Bolstering Heuristics for Statistical Validation of Prediction Algorithms

2015 ◽  
Author(s):  
Alex F. Mendelson ◽  
Maria A. Zuluaga ◽  
Brian F. Hutton ◽  
Sebastien Ourselin
Keyword(s):  
Statistical Validation ◽  
Prediction Algorithms

scholarly journals A Stochastic Framework for Evaluating Seizure Prediction Algorithms Using Hidden Markov Models

2007 ◽  
Vol 97 (3) ◽  
pp. 2525-2532 ◽  
Author(s):  
Stephen Wong ◽  
Andrew B. Gardner ◽  
Abba M. Krieger ◽  
Brian Litt
Keyword(s):  
Markov Models ◽  
Hidden Markov ◽  
Detection Algorithm ◽  
Type I ◽  
Seizure Prediction ◽  
Seizure Onset ◽  
Statistical Validation ◽  
Prediction Algorithms ◽  
Prediction Horizon ◽  
Stochastic Framework

Responsive, implantable stimulation devices to treat epilepsy are now in clinical trials. New evidence suggests that these devices may be more effective when they deliver therapy before seizure onset. Despite years of effort, prospective seizure prediction, which could improve device performance, remains elusive. In large part, this is explained by lack of agreement on a statistical framework for modeling seizure generation and a method for validating algorithm performance. We present a novel stochastic framework based on a three-state hidden Markov model (HMM) (representing interictal, preictal, and seizure states) with the feature that periods of increased seizure probability can transition back to the interictal state. This notion reflects clinical experience and may enhance interpretation of published seizure prediction studies. Our model accommodates clipped EEG segments and formalizes intuitive notions regarding statistical validation. We derive equations for type I and type II errors as a function of the number of seizures, duration of interictal data, and prediction horizon length and we demonstrate the model's utility with a novel seizure detection algorithm that appeared to predicted seizure onset. We propose this framework as a vital tool for designing and validating prediction algorithms and for facilitating collaborative research in this area.

A Comprehensive Study of Route Prediction Algorithms

2019 ◽  
Vol 7 (9) ◽  
pp. 78-85
Author(s):  
Dimple Singh ◽  
Pritam . ◽  
Neelam Duhan ◽  
Komal Kumar Bhatia
Keyword(s):  
Prediction Algorithms ◽  
Route Prediction ◽  
Comprehensive Study

The Evaluation of the Role of the Cytokines TNF- alfa and IL 6 in the Production of Hypoalbuminemia in Patients Undergoing Major Surgical Interventions

2018 ◽  
Vol 69 (7) ◽  
pp. 1830-1837
Author(s):  
Cristian Nicolescu ◽  
Alaxendru Pop ◽  
Alin Mihu ◽  
Luminita Pilat ◽  
Ovidiu Bedreag ◽  
...  
Keyword(s):  
Surgical Procedure ◽  
Tnf Alpha ◽  
Phase Reaction ◽  
Statistical Validation ◽  
Necrosis Factor Alpha ◽  
Surgical Interventions ◽  
Plasmatic Level ◽  
Factor Alpha ◽  
Validation Tests

This article presents an observational randomized prospective study done on 65 patients, who underwent major surgical interventions in the field of orthopedic surgery-total hip replacement or general surgery � total colectomy. The level of albuminemia in these cases were determined before the surgical intervention, after 6 hours of the intervention and after 24 h of the intervention. The measurements of the plasmatic concentration of the pro-inflammatory cytokines Tumor Necrosis factor -alpha (TNF-alpha) and interleukin 6 (IL6) were simultaneously done with the determination of the plasmatic levels of albumin. Values of hemoglobin and hematocrit were determined 24 h after the surgical procedure in order to exclude hemodilution, which could lead to a possible drop in the levels of plasmatic albumin. After the collection of the data, the statistical work was done and it consisted of descriptive statistics, correlation and comparison tests as well as statistical validation tests. Obtained results indicate that IL-6 plays a major role comparatively with that of TNF-alfa, regarding the decrease of the plasmatic level of albumin, and due to this, the primordial cause for hypoalbuminemia is an acute hepatic phase reaction. Supplemental permeability of the capillary wall under the action of TNF alpha has a secondary role, but could lead to a faster decrease in plasmatic albumin in the first hours after the surgical procedure.

scholarly journals Evaluation of Mixed Deep Neural Networks for Reverberant Speech Enhancement

