Search Engines to Capture Missing Deaths From Institutional Data Warehouse.

INTRODUCTION: Clinical publications use mortality as a hard end point. It is unknown how many patient deaths are under-reported in institutional databases. The objective of this study was to query mortality in our patient cohort from our data warehouse and compare these deaths to those identified in different databases. METHODS: We passed the first/last name and date of birth of 134 patients through online mortality search engines (Find a Grave Index, US Cemetery and Funeral Home Collection, etc.) to assess their ability to capture patient deaths and compared that to deaths recorded from our institutional data warehouse. RESULTS: Our institutional data warehouse found approximately one-third of the total patient mortalities. After the Social Security Death Index, we found that the Find a Grave Index captured the most mortalities missed by the institutional data warehouse. These results highlight the advantages of incorporating readily available search engines into institutional data warehouses for the accurate collection of patient mortalities, particularly those that occur outside of index operative admission. CONCLUSIONS: The incorporation of the mortality search engines significantly augmented the capture of patient deaths. Our approach may be useful for tailored patient outreach and reporting mortalities with institutional data.

Stochastic-HD: Leveraging Stochastic Computing on the Hyper-Dimensional Computing Pipeline.

Brain-inspired Hyper-dimensional(HD) computing is a novel and efficient computing paradigm. However, highly parallel architectures such as Processing-in-Memory(PIM) are bottle-necked by reduction operations required such as accumulation. To reduce this bottle-neck of HD computing in PIM, we present Stochastic-HD that combines the simplicity of operations in Stochastic Computing (SC) with the complex task solving capabilities of the latest HD computing algorithms. Stochastic-HD leverages deterministic SC, which enables all of HD operations to be done as highly parallel bitwise operations and removes all reduction operations, thus improving the throughput of PIM. To this end, we propose an in-memory hardware design for Stochastic-HD that exploits its high level of parallelism and robustness to approximation. Our hardware uses in-memory bitwise operations along with associative memory-like operations to enable a fast and energy-efficient implementation. With Stochastic-HD, we were able to reach a comparable accuracy with the Baseline-HD. Furthermore, by proposing an integrated Stochastic-HD retraining approach Stochastic-HD is able to reduce the accuracy loss to just 0.3%. We additionally accelerate the retraining process in our hardware design to create an end-to-end accelerator for Stochastic-HD. Finally, we also add support for HD Clustering to Stochastic-HD, which is the first to map the HD Clustering operations to the stochastic domain. As compared to the best PIM design for HD, Stochastic-HD is also 4.4% more accurate and 43.1× more energy-efficient.