Deepm5C: A deep-learning-based hybrid framework for identifying human RNA N5-methylcytosine sites using a stacking strategy

1. Download : Download high-res image (173KB)
2. Download : Download full-size image

     

A Perioperative Care Display for Understanding High Acuity Patients

Background  The data visualization literature asserts that the details of the optimal data display must be tailored to the specific task, the background of the user, and the characteristics of the data. The general organizing principle of a concept-oriented display is known to be useful for many tasks and data types. Objectives  In this project, we used general principles of data visualization and a co-design process to produce a clinical display tailored to a specific cognitive task, chosen from the anesthesia domain, but with clear generalizability to other clinical tasks. To support the work of the anesthesia-in-charge (AIC) our task was, for a given day, to depict the acuity level and complexity of each patient in the collection of those that will be operated on the following day. The AIC uses this information to optimally allocate anesthesia staff and providers across operating rooms. Methods  We used a co-design process to collaborate with participants who work in the AIC role. We conducted two in-depth interviews with AICs and engaged them in subsequent input on iterative design solutions. Results  Through a co-design process, we found (1) the need to carefully match the level of detail in the display to the level required by the clinical task, (2) the impedance caused by irrelevant information on the screen such as icons relevant only to other tasks, and (3) the desire for a specific but optional trajectory of increasingly detailed textual summaries. Conclusion  This study reports a real-world clinical informatics development project that engaged users as co-designers. Our process led to the user-preferred design of a single binary flag to identify the subset of patients needing further investigation, and then a trajectory of increasingly detailed, text-based abstractions for each patient that can be displayed when more information is needed.     

ONRAB® oral rabies vaccine is shed from,but does not persist in,captive mammals

ONRAB® is a human adenovirus rabies glycoprotein recombinant vaccine developed to control rabies in wildlife. To support licensing and widespread use of the vaccine, safety studies are needed to assess its potential residual impact on wildlife populations. We examined the persistence of the ONRAB® vaccine virus in captive rabies vector and non-target mammals. This research complements work on important rabies vector species (raccoon, striped skunk, and red fox) but also adds to previous findings with the addition of some non-target species (Virginia opossum, Norway rats, and cotton rats) and a prolonged period of post vaccination monitoring (41 days). Animals were directly inoculated orally with the vaccine and vaccine shedding was monitored using quantitative real-time PCR applied to oral and rectal swabs. ONRAB® DNA was detected in both oral and rectal swabs from 6 h to 3 days post-inoculation in most animals, followed by a resurgence of shedding between days 17 and 34 in some species. Overall, the duration over which ONRAB® DNA was detectable was shorter for non-target mammals, and by day 41, no animal had detectable DNA in either oral or rectal swabs. All target species, as well as cotton rats and laboratory-bred Norway rats, developed robust humoral immune responses as measured by competitive ELISA, with all individuals being seropositive at day 31. Similarly, opossums showed good response (89% seropositive; 8/9), whereas only one of nine wild caught Norway rats was seropositive at day 31. These results support findings of other safety studies suggesting that ONRAB® does not persist in vector and non-target mammals exposed to the vaccine. As such, we interpret these data to reflect a low risk of adverse effects to wild populations following distribution of ONRAB® to control sylvatic rabies.     

Rethinking PICO in the Machine Learning Era: ML-PICO

Background  Machine learning (ML) has captured the attention of many clinicians who may not have formal training in this area but are otherwise increasingly exposed to ML literature that may be relevant to their clinical specialties. ML papers that follow an outcomes-based research format can be assessed using clinical research appraisal frameworks such as PICO (Population, Intervention, Comparison, Outcome). However, the PICO frameworks strain when applied to ML papers that create new ML models, which are akin to diagnostic tests. There is a need for a new framework to help assess such papers. Objective  We propose a new framework to help clinicians systematically read and evaluate medical ML papers whose aim is to create a new ML model: ML-PICO (Machine Learning, Population, Identification, Crosscheck, Outcomes). We describe how the ML-PICO framework can be applied toward appraising literature describing ML models for health care. Conclusion  The relevance of ML to practitioners of clinical medicine is steadily increasing with a growing body of literature. Therefore, it is increasingly important for clinicians to be familiar with how to assess and best utilize these tools. In this paper we have described a practical framework on how to read ML papers that create a new ML model (or diagnostic test): ML-PICO. We hope that this can be used by clinicians to better evaluate the quality and utility of ML papers.     

