnostics.

The comparison between CHOP and R-CHOP in primary gastric diffuse large B cell lymphoma.

The combination chemotherapy with cyclophosphamide, doxorubicin, vincristine, and prednisolone (CHOP) plus rituximab is the standard treatment for patients with primary gastric diffuse large B cell lymphoma (DLBCL). However, a few trials comparing CHOP plus rituximab (R-CHOP) with CHOP have been conducted in primary gastric DLBCL. Among 93 consecutive patients receiving CHOP or R-CHOP as a first-line chemotherapy at our institution, 38 patients received CHOP and 55 patients received R-CHOP. With a median follow-up time of 48 months, the complete response (CR) rate, event-free survival (EFS), and overall survival (OS) did not differ between two treatment groups (P = 1.000, P = 0.744, and P = 0.213, respectively). The CR rates were 93.9% for patients receiving CHOP and 92.5% for patients receiving R-CHOP. The 3-year EFS rates were 86.0% for patients receiving CHOP and 81.7% for patients receiving R-CHOP; the 3-year OS rates were 94.7 and 84.7%, respectively. In a multivariate analysis, The CR rate was affected by the number of extranodal involvements (P = 0.011). The EFS and OS rates were affected by the Lugano stage (P = 0.067 and P = 0.008, respectively). High serum level of ß2-microglobulin was associated with worse EFS and OS in patients receiving R-CHOP (P = 0.018 and P = 0.015, respectively). In conclusion, the addition of rituximab was not found to have an impact on patients' outcomes with primary gastric DLBCL. The ß2-microglobulin in primary gastric DLBCL might be able to discriminate the patients' prognosis who are treated with R-CHOP chemotherapy.

A case of carbon monoxide poisoning with thrombus in right atrium.

Carbon monoxide is a nonirritant, odorless, colorless gas. Its effects are prominent in organs most sensitive to oxygen deprivation, such as the heart, brain, and kidney. Although less frequently, an association between thromboembolic events and carbon monoxide poisoning has been shown in the literatures. In this case, we report a case of atrial thrombus associated with carbon monoxide poisoning.