Robust evaluation of deep learning-based representation methods for survival and gene essentiality prediction on bulk RNA-seq data.

Deep learning (DL) has shown potential to provide powerful representations of bulk RNA-seq data in cancer research. However, there is no consensus regarding the impact of design choices of DL approaches on the performance of the learned representation, including the model architecture, the training methodology and the various hyperparameters. To address this problem, we evaluate the performance of various design choices of DL representation learning methods using TCGA and DepMap pan-cancer datasets and assess their predictive power for survival and gene essentiality predictions.

The burden of significant pain in the cirrhosis population: Risk factors, analgesic use, and impact on health care utilization and clinical outcomes.

Background: We aimed to characterize pain and analgesic use in a large contemporary cohort of patients with cirrhosis and to associate pain with unplanned health care utilization and clinical outcomes in this population.

Methods: We included all patients with cirrhosis seen in UCSF hepatology clinics from 2013 to 2020. Pain severity and location were determined using documented pain scores at the initial visit; "significant pain" was defined as moderate or severe using established cutoffs.

Attention capture by own name decreases with speech compression.

Auditory stimuli that are relevant to a listener have the potential to capture focal attention even when unattended, the listener's own name being a particularly effective stimulus. We report two experiments to test the attention-capturing potential of the listener's own name in normal speech and time-compressed speech. In Experiment 1, 39 participants were tested with a visual word categorization task with uncompressed spoken names as background auditory distractors.

MELLODDY: Cross-pharma Federated Learning at Unprecedented Scale Unlocks Benefits in QSAR without Compromising Proprietary Information.

Federated multipartner machine learning has been touted as an appealing and efficient method to increase the effective training data volume and thereby the predictivity of models, particularly when the generation of training data is resource-intensive. In the landmark MELLODDY project, indeed, each of ten pharmaceutical companies realized aggregated improvements on its own classification or regression models through federated learning. To this end, they leveraged a novel implementation extending multitask learning across partners, on a platform audited for privacy and security.

Effects of multitasking on interpreting a spearcon sequence display for monitoring multiple patients.

Spearcons are time-compressed speech phrases. When arranged in a sequence representing vital signs of multiple patients, spearcons may be more informative than conventional auditory alarms. However, multiple resource theory suggests that certain timeshared tasks might interfere with listeners' ability to understand spearcons.

Incremental advances will improve medical device alarm sounds.

The March issue contains a laboratory study of auditory perception, which is an unusual topic for this journal. A perspective is provided on how the study relates to recent research on clinical auditory alarms and displays. Techniques used in the study are explored and explained, such as enrolment of non-clinician volunteer participants, use of coordinate response measure phrase stimuli, presentation of sound loudness levels using the decibel scale, and analysis using signal detection theory.

Evaluating enhanced pulse oximetry auditory displays for neonatal oxygen targeting: A randomized laboratory trial with clinicians and non-clinicians.

Standard pulse oximeter auditory tones do not clearly indicate departures from the target range of oxygen saturation (SpO) of 90%-95% in preterm neonates. We tested whether acoustically enhanced tones would improve participants' ability to identify SpO range. Twenty-one clinicians and 23 non-clinicians used (1) standard pulse oximetry variable-pitch tones plus alarms; (2) beacon-enhanced tones without alarms in which reference tones were inserted before standard pulse tones when SpO was outside target range; and (3) tremolo-enhanced tones without alarms in which pulse tones were modified with tremolo when SpO was outside target range.

Auditory Sequences Presented With Spearcons Support Better Multiple Patient Monitoring Than Single-Patient Alarms: A Preclinical Simulation.

Objective: A study of auditory displays for simulated patient monitoring compared the effectiveness of two sound categories (alarm sounds indicating general risk categories from international alarm standard IEC 60601-1-8 event-specific sounds according to the type of nursing unit) and two configurations (single-patient alarms multi-patient sequences).

Background: Fieldwork in speciality-focused high dependency units (HDU) indicated that auditory alarms are ambiguous and do not identify which patient has a problem. We tested whether participants perform better using auditory displays that identify the relevant patient and problem.

Signaling Patient Oxygen Desaturation with Enhanced Pulse Oximetry Tones.

Manufacturers could improve the pulse tones emitted by pulse oximeters to support more accurate identification of a patient's peripheral oxygen saturation (SpO2) range. In this article, we outline the strengths and limitations of the variable-pitch tone that represents SpO2 of each detected pulse, and we argue that enhancements to the tone to demarcate clinically relevant ranges are feasible and desirable. The variable-pitch tone is an appreciated and trusted feature of the pulse oximeter's user interface.

Attention to Changes on a Head-Worn Display: Two Preclinical Studies with Healthcare Scenarios.

Objective: In two experiments, we examined how quickly different visual alerts on a head-worn display (HWD) would capture participants' attention to a matrix of patient vital sign values, while multitasking.

Background: An HWD could help clinicians monitor multiple patients, regardless of where the clinician is located. We sought effective ways for HWDs to alert multitasking wearers to important events.

The Use of Head-Worn Displays for Vital Sign Monitoring in Critical and Acute Care: Systematic Review.

Background: Continuous monitoring of patient vital signs may improve patient outcomes. Head-worn displays (HWDs) can provide hands-free access to continuous vital sign information of patients in critical and acute care contexts and thus may reduce instances of unrecognized patient deterioration.

Objective: The purpose of the study is to conduct a systematic review of the literature to evaluate clinical, surrogate, and process outcomes when clinicians use HWDs for continuous patient vital sign monitoring.

We're Not Sure We Like It but We Still Want More: Trainee and Faculty Perceptions of Remote Learning During the COVID-19 Pandemic.

Objective: In this study, the authors aim to compare perceptions of remote learning versus in-person learning among faculty and trainees at a single institution during the COVID-19 pandemic and to evaluate the impact that a brief faculty training on best practices in online teaching would have on faculty attitudes towards remote learning.

Methods: The authors conducted an attitude survey on remote learning among trainees and faculty members approximately 3 months after the transition from in-person to remote learning. The authors then conducted a faculty training on best practices in online teaching followed by an evaluation survey.

Spearcon compression levels influence the gap in comprehension between untrained and trained listeners.

Auditory alarms in hospitals are ambiguous and do not provide enough information to support doctors and nurses' awareness of patient events. A potential alternative is the use of short segments of time-compressed speech, or However, sometimes it might be desirable for patients to understand spearcons and sometimes not. We used reverse hierarchy theory to hypothesize that there will be a degree of compression where spearcons are intelligible for trained listeners but not for untrained listeners.

Evaluation of an enhanced pulse oximeter auditory display: a simulaion study.

Background: We compared anaesthetists' ability to identify haemoglobin oxygen saturation (SpO) levels using two auditory displays: one based on a standard pulse oximeter display (varying pitch plus alarm) and the other enhanced with additional sound properties (varying pitch plus tremolo and acoustic brightness) to differentiate SpO ranges.

Methods: In a counter-balanced crossover study in a simulator, 20 experienced anaesthetists supervised a junior colleague (an actor) managing two airway surgery scenarios: once while using the enhanced auditory display and once while using a standard auditory display. Participants were distracted with other tasks such as paperwork and workplace interruptions, but were required to identify when SpO transitioned between pre-set ranges (target, low, critical) and when other vital signs transitioned out of a target range.

The impact of concurrent linguistic tasks on participants' identification of spearcons.

Spearcons (time-compressed speech) may be a viable auditory display for patient monitoring; however, the impact of concurrent linguistic tasks remains unexamined. We tested whether different concurrent linguistic tasks worsen participants' identification of spearcons. Experiment 1 tested non-clinician participants' identification of multiple-patient spearcons representing 2 vital signs of 5 patients while participants performed no concurrent task, reading, or saying linguistic tasks.

Comparison of Standard and Enhanced Pulse Oximeter Auditory Displays of Oxygen Saturation: A Laboratory Study With Clinician and Nonclinician Participants.

Background: When engaged in visually demanding tasks, anesthesiologists depend on the auditory display of the pulse oximeter (PO) to provide information about patients' oxygen saturation (SpO2). Current auditory displays are not always effective at providing SpO2 information. In this laboratory study, clinician and nonclinician participants identified SpO2 parameters using either a standard auditory display or an auditory display enhanced with additional acoustic properties while performing distractor tasks and in the presence of background noise.

Smooth or Stepped? Laboratory Comparison of Enhanced Sonifications for Monitoring Patient Oxygen Saturation.

Background: The pulse oximeter (PO) provides anesthesiologists with continuous visual and auditory information about a patient's oxygen saturation (SpO). However, anesthesiologists' attention is often diverted from visual displays, and clinicians may inaccurately judge SpO values when relying on conventional PO auditory tones. We tested whether participants could identify SpO value (e.

Monitoring vital signs with time-compressed speech.

Spearcons-time-compressed speech phrases-may be an effective way of communicating vital signs to clinicians without disturbing patients and their families. Four experiments tested the effectiveness of spearcons for conveying oxygen saturation (SpO2) and heart rate (HR) of one or more patients. Experiment 1 demonstrated that spearcons were more effective than earcons (abstract auditory motifs) at conveying clinical ranges.

The Impact of Head-Worn Displays on Strategic Alarm Management and Situation Awareness.

Objective: To investigate whether head-worn displays (HWDs) help mobile participants make better alarm management decisions and achieve better situation awareness than alarms alone.

Background: Patient alarms occur frequently in hospitals but often do not require clinical intervention. Clinicians may become desensitized to alarms and fail to respond to clinically relevant alarms.

Detection of visual stimuli on monocular peripheral head-worn displays.

Objective: To compare people's ability to detect peripherally presented stimuli on a monocular head-worn display (HWD) versus a conventional screen.

Background: Visual attention capture has been systematically investigated, but not with respect to HWDs. How stimulus properties affect attention capture is likely to be different on an HWD when compared to a traditional computer display.

Bayesian Latent Class Analysis Tutorial.

This article is a how-to guide on Bayesian computation using Gibbs sampling, demonstrated in the context of Latent Class Analysis (LCA). It is written for students in quantitative psychology or related fields who have a working knowledge of Bayes Theorem and conditional probability and have experience in writing computer programs in the statistical language R . The overall goals are to provide an accessible and self-contained tutorial, along with a practical computation tool.

High resolution retinal scanning reveals regional structural differences between MS and NMOSD optic neuritis regardless of antibody status.

Background: There is a need for biomarkers that can classify optic neuritis (ON) attacks as belonging to either neuromyelitis optica spectrum disorder with optic neuritis (NMOSD-ON) or relapsing remitting multiple sclerosis with optic neuritis (MS-ON). This study uses spectral domain optical coherence tomography (SD-OCT) data to perform a preliminary contrast between NMOSD-ON and MS-ON by analyzing peripapillary retinal nerve fiber layer and intra-macular layer patterns of injury.

Methods: In this cross-sectional study, we used SD-OCT to obtain peripapillary retinal nerve fiber layer and intra-macular layer data for 26 NMOSD-ON, 25 MS-ON, and 26 healthy control (HC) age-matched eyes.