Multidimensional Ultrasound Doppler Signal Analysis for Fetal Activity Monitoring

Fetal activity parameters such as movements, heart rate and the related parameters are essential indicators of fetal wellbeing, and no device provides simultaneous access to and sufficient estimation of all of these parameters to evaluate fetal health. This work was aimed at collecting these parameters to automatically separate healthy from compromised fetuses. To achieve this goal, we first developed a multi-sensor–multi-gate Doppler system. Then we recorded multidimensional Doppler signals and estimated the fetal activity parameters via dedicated signal processing techniques. Finally, we combined these parameters into four sets of parameters (or four hyper-parameters) to determine the set of parameters that is able to separate healthy from other fetuses. To validate our system, a data set consisting of two groups of fetal signals (normal and compromised) was established and provided by physicians. From the estimated parameters, an instantaneous Manning-like score, referred to as the ultrasonic score, was calculated and was used together with movements, heart rate and the associated parameters in a classification process employing the support vector machine method. We investigated the influence of the sets of parameters and evaluated the performance of the support vector machine using the computation of sensibility, specificity, percentage of support vectors and total classification error. The sensitivity of the four sets ranged from 79% to 100%. Specificity was 100% for all sets. The total classification error ranged from 0% to 20%. The percentage of support vectors ranged from 33% to 49%. Overall, the best results were obtained with the set of parameters consisting of fetal movement, short-term variability, long-term variability, deceleration and ultrasound score. The sensitivity, specificity, percentage of support vectors and total classification error of this set were respectively 100%, 100%, 35% and 0%. This indicated our ability to separate the data into two sets (normal fetuses and pathologic fetuses), and the results highlight the excellent match with the clinical classification performed by the physicians. This work indicates the feasibility of detecting compromised fetuses and also represents an interesting method of close fetal monitoring during the entire pregnancy.     

Endovascular deep brain stimulation: Investigating the relationship between vascular structures and deep brain stimulation targets

BackgroundEndovascular delivery of current using ‘stentrodes’ – electrode bearing stents – constitutes a potential alternative to conventional deep brain stimulation (DBS). The precise neuroanatomical relationships between DBS targets and the vascular system, however, are poorly characterized to date.ObjectiveTo establish the relationships between cerebrovascular system and DBS targets and investigate the feasibility of endovascular stimulation as an alternative to DBS.MethodsNeuroanatomical targets as employed during deep brain stimulation (anterior limb of the internal capsule, dentatorubrothalamic tract, fornix, globus pallidus pars interna, medial forebrain bundle, nucleus accumbens, pedunculopontine nucleus, subcallosal cingulate cortex, subthalamic nucleus, and ventral intermediate nucleus) were superimposed onto probabilistic vascular atlases obtained from 42 healthy individuals. Euclidian distances between targets and associated vessels were measured. To determine the electrical currents necessary to encapsulate the predefined neurosurgical targets and identify potentially side-effect inducing substrates, a preliminary volume of tissue activated (VTA) analysis was performed.ResultsSix out of ten DBS targets were deemed suitable for endovascular stimulation: medial forebrain bundle (vascular site: P1 segment of posterior cerebral artery), nucleus accumbens (vascular site: A1 segment of anterior cerebral artery), dentatorubrothalamic tract (vascular site: s2 segment of superior cerebellar artery), fornix (vascular site: internal cerebral vein), pedunculopontine nucleus (vascular site: lateral mesencephalic vein), and subcallosal cingulate cortex (vascular site: A2 segment of anterior cerebral artery). While VTAs effectively encapsulated mfb and NA at current thresholds of 3.5 V and 4.5 V respectively, incremental amplitude increases were required to effectively cover fornix, PPN and SCC target (mean voltage: 8.2 ± 4.8 V, range: 3.0–17.0 V). The side-effect profile associated with endovascular stimulation seems to be comparable to conventional lead implantation. Tailoring of targets towards vascular sites, however, may allow to reduce adverse effects, while maintaining the efficacy of neural entrainment within the target tissue.ConclusionsWhile several challenges remain at present, endovascular stimulation of select DBS targets seems feasible offering novel and exciting opportunities in the neuromodulation armamentarium.