Forecasting adverse surgical events using self-supervised transfer learning for physiological signals

Hundreds of millions of surgical procedures take place annually across the world, which generate a prevalent type of electronic health record (EHR) data comprising time series physiological signals. Here, we present a transferable embedding method (i.e., a method to transform time series signals into input features for predictive machine learning models) named PHASE (PHysiologicAl Signal Embeddings) that enables us to more accurately forecast adverse surgical outcomes based on physiological signals. We evaluate PHASE on minute-by-minute EHR data of more than 50,000 surgeries from two operating room (OR) datasets and patient stays in an intensive care unit (ICU) dataset. PHASE outperforms other state-of-the-art approaches, such as long-short term memory networks trained on raw data and gradient boosted trees trained on handcrafted features, in predicting six distinct outcomes: hypoxemia, hypocapnia, hypotension, hypertension, phenylephrine, and epinephrine. In a transfer learning setting where we train embedding models in one dataset then embed signals and predict adverse events in unseen data, PHASE achieves significantly higher prediction accuracy at lower computational cost compared to conventional approaches. Finally, given the importance of understanding models in clinical applications we demonstrate that PHASE is explainable and validate our predictive models using local feature attribution methods.

Parkinson’s Disease Rating Scale Using Synchronization Analysis of Gait Dynamics

Analysis of gait dynamics is a noninvasive and totally painless test, and it can be an ideal method for the diagnosis of neurodegenerative diseases. In this study, based on the strength of synchronization between dynamics of strides, we have suggested a rating scale method for Parkinson’s disease (PD). Methods. The sample included 15 persons with PD (age: 66.8 ± 10.9 years) and 16 healthy persons (age: 39.3 ± 18.5 years) which were recruited from the Neurology Outpatient Clinic at Massachusetts General Hospital and were instructed to walk a 77 m long, straight hallway. The time interval of strides and subphases of strides were measured. Using the Hilbert transformation method, we obtained the data phase and used mean absolute error (MAE) to calculate the synchronization strength of the data phase. Results. In order to check the accuracy of our method, we measured the correlation between our numerical results (MAE) and values of the Hoehn-Yahr scale. Spearman’s rank correlation coefficients ( r ) and the P values were calculated. MAE of left and right stride intervals (LRSI) significantly correlates with the Hoehn-Yahr scale for the subjects with PD (with r = 0.60 and P = 0.025 < 0.05 ). Conclusion. We have revealed that the synchronization weakness of LRSI shows the severity of PD. This method seems to be well suited as a rating scale for people with PD.

CAN Tx Frame Implementation using Verilog

This article discusses the concept of CAN protocol and its implementation in verilog language. Initially the CAN protocol description is given in brief with the block diagram, later its design, implementation in verilog code is presented. The CAN transmission (Tx) data Frame is realized using verilog code, this is achieved by defining individual sub-blocks verilog codes and combining these to get the CAN transmission of data frame. In the year 1986, CAN data link layer protocol was introduced in SAE conference. In 1993, CAN protocol and high speed physical layer were internationally accredited as ISO 11898. As on today it has 11898-1 to 4 standard documents. The CAN 1.0, 2.0 versions were initially had fixed data rate for the entire frame. In 2012, CAN-FD (Flexible data rate) protocol was introduced. This will allow data phase a second higher bit rate, along with this restriction of 8 bytes is extended up to 64 bytes.In this paper CAN Tx data frame is realized using Xilinx 14.7 version using verilog language.

Monitoring the Daily Evolution and Extent of Snow Drought

Snow droughts are commonly defined as below average snowpack at a point in time, typically 1 April in the western United States (wUS). This definition is valuable for interpreting the state of the snowpack but obscures the temporal evolution of snow drought. Borrowing from dynamical systems theory, we applied phase diagrams to visually examine the evolution of snow water equivalent (SWE) and accumulated precipitation conditions in maritime, intermountain, and continental snow climates in the wUS using station observations as well as spatially distributed estimates of SWE and precipitation. Using a percentile-based drought definition phase diagrams of daily observed SWE and precipitation highlighted decision-relevant aspects of snow drought such as onset, evolution, and termination. The phase diagram approach can be used in tandem with spatially distributed estimates of daily SWE and precipitation to reveal variability in snow drought type and extent. When combined streamflow or other data, phase diagrams and spatial estimates of snow drought conditions can help inform drought monitoring and early warning and help link snow drought type and evolution impacts on ecosystems, water resources, and recreation. A web tool is introduced allowing users to create real-time or historic snow drought phase diagrams.

Translation and adaptation of the STOPP-START screening tool to Portuguese for detecting inappropriate prescriptions in older people: a protocol

IntroductionRational prescribing for older adults is a challenge because they usually exhibit multimorbidity and multimedication. One available and reliable tool to tackle this issue consists of the Screening Tool of Older People’s Prescriptions (STOPP) and the Screening Tool to Alert to Right Treatment (START), which has been associated with improvements in clinical outcomes. Our goal here is to translate and validate the STOPP-START screening tool for use with Portuguese general practitioners/family physicians.Methods and analysisThe study will be conducted in four phases: phase I—translation of the STOPP-START screening tool to Portuguese; phase II—data collection of patient data; phase III—intrarater reliability and agreement study; and phase IV—inter-rater reliability and agreement study.Ethics and disseminationThis study was approved by the Ethics Committee of the Central Health Region of Portugal (where the study will take place). Every participant will sign a written consent form. We intend to publish the full article in a related peer-reviewed journal, conference presentations, reports and in a PhD thesis.