Neural-network analysis of socio-medical data to identify predictors of undiagnosed hepatitis C virus infections in Germany (DETECT)

Reiser, Markus; Wiebner, B.; Hirsch, Jürgen

doi:10.1186/s12967-019-1832-4

Cited by 12 publications

(11 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In connection with HCV, SOM clustering was used to investigate hepatocellular carcinoma (HCC) development as the basis for tumor differentiation and invasiveness, from expression levels of 12,600 genes in 50 HCC samples from patients with positive HCV serology (50). Also, Kohonen's ANN were trained to predict undiagnosed HCV infections and infection risk (51).…”

Section: Mutation Types and Amino Acid Substitution Tolerance In Haplotypes From Low And High Fitness Peaksmentioning

confidence: 99%

A two-level, dynamic fitness landscape of hepatitis C virus revealed by self-organized haplotype maps

Delgado

Perales

García-Crespo

et al. 2021

Preprint

View full text Add to dashboard Cite

Fitness landscapes reflect the adaptive potential of viruses. There is no information on how fitness peaks evolve when a virus replicates extensively in a controlled cell culture environment. Here we report the construction of Self-Organized Maps (SOMs), based on deep sequencing reads of three amplicons of the NS5A-NS5B-coding region of hepatitis C virus (HCV). A two-dimensional neural network was constructed and organized according to sequence relatedness. The third dimension of the fitness profile was given by the haplotype frequencies at each neuron. Fitness maps were derived for 44 HCV populations that share a common ancestor that was passaged up to 210 times in human hepatoma Huh-7.5 cells. As the virus increased its adaptation to the cells, the number of fitness peaks expanded, and their distribution shifted in sequence space. The landscape consisted of an extended basal platform, and a lower number of protruding higher fitness peaks. The function that relates fitness level and peak abundance corresponds a power law, a relationship observed with other complex natural phenomena. The dense basal platform may serve as spring-board to attain high fitness peaks. The study documents a highly dynamic, double-layer fitness landscape of HCV when evolving in a monotonous cell culture environment. This information may help interpreting HCV fitness landscapes in complex in vivo environments.IMPORTANCEThe study provides for the first time the fitness landscape of a virus in the course of its adaptation to a cell culture environment, in absence of external selective constraints. The deep sequencing-based self-organized maps document a two-layer fitness distribution with an ample basal platform, and a lower number of protruding, high fitness peaks. This landscape structure offers potential benefits for virus resilience to mutational inputs.

show abstract

Section: Mutation Types and Amino Acid Substitution Tolerance In Haplotypes From Low And High Fitness Peaksmentioning

confidence: 99%

A two-level, dynamic fitness landscape of hepatitis C virus revealed by self-organized haplotype maps

Delgado

Perales

García-Crespo

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Considering the maximum number of ARMA, seasonal auto regressive (SAR) and seasonal moving average (SMA) as 5, an example of the optimum achieved solution by ARIMA-CGA is provided in Figure 2. (23) where N is the number of samples, MSE is the mean square error and Comp. is the complexity of the model.…”

Section: Stochastic Modelingmentioning

confidence: 99%

“…Over the past few years, soft computing methods have been employed across domains and have established reliable tools for modeling complex systems and predicting different phenomena in healthcare (18)(19)(20)(21)(22)(23)(24). Among soft computing techniques, the Group Method of Data Handling (GMDH) is a common self-organizing heuristic model, which can be used for simulating complicated nonlinear problems.…”

Section: Introductionmentioning

confidence: 99%

A continuous data driven translational model to evaluate effectiveness of population-level health interventions: case study, smoking ban in public places on hospital admissions for acute coronary events.

Bonakdari

Pelletier

Martel‐Pelletier

2020

Preprint

View full text Add to dashboard Cite

Background. An important task in developing accurate public health intervention evaluation methods based on historical interrupted time series (ITS) records is to determine the exact lag time between pre- and post-intervention. We propose a novel continuous transitional data-driven hybrid methodology using a non-linear approach based on a combination of stochastic and artificial intelligence methods that facilitate the evaluation of ITS data without knowledge of lag time. Understanding the influence of implemented intervention on outcome(s) is imperative for decision makers in order to manage health systems accurately and in a timely manner. Methods. To validate a developed hybrid model, we used, as an example, a published dataset based on a real health problem on the effects of the Italian smoking ban in public spaces on hospital admissions for acute coronary events. We employed a continuous methodology based on data preprocessing to identify linear and nonlinear components in which autoregressive moving average and generalized structure group method of data handling were combined to model stochastic and nonlinear components of ITS. We analyzed the rate of admission for acute coronary events from January 2002 to November 2006 using this new data-driven hybrid methodology that allowed for long-term outcome prediction. Results. Our results showed the Pearson correlation coefficient of the proposed combined transitional data-driven model exhibited an average of 17.74% enhancement from the single stochastic model and 2.05% from the nonlinear model. In addition, data demonstrated that the developed model improved the mean absolute percentage error and correlation coefficient values for which 2.77% and 0.89 were found compared to 4.02% and 0.76, respectively. Importantly, this model does not use any predefined lag time between pre- and post-intervention.Conclusions. Most of the previous studies employed the linear regression and considered a lag time to interpret the impact of intervention on public health outcome. The proposed hybrid methodology improved ITS prediction from conventional methods and could be used as a reliable alternative in public health intervention evaluation.

show abstract

“…With the penetration of Internet technology into daily medical treatments, people are more accustomed to seeking help and sharing clinical experience on the Internet. Therefore, a large amount of open online medical data has accumulated [10], [11]. With the rapid growth of medical social websites, the average number of search results for common diseases such as hypertension in search engines has exceeded 100 million.…”

Section: Introductionmentioning

confidence: 99%

Guideline-Driven Medical Decision Support Methods for Family Healthcare

Wang

Qian

2021

IEEE Access

View full text Add to dashboard Cite

Medical guidelines are effective to guide medical practice and improve therapeutic effect. Currently, medical guidelines are primarily used in medical institutions but are still not available to the public. To improve the practicality of guidelines in family practice, this paper proposes a novel approach to assisting family medical decision support using semantic technology and open data analysis. A diseasespecific knowledge model is constructed using semantic guideline expressions, which provide standard care plans to the public. A medical text corpus is formed by collecting medical information from open data sources online. Via text mining and sentiment analysis of the medical text corpus, the word frequency and sentiment score of different medical procedures are calculated, which are used to provide detailed instructions for public treatment. A guideline-based knowledge model is constructed to create eczema-specific standard care plans. According to the resulting frequencies, hydrocortisone butyrate cream (HBC) elicited the most concern among hormone drugs (54%), followed by mometasone furoate cream (MFC), accounting for 28% among all hormone drugs. According to the average sentiment score, MFC is more frequently recommended than HBC. For skin care products, YMJ elicited the most concern, while Cetaphil was the most recommended. The results of the word frequency analysis and sentiment analysis are combined to provide detailed and clear recommendations to supplement standard care plans for family medical decision support. The method proposed by this paper is an important supplement and extension to in-hospital data analysis.

show abstract

Neural-network analysis of socio-medical data to identify predictors of undiagnosed hepatitis C virus infections in Germany (DETECT)

Cited by 12 publications

References 12 publications

A two-level, dynamic fitness landscape of hepatitis C virus revealed by self-organized haplotype maps

A two-level, dynamic fitness landscape of hepatitis C virus revealed by self-organized haplotype maps

A continuous data driven translational model to evaluate effectiveness of population-level health interventions: case study, smoking ban in public places on hospital admissions for acute coronary events.

Guideline-Driven Medical Decision Support Methods for Family Healthcare

Contact Info

Product

Resources

About