Scopus İndeksli Açık & Kapalı Erişimli Yayınlar

Permanent URI for this communityhttps://hdl.handle.net/11727/10752

Browse

Filters

2020 - 20223

Settings

Subject: search.filters.subject.machine learning

Search Results

Now showing 1 - 3 of 3
  • No Thumbnail Available
    Item
    Searching For The Urine Osmolality Surrogate: An Automated Machine Learning Approach
    (2022) Topcu, Deniz Ilhan; Bayraktar, Nilufer; https://orcid.org/0000-0002-1219-6368; https://orcid.org/0000-0002-7886-3688; 000819864400001; E-3717-2019; Y-8758-2018
    Objectives Automated machine learning (AutoML) tools can help clinical laboratory professionals to develop machine learning models. The objective of this study was to develop a novel formula for the estimation of urine osmolality using an AutoML tool and to determine the efficiency of AutoML tools in a clinical laboratory setting. Methods Three hundred routine urinalysis samples were used for reference osmolality and urine clinical chemistry analysis. The H2O AutoML engine completed the machine learning development steps with minimum human intervention. Four feature groups were created, which include different urinalysis measurements according to the Boruta feature selection algorithm. Method comparison statistics including Spearman correlation, Passing-Bablok regression analysis were performed, and Bland Altman plots were created to compare model predictions with the reference method. The minimum allowable bias (24.17%) from biological variation data was used as the limit of agreement. Results The AutoML engine developed a total of 183 ML models. Conductivity and specific gravity had the highest variable importance. Models that include conductivity, specific gravity, and other urinalysis parameters had the highest R-2 (0.70-0.83), and 70-84% of results were within the limit of agreement. Conclusions Combining urinary conductivity with other urinalysis parameters using validated machine learning models can yield a promising surrogate. Additionally, AutoML tools facilitate the machine learning development cycle and should be considered for developing ML models in clinical laboratories.
  • No Thumbnail Available
    Item
    Estimation of Low-Density Lipoprotein Cholesterol Concentration Using Machine Learning
    (2021) Cubukcu, Hikmet Can; Topcu, Deniz İlhan; 0000-0002-1219-6368; 34635916; E-3717-2019
    Objective Low-density lipoprotein cholesterol (LDL-C) can be estimated using the Friedewald and Martin-Hopkins formulas. We developed LDL-C prediction models using multiple machine learning methods and investigated the validity of the new models along with the former formulas. Methods Laboratory data (n = 59,415) on measured LDL-C, high-density lipoprotein cholesterol, triglycerides (TG), and total cholesterol were partitioned into training and test data sets. Linear regression, gradient-boosted trees, and artificial neural network (ANN) models were formed based on the training data. Paired-group comparisons were performed using a t-test and the Wilcoxon signed-rank test. We considered P values .2 to be statistically significant. Results For TG >= 177 mg/dL, the Friedewald formula underestimated and the Martin-Hopkins formula overestimated the LDL-C (P <.001), which was more significant for LDL-C <70 mg/dL. The linear regression, gradient-boosted trees, and ANN models outperformed the aforementioned formulas for TG >= 177 mg/dL and LDL-C <70 mg/dL based on a comparison with a homogeneous assay (P >.001 vs. P <.001) and classification accuracy. Conclusion Linear regression, gradient-boosted trees, and ANN models offer more accurate alternatives to the aforementioned formulas, especially for TG 177 to 399 mg/dL and LDL-C <70 mg/dL.
  • No Thumbnail Available
    Item
    Predicting Infections Using Computational Intelligence - A Systematic Review
    (2020) Baldominos, Alejandro; Puello, Adrian; Ogul, Hasan; Asuroglu, Tunc; Colomo-Palacios, Ricardo; 0000-0003-4153-0764
    Infections encompass a set of medical conditions of very diverse kinds that can pose a significant risk to health, and even death. As with many other diseases, early diagnosis can help to provide patients with proper care to minimize the damage produced by the disease, or to isolate them to avoid the risk of spread. In this context, computational intelligence can be useful to predict the risk of infection in patients, raising early alarms that can aid medical teams to respond as quick as possible. In this paper, we survey the state of the art on infection prediction using computer science by means of a systematic literature review. The objective is to find papers where computational intelligence is used to predict infections in patients using physiological data as features. We have posed one major research question along with nine specific subquestions. The whole review process is thoroughly described, and eight databases are considered which index most of the literature published in different scholarly formats. A total of 101 relevant documents have been found in the period comprised between 2003 and 2019, and a detailed study of these documents is carried out to classify the works and answer the research questions posed, resulting to our best knowledge in the most comprehensive study of its kind. We conclude that the most widely addressed infection is by far sepsis, followed by Clostridium difficile infection and surgical site infections. Most works use machine learning techniques, from which logistic regression, support vector machines, random forest and naive Bayes are the most common. Some machine learning works provide some ideas on the problems of small data and class imbalance, which can be of interest. The current systematic literature review shows that automatic diagnosis of infectious diseases using computational intelligence is well documented in the medical literature.