Towards Personalization of Diabetes Therapy Using Computerized Decision Support and Machine Learning: Some Open Problems and Challenges

2015 ◽  
pp. 237-260 ◽  
Author(s):  
Klaus Donsa ◽  
Stephan Spat ◽  
Peter Beck ◽  
Thomas R. Pieber ◽  
Andreas Holzinger
Keyword(s):  
Machine Learning ◽  
Decision Support ◽  
Computerized Decision Support ◽  
Open Problems ◽  
Diabetes Therapy

Review of classification studies for machine learning in the development of intelligent management decision support systems

2020 ◽  
Vol 89 ◽  
pp. 20-29
Author(s):  
Sh. K. Kadiev ◽  
◽  
R. Sh. Khabibulin ◽  
P. P. Godlevskiy ◽  
V. L. Semikov ◽  
...  
Keyword(s):  
Machine Learning ◽  
Decision Support ◽  
Mathematical Models ◽  
Decision Support Systems ◽  
Support Systems ◽  
Management Decision ◽  
Classification Methods ◽  
Advantages And Disadvantages ◽  
Intelligent Management ◽  
Management Decision Support

Introduction. An overview of research in the field of classification as a method of machine learning is given. Articles containing mathematical models and algorithms for classification were selected. The use of classification in intelligent management decision support systems in various subject areas is also relevant. Goal and objectives. The purpose of the study is to analyze papers on the classification as a machine learning method. To achieve the objective, it is necessary to solve the following tasks: 1) to identify the most used classification methods in machine learning; 2) to highlight the advantages and disadvantages of each of the selected methods; 3) to analyze the possibility of using classification methods in intelligent systems to support management decisions to solve issues of forecasting, prevention and elimination of emergencies. Methods. To obtain the results, general scientific and special methods of scientific knowledge were used - analysis, synthesis, generalization, as well as the classification method. Results and discussion thereof. According to the results of the analysis, studies with a mathematical formulation and the availability of software developments were identified. The issues of classification in the implementation of machine learning in the development of intelligent decision support systems are considered. Conclusion. The analysis revealed that enough algorithms were used to perform the classification while sorting the acquired knowledge within the subject area. The implementation of an accurate classification is one of the fundamental problems in the development of management decision support systems, including for fire and emergency prevention and response. Timely and effective decision by officials of operational shifts for the disaster management is also relevant. Key words: decision support, analysis, classification, machine learning, algorithm, mathematical models.

scholarly journals Computer-supported Detection of M-Components and Evaluation of Immunoglobulins after Capillary Electrophoresis

2001 ◽  
Vol 47 (1) ◽  
pp. 110-117 ◽  
Author(s):  
Magnus Jonsson ◽  
Joyce Carlson ◽  
Jan-Olof Jeppsson ◽  
Per Simonsson
Keyword(s):  
Capillary Electrophoresis ◽  
Decision Support ◽  
Protein Separation ◽  
Serum Proteins ◽  
Cost Effective ◽  
Clinical Samples ◽  
Serum Samples ◽  
Computerized Decision Support ◽  
Cost Effective Method ◽  
Mathematical Algorithms

Abstract Background: Electrophoresis of serum samples allows detection of monoclonal gammopathies indicative of multiple myeloma, Waldenström macroglobulinemia, monoclonal gammopathy of undetermined significance, and amyloidosis. Present methods of high-resolution agarose gel electrophoresis (HRAGE) and immunofixation electrophoresis (IFE) are manual and labor-intensive. Capillary zone electrophoresis (CZE) allows rapid automated protein separation and produces digital absorbance data, appropriate as input for a computerized decision support system. Methods: Using the Beckman Paragon CZE 2000 instrument, we analyzed 711 routine clinical samples, including 95 monoclonal components (MCs) and 9 cases of Bence Jones myeloma, in both the CZE and HRAGE systems. Mathematical algorithms developed for the detection of monoclonal immunoglobulins (MCs) in the γ- and β-regions of the electropherogram were tested on the entire material. Additional algorithms evaluating oligoclonality and polyclonal concentrations of immunoglobulins were also tested. Results: CZE electropherograms corresponded well with HRAGE. Only one IgG MC of 1 g/L, visible on HRAGE, was not visible after CZE. Algorithms detected 94 of 95 MCs (98.9%) and 100% of those visible after CZE. Of 607 samples lacking an MC on HRAGE, only 3 were identified by the algorithms (specificity, 99%). Algorithms evaluating total gammaglobulinemia and oligoclonality also identified several cases of Bence Jones myeloma. Conclusions: The use of capillary electrophoresis provides a modern, rapid, and cost-effective method of analyzing serum proteins. The additional option of computerized decision support, which provides rapid and standardized interpretations, should increase the clinical availability and usefulness of protein analyses in the future.

scholarly journals Development of Machine Learning Models to Predict Compressed Sward Height in Walloon Pastures Based on Sentinel-1, Sentinel-2 and Meteorological Data Using Multiple Data Transformations

2021 ◽  
Vol 13 (3) ◽  
pp. 408
Author(s):  
Charles Nickmilder ◽  
Anthony Tedde ◽  
Isabelle Dufrasne ◽  
Françoise Lessire ◽  
Bernard Tychon ◽  
...  
Keyword(s):  
Machine Learning ◽  
Decision Support ◽  
Support System ◽  
Cross Validation ◽  
Learning Models ◽  
Data Transformations ◽  
Independent Validation ◽  
Sward Height ◽  
Machine Learning Models ◽  
Sentinel 2

Accurate information about the available standing biomass on pastures is critical for the adequate management of grazing and its promotion to farmers. In this paper, machine learning models are developed to predict available biomass expressed as compressed sward height (CSH) from readily accessible meteorological, optical (Sentinel-2) and radar satellite data (Sentinel-1). This study assumed that combining heterogeneous data sources, data transformations and machine learning methods would improve the robustness and the accuracy of the developed models. A total of 72,795 records of CSH with a spatial positioning, collected in 2018 and 2019, were used and aggregated according to a pixel-like pattern. The resulting dataset was split into a training one with 11,625 pixellated records and an independent validation one with 4952 pixellated records. The models were trained with a 19-fold cross-validation. A wide range of performances was observed (with mean root mean square error (RMSE) of cross-validation ranging from 22.84 mm of CSH to infinite-like values), and the four best-performing models were a cubist, a glmnet, a neural network and a random forest. These models had an RMSE of independent validation lower than 20 mm of CSH at the pixel-level. To simulate the behavior of the model in a decision support system, performances at the paddock level were also studied. These were computed according to two scenarios: either the predictions were made at a sub-parcel level and then aggregated, or the data were aggregated at the parcel level and the predictions were made for these aggregated data. The results obtained in this study were more accurate than those found in the literature concerning pasture budgeting and grassland biomass evaluation. The training of the 124 models resulting from the described framework was part of the realization of a decision support system to help farmers in their daily decision making.

scholarly journals NCOG-31. DEVELOPMENT AND EVALUATION OF PROGNOSTIC MODELS TO PREDICT SURVIVAL OF PATIENTS WITH GLIOBLASTOMA MULTIFORME

2020 ◽  
Vol 22 (Supplement_2) ◽  
pp. ii135-ii136
Author(s):  
John Lin ◽  
Michelle Mai ◽  
Saba Paracha
Keyword(s):  
Machine Learning ◽  
Decision Support ◽  
Glioblastoma Multiforme ◽  
Random Forest ◽  
Regression Model ◽  
Clinical Decision Support ◽  
Multivariate Regression ◽  
Visual Analysis ◽  
Clinical Decision ◽  
Prognostic Models

Abstract Glioblastoma multiforme (GBM), the most common form of glioma, is a malignant tumor with a high risk of mortality. By providing accurate survival estimates, prognostic models have been identified as promising tools in clinical decision support. In this study, we produced and validated two machine learning-based models to predict survival time for GBM patients. Publicly available clinical and genomic data from The Cancer Genome Atlas (TCGA) and Broad Institute GDAC Firehouse were obtained through cBioPortal. Random forest and multivariate regression models were created to predict survival. Predictive accuracy was assessed and compared through mean absolute error (MAE) and root mean square error (RMSE) calculations. 619 GBM patients were included in the dataset. There were 381 (62.9%) cases of recurrence/progression and 53 (8.7%) cases of disease-free survival. The MAE and RMSE values were 0.553 and 0.887 years respectively for the random forest regression model, and they were 1.756 and 2.451 years respectively for the multivariate regression model. Both models accurately predicted overall survival. Comparison of models through MAE, RMSE, and visual analysis produced higher accuracy values for random forest than multivariate linear regression. Further investigation on feature selection and model optimization may improve predictive power. These findings suggest that using machine learning in GBM prognostic modeling will improve clinical decision support. *Co-first authors.

Sign in / Sign up

Export Citation Format

Share Document