Biomimetics ◽  
2019 ◽  
Vol 5 (1) ◽  
pp. 1 ◽  
Author(s):  
Michelle Gutiérrez-Muñoz ◽  
Astryd González-Salazar ◽  
Marvin Coto-Jiménez
Keyword(s):  
Neural Networks ◽  
Short Term Memory ◽  
Computational Cost ◽  
Real Life ◽  
Fixed Number ◽  
Training Procedure ◽  
Statistical Validation ◽  
Significant Drop ◽  
Training Time ◽  
Important Solution

Speech signals are degraded in real-life environments, as a product of background noise or other factors. The processing of such signals for voice recognition and voice analysis systems presents important challenges. One of the conditions that make adverse quality difficult to handle in those systems is reverberation, produced by sound wave reflections that travel from the source to the microphone in multiple directions. To enhance signals in such adverse conditions, several deep learning-based methods have been proposed and proven to be effective. Recently, recurrent neural networks, especially those with long short-term memory (LSTM), have presented surprising results in tasks related to time-dependent processing of signals, such as speech. One of the most challenging aspects of LSTM networks is the high computational cost of the training procedure, which has limited extended experimentation in several cases. In this work, we present a proposal to evaluate the hybrid models of neural networks to learn different reverberation conditions without any previous information. The results show that some combinations of LSTM and perceptron layers produce good results in comparison to those from pure LSTM networks, given a fixed number of layers. The evaluation was made based on quality measurements of the signal’s spectrum, the training time of the networks, and statistical validation of results. In total, 120 artificial neural networks of eight different types were trained and compared. The results help to affirm the fact that hybrid networks represent an important solution for speech signal enhancement, given that reduction in training time is on the order of 30%, in processes that can normally take several days or weeks, depending on the amount of data. The results also present advantages in efficiency, but without a significant drop in quality.

scholarly journals Partition Quantitative Assessment (PQA): A Quantitative Methodology to Assess the Embedded Noise in Clustered Omics and Systems Biology Data

2021 ◽  
Vol 11 (13) ◽  
pp. 5999
Author(s):  
Diego A. Camacho-Hernández ◽  
Victor E. Nieto-Caballero ◽  
José E. León-Burguete ◽  
Julio A. Freyre-González
Keyword(s):  
Systems Biology ◽  
Clustering Analysis ◽  
Quantitative Assessment ◽  
Clustering Algorithm ◽  
Statistical Evaluation ◽  
Quantitative Methodology ◽  
Typical Problem ◽  
Statistical Validation ◽  
Common Features ◽  
Biology Research

Identifying groups that share common features among datasets through clustering analysis is a typical problem in many fields of science, particularly in post-omics and systems biology research. In respect of this, quantifying how a measure can cluster or organize intrinsic groups is important since currently there is no statistical evaluation of how ordered is, or how much noise is embedded in the resulting clustered vector. Much of the literature focuses on how well the clustering algorithm orders the data, with several measures regarding external and internal statistical validation; but no score has been developed to quantify statistically the noise in an arranged vector posterior to a clustering algorithm, i.e., how much of the clustering is due to randomness. Here, we present a quantitative methodology, based on autocorrelation, in order to assess this problem.

scholarly journals An Analysis of Past Florence Nightingale Medal Recipients: Insights Into Exceptional Nurses and the Evolution of Nursing

2021 ◽  
Vol 7 ◽  
pp. 237796082098839
Author(s):  
Qian Wang ◽  
Ruifang Zhu ◽  
Zhiguang Duan
Keyword(s):  
Nursing Education ◽  
Red Cross ◽  
Statistical Validation ◽  
Award Recipient ◽  
Culturally Sensitive Care ◽  
Descriptive Research ◽  
Florence Nightingale ◽  
Specialist Nurses ◽  
High Level ◽  
Disaster Aid

Aim To examine past Florence Nightingale Medal recipients’ parallels with the evolving nature of the nursing field as a whole. Design Descriptive research. Method The professional and demographic characteristics of 1,449 Florence Nightingale Medal recipients between 1920 and 2015 were analyzed to develop a high-level overview of the award recipient characteristics. Result Medal recipients were primarily female (98.07%), with 36% being Specialist nurses. Awards were mainly conferred for aid work (30.4%) in the context of war or armed conflict followed by Nursing education (17.2%) and disaster aid (14.9%). The majority of recipients were affiliated with the Red Cross and the majority of recipients were those conducting Red Cross duties. Conclusion Our results offer statistical validation for the dedication of these exceptional individuals, while also highlighting overall parallels with the ongoing development of the nursing field as it expands to better deliver culturally-sensitive care and to overcome outdated stereotypes that would otherwise constrain innovation.

Sign in / Sign up

Export Citation Format

Share Document