Hybrid Bayesian Network-Based Modeling: COVID-19-Pneumonia Case

Derevitskii, Ilia V.; Mramorov, Nikita; Usoltsev, Simon Dmitrievich; Kovalchuk, Sergey V.

doi:10.3390/jpm12081325

Cited by 6 publications

(4 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The four parts of automatic data cleaning [ 53 ], automatic feature engineering [ 54 ], automatic hyperparameter optimization [ 55 ], and automatic pipeline assembly [ 55 , 56 ] provide a new strategy to further understand the performance of ML modeling algorithms in different environment and they analyze pipeline optimization and best practices. Recently, this method is used in various fields, such as neuroradiology [ 57 ], COVID-19 [ 58 ], biomedical big data [ 56 ]. We applied this complete ML method to distinguish SLE without LN from SLE with LN, and explored the potential risk factors for LN by combining serological and meteorological indexes.…”

Section: Discussionmentioning

confidence: 99%

Lupus nephritis or not? A simple and clinically friendly machine learning pipeline to help diagnosis of lupus nephritis

Wang

Wang³

et al. 2023

Inflamm. Res.

View full text Add to dashboard Cite

Objective Diagnosis of lupus nephritis (LN) is a complex process, which usually requires renal biopsy. We aim to establish a machine learning pipeline to help diagnosis of LN. Methods A cohort of 681 systemic lupus erythematosus (SLE) patients without LN and 786 SLE patients with LN was established, and a total of 95 clinical, laboratory data and 17 meteorological indicators were collected. After tenfold cross-validation, the patients were divided into training set and test set. The features selected by collective feature selection method of mutual information (MI) and multisurf were used to construct the models of logistic regression, decision tree, random forest, naive Bayes, support vector machine (SVM), light gradient boosting (LGB), extreme gradient boosting (XGB), and artificial neural network (ANN), the models were compared and verified in post-analysis. Results Collective feature selection method screens out antistreptolysin (ASO), retinol binding protein (RBP), lupus anticoagulant 1 (LA1), LA2, proteinuria and other features, and the hyperparameter optimized XGB (ROC: AUC = 0.995; PRC: AUC = 1.000, APS = 1.000; balance accuracy: 0.990) has the best performance, followed by LGB (ROC: AUC = 0.992; PRC: AUC = 0.997, APS = 0.977; balance accuracy: 0.957). The worst performance is naive Bayes model (ROC: AUC = 0.799; PRC: AUC = 0.822, APS = 0.823; balance accuracy: 0.693). In the composite feature importance bar plots, ASO, RF, Up/Ucr, and other features play important roles in LN. Conclusion We developed and validated a new and simple machine learning pathway for diagnosis of LN, especially the XGB model based on ASO, LA1, LA2, proteinuria, and other features screened out by collective feature selection. Supplementary Information The online version contains supplementary material available at 10.1007/s00011-023-01755-7.

show abstract

Section: Discussionmentioning

confidence: 99%

Lupus nephritis or not? A simple and clinically friendly machine learning pipeline to help diagnosis of lupus nephritis

Wang

Wang³

et al. 2023

Inflamm. Res.

View full text Add to dashboard Cite

show abstract

“…Finally, a BN-based approach to predict important clinical indicators to improve treatment for COVID-19-related pneumonia was developed by Derevitskii et al [69]. Using expert knowledge, the current clinical recommendations, previous research, and classic predictive metrics, the models were validated.…”

Section: Comprehensive Review Of Bayesian Network On Some Diseasesmentioning

confidence: 99%

Bayesian Networks for the Diagnosis and Prognosis of Diseases: A Scoping Review

Polotskaya,

Muñoz-Valencia,

Rabasa

et al. 2024

MAKE

View full text Add to dashboard Cite

Bayesian networks (BNs) are probabilistic graphical models that leverage Bayes’ theorem to portray dependencies and cause-and-effect relationships between variables. These networks have gained prominence in the field of health sciences, particularly in diagnostic processes, by allowing the integration of medical knowledge into models and addressing uncertainty in a probabilistic manner. Objectives: This review aims to provide an exhaustive overview of the current state of Bayesian networks in disease diagnosis and prognosis. Additionally, it seeks to introduce readers to the fundamental methodology of BNs, emphasising their versatility and applicability across varied medical domains. Employing a meticulous search strategy with MeSH descriptors in diverse scientific databases, we identified 190 relevant references. These were subjected to a rigorous analysis, resulting in the retention of 60 papers for in-depth review. The robustness of our approach minimised the risk of selection bias. Results: The selected studies encompass a wide range of medical areas, providing insights into the statistical methodology, implementation feasibility, and predictive accuracy of BNs, as evidenced by an average area under the curve (AUC) exceeding 75%. The comprehensive analysis underscores the adaptability and efficacy of Bayesian networks in diverse clinical scenarios. The majority of the examined studies demonstrate the potential of BNs as reliable adjuncts to clinical decision-making. The findings of this review affirm the role of Bayesian networks as accessible and versatile artificial intelligence tools in healthcare. They offer a viable solution to address complex medical challenges, facilitating timely and informed decision-making under conditions of uncertainty. The extensive exploration of Bayesian networks presented in this review highlights their significance and growing impact in the realm of disease diagnosis and prognosis. It underscores the need for further research and development to optimise their capabilities and broaden their applicability in addressing diverse and intricate healthcare challenges.

show abstract

“…Evrimsel bir yaklaşım kullanarak otomatik bir şekilde farklı gerçek dünya süreçleri için özel modelleme oluşturabilir. FEDOT, ikili ve çoklu sınıflandırma, regresyon, kümeleme ve zaman serisi tahmin görevlerini destekler [42].…”

Section: Fedot (Fedot)unclassified

Zaman serisi tahminlemede otomatikleştirilmiş makine öğrenmesi (AutoML) kütüphanelerinin karşılaştırılması

Akkurt,

Hasgül

2024

Gazi Üniversitesi Mühendislik Mimarlık Fakültesi Dergisi

View full text Add to dashboard Cite

Firmaların bulunduğu konumu koruması veya geliştirebilmesi, ileride meydana gelebilecek durumlara karşı önceden tedbir alabilmesi ve diğer firmalar ile rekabet edebilmesi açısından geleceğe yönelik tahminleme gerçekleştirmesi gereklidir. Gelişen veri teknolojileri ile anlamlı veriye ulaşabilmek kolaylaşmıştır ve yapay zekâ, makine öğrenmesi, derin öğrenme gibi yöntemlerle birlikte bu verilerin analiz edilmesiyle geleceğe yönelik tahminlemede oldukça başarılı sonuçlar elde edilebilmektedir. Ancak literatürde birçok farklı yöntemin bulunması, araştırmacıların hangi yöntemi kullanacağı, model ve hiper-parametre seçimi için hangi teknikleri kullanacağı gibi birçok problem oluşturabilmektedir. Model ve hiper-parametre seçimde farklı değerlerin karşılaştırılması zahmetli ve uzun süreli olabilir. Bu doğrultuda gerçekleştirilen çalışmanın amacı, makine öğrenmesinin gelişmiş bir versiyonu olan otomatikleştirilmiş makine öğrenmesi (AutoML) yöntemini kullanmaktır. AutoML, makine öğrenmesi modellerini otomatikleştirerek bu alanda uzmanlık gerektirmeden makine öğrenmesi algoritmalarının kullanımına ve geliştirilmesine olanak tanır. Çalışmada, tek değişkenli bir zaman serisi verisi üzerinde 6 farklı AutoML kütüphanesi ile tahminleme çalışması gerçekleştirilmiştir ve tahminleme başarıları çeşitli performans metrikleri üzerinden karşılaştırılmıştır. Kullanılan veri seti üzerinde elde edilen sonuçlara göre seçilen kütüphanelerden tahminleme başarısı en yüksek olanın Auto_ARIMA kütüphanesi olduğu gözlenmiştir.

show abstract

Hybrid Bayesian Network-Based Modeling: COVID-19-Pneumonia Case

Cited by 6 publications

References 44 publications

Lupus nephritis or not? A simple and clinically friendly machine learning pipeline to help diagnosis of lupus nephritis

Lupus nephritis or not? A simple and clinically friendly machine learning pipeline to help diagnosis of lupus nephritis

Bayesian Networks for the Diagnosis and Prognosis of Diseases: A Scoping Review

Zaman serisi tahminlemede otomatikleştirilmiş makine öğrenmesi (AutoML) kütüphanelerinin karşılaştırılması

Contact Info

Product

Resources

About