This letter outlines how to identify, and potentially mitigate, common sources of “dataset shift” in machine-learning systems. This occurs when the model “training data” differ from the data used by ...the model to provide diagnostic, prognostic, or treatment advice.
AbstractObjectiveTo provide focused evaluation of predictive modeling of electronic medical record (EMR) data to predict 30 day hospital readmission.DesignSystematic review.Data sourceOvid Medline, ...Ovid Embase, CINAHL, Web of Science, and Scopus from January 2015 to January 2019.Eligibility criteria for selecting studiesAll studies of predictive models for 28 day or 30 day hospital readmission that used EMR data.Outcome measuresCharacteristics of included studies, methods of prediction, predictive features, and performance of predictive models.ResultsOf 4442 citations reviewed, 41 studies met the inclusion criteria. Seventeen models predicted risk of readmission for all patients and 24 developed predictions for patient specific populations, with 13 of those being developed for patients with heart conditions. Except for two studies from the UK and Israel, all were from the US. The total sample size for each model ranged between 349 and 1 195 640. Twenty five models used a split sample validation technique. Seventeen of 41 studies reported C statistics of 0.75 or greater. Fifteen models used calibration techniques to further refine the model. Using EMR data enabled final predictive models to use a wide variety of clinical measures such as laboratory results and vital signs; however, use of socioeconomic features or functional status was rare. Using natural language processing, three models were able to extract relevant psychosocial features, which substantially improved their predictions. Twenty six studies used logistic or Cox regression models, and the rest used machine learning methods. No statistically significant difference (difference 0.03, 95% confidence interval −0.0 to 0.07) was found between average C statistics of models developed using regression methods (0.71, 0.68 to 0.73) and machine learning (0.74, 0.71 to 0.77).ConclusionsOn average, prediction models using EMR data have better predictive performance than those using administrative data. However, this improvement remains modest. Most of the studies examined lacked inclusion of socioeconomic features, failed to calibrate the models, neglected to conduct rigorous diagnostic testing, and did not discuss clinical impact.
Literature on invasive neuromonitoring and bilateral decompressive craniectomies (BDC) in patients with refractory status epilepticus (RSE)-mediated hypoxic-ischemic brain injury (HIBI) is limited. ...Neuromonitoring can guide decision making and treatment escalation.
We report a case of a 17 years-old male who was admitted to our hospital's intensive care unit for RSE. HIBI was detected on neuroimaging on this patient's second day of admission after he developed central diabetes insipidus (DI). Invasive neuromonitoring revealed raised intracranial pressure (ICP) and brain hypoxia as measured by reduced brain tissue oxygen tension (PbtO
). Treatments were escalated in a tiered fashion, including administration of hyperosmolar agents, analgesics, sedatives, and a neuromuscular blocking drug. Eventually, BDC was performed as a salvage therapy as a means of controlling refractory ICP crisis in the setting of diffuse cerebral edema (DCE) following HIBI.
SE-mediated HIBI can result in refractory ICP crisis. Neuromonitoring can help identify secondary brain injury (SBI), guide treatment strategies, including surgical interventions, and may lead to better outcomes.
The COVID-19 pandemic has been damaging to the lives of people all around the world. Accompanied by the pandemic is an infodemic, an abundant and uncontrolled spread of potentially harmful ...misinformation. The infodemic may severely change the pandemic's course by interfering with public health interventions such as wearing masks, social distancing, and vaccination. In particular, the impact of the infodemic on vaccination is critical because it holds the key to reverting to pre-pandemic normalcy. This paper presents findings from a global survey on the extent of worldwide exposure to the COVID-19 infodemic, assesses different populations' susceptibility to false claims, and analyzes its association with vaccine acceptance. Based on responses gathered from over 18,400 individuals from 40 countries, we find a strong association between perceived believability of COVID-19 misinformation and vaccination hesitancy. Our study shows that only half of the online users exposed to rumors might have seen corresponding fact-checked information. Moreover, depending on the country, between 6% and 37% of individuals considered these rumors believable. A key finding of this research is that poorer regions were more susceptible to encountering and believing COVID-19 misinformation; countries with lower gross domestic product (GDP) per capita showed a substantially higher prevalence of misinformation. We discuss implications of our findings to public campaigns that proactively spread accurate information to countries that are more susceptible to the infodemic. We also defend that fact-checking platforms should prioritize claims that not only have wide exposure but are also perceived to be believable. Our findings give insights into how to successfully handle risk communication during the initial phase of a future pandemic.
Celotno besedilo
Dostopno za:
DOBA, IZUM, KILJ, NUK, PILJ, PNG, SAZU, SIK, UILJ, UKNU, UL, UM, UPUK
We report here a novel IBX-promoted oxidative coupling of primary amines and its utilization to Ugi reaction. Advantageously, the reaction could be carried out in choline chloride urea as a natural ...deep eutectic solvent. A range of imines and bisamides from pseudo-four-component oxidative Ugi reaction could be synthesized under mild and metal-free conditions. Advantageously, the oxidant (IBX) and solvent could be recycled up to five times with only a slight loss in activity.
The experimental and numerical analysis of the under-reamed piled ring foundation (with/without RDFS cushion) supported by soft clay was carried out. Total 34 model tests were performed to understand ...the effect of the under-reams and randomly distributed fibre reinforced sand (RDFS) cushion on the parameters like pile length, centre to centre spacing between under-reams, differential settlement, axial force in the under-ream pile and load sharing mechanism. Results have indicated that in comparison to the straight piles, under-reams at the bottom of piles significantly increases the load carrying capacity and reduce the differential settlement of the piled ring foundation. Load improvement factor for under-reamed piled ring foundation with RDFS cushion was noticeably higher, and settlement reduction ratio was lower than that without RDFS cushion. RDFS cushion increases the percentage of the load taken by the ring raft in the under-reamed piled ring foundation. The inner edge of the ring raft settled more than that outer edge and the centre. And the differential settlement of the under-reamed piled foundation with/without RDFS increased with the increase in the pile length and reduction in spacing between under-reams.
Celotno besedilo
Dostopno za:
BFBNIB, DOBA, GIS, IJS, IZUM, KILJ, KISLJ, NUK, PILJ, PNG, SAZU, UILJ, UKNU, UL, UM, UPUK
7.
Deep learning enabled inorganic material generator Pathak, Yashaswi; Juneja, Karandeep Singh; Varma, Girish ...
Physical chemistry chemical physics : PCCP,
12/2020, Letnik:
22, Številka:
46
Journal Article
Recenzirano
Recent years have witnessed utilization of modern machine learning approaches for predicting the properties of materials using available datasets. However, to identify potential candidates for ...material discovery, one has to systematically scan through a large chemical space and subsequently calculate the properties of all such samples. On the other hand, generative methods are capable of efficiently sampling the chemical space and can generate molecules/materials with desired properties. In this study, we report a deep learning based inorganic material generator (DING) framework consisting of a generator module and a predictor module. The generator module is developed based on conditional variational autoencoders (CVAEs) and the predictor module consists of three deep neural networks trained for predicting the enthalpy of formation, volume per atom and energy per atom chosen to demonstrate the proposed method. The predictor and generator modules have been developed using a one-hot key representation of the material composition. A series of tests were done to examine the robustness of the predictor models, to demonstrate the continuity of the latent material space, and its ability to generate materials exhibiting target property values. The DING architecture proposed in this paper can be extended to other properties based on which the chemical space can be efficiently explored for interesting materials/molecules.
A machine learning framework that generates material compositions exhibiting properties desired by the user.
Reducing unplanned readmissions is a major focus of current hospital quality efforts. In order to avoid unfair penalization, administrators and policymakers use prediction models to adjust for the ...performance of hospitals from healthcare claims data. Regression-based models are a commonly utilized method for such risk-standardization across hospitals; however, these models often suffer in accuracy. In this study we, compare four prediction models for unplanned patient readmission for patients hospitalized with acute myocardial infarction (AMI), congestive health failure (HF), and pneumonia (PNA) within the Nationwide Readmissions Database in 2014. We evaluated hierarchical logistic regression and compared its performance with gradient boosting and two models that utilize artificial neural networks. We show that unsupervised Global Vector for Word Representations embedding representations of administrative claims data combined with artificial neural network classification models improves prediction of 30-day readmission. Our best models increased the AUC for prediction of 30-day readmissions from 0.68 to 0.72 for AMI, 0.60 to 0.64 for HF, and 0.63 to 0.68 for PNA compared to hierarchical logistic regression. Furthermore, risk-standardized hospital readmission rates calculated from our artificial neural network model that employed embeddings led to reclassification of approximately 10% of hospitals across categories of hospital performance. This finding suggests that prediction models that incorporate new methods classify hospitals differently than traditional regression-based approaches and that their role in assessing hospital performance warrants further investigation.
Celotno besedilo
Dostopno za:
DOBA, IZUM, KILJ, NUK, PILJ, PNG, SAZU, SIK, UILJ, UKNU, UL, UM, UPUK
Many aspects of CKD management rely heavily on patient self-care, including medication and dietary adherence, self-monitoring of BP, and daily physical activity. Growing evidence suggests that ...incorporating smartphone-based applications can support self-care in CKD and chronic disease more generally.
We identified applications targeting patients with CKD by conducting a search of the US Apple App Store (iOS) and Google Play Store (Android) using the following four phrases: "kidney disease," "renal," "dialysis," and "kidney transplant." We considered the first 50 applications for each search term on each application store. We adapted a previously described framework for assessment of mobile health applications to account for kidney disease-specific content areas and evaluated applications on their types of patient engagement, quality, usability, and safety. Engagement and quality were assessed by both a patient and a nephrologist, usability was assessed by a patient, and safety was assessed by a nephrologist. Overall, two patients with CKD and three nephrologists performed the evaluations. We examined pairwise correlations between patient, nephrologist, and consumer ratings of application quality.
Our search strategy identified 174 unique applications on Android and 165 unique applications on iOS. After excluding applications that were not related to kidney disease, were not patient facing, or were last updated before 2014, 12 Android-only applications, 11 iOS-only applications, and five dual-platform applications remained. Patient and nephrologist application quality ratings, assessed by the net promoter score, were not correlated (
=0.36;
=0.06). Consumer ratings on the application stores did not correlate with patient ratings of application quality (
=0.34;
=0.18).
Only a small subset of CKD applications was highly rated by both patients and nephrologists. Patients' impressions of application quality are not directly linked to consumer application ratings or nephrologist impressions.