A machine learning evolutionary algorithm-based formula to assess tumor markers and predict lung cancer in cytologically negative pleural effusions

Malignant pleural effusion is diagnostically challenging in presence of negative cytology. The assessment of tumor markers in serum has become a standard tool in cancer diagnosis, while pleural fluid sampling has not met universal consensus. The evaluation of a panel of markers both in serum and pleural fluid may be crucial to improve the diagnostic accuracy. Using a machine learning-based approach, we provide a mathematical formula capable to express the complex relation existing among the expressed markers in serum and pleural effusion and the presence of lung cancer. The formula indicates CEA and CYFRA21-1 in pleural fluid as the best diagnostic markers, with 97% accuracy, 98% sensitivity, 95% specificity, 96% area under curve, 98% positive predictive value, and 92% MCC (Matthews correlation coefficient).

[1]  Mayank Sharma,et al.  Diagnostic utility of serum and pleural fluid carcinoembryonic antigen, and cytokeratin 19 fragments in patients with effusion from nonsmall cell lung cancer , 2015, Journal of carcinogenesis.

[2]  M. Metintaş,et al.  Diagnostic value of CEA, CA 15-3, CA 19-9, CYFRA 21-1, NSE and TSA assay in pleural effusions. , 2001, Lung cancer.

[3]  R. Light,et al.  The undiagnosed pleural effusion. , 2006, Clinics in chest medicine.

[4]  Luigi Glielmo,et al.  Spacecraft autonomy modeled via Markov decision process and associative rule-based machine learning , 2017, 2017 IEEE International Workshop on Metrology for AeroSpace (MetroAeroSpace).

[5]  L Antonangelo,et al.  Pleural fluid tumour markers in malignant pleural effusion with inconclusive cytologic results. , 2015, Current oncology.

[6]  R. Krenke,et al.  Diagnostic utility of pleural fluid and serum markers in differentiation between malignant and non-malignant pleural effusions , 2009, European journal of medical research.

[7]  Rahul Bhatnagar,et al.  Management of malignant pleural effusions. , 2020, Current opinion in pulmonary medicine.

[8]  J. Heffner,et al.  Recent advances in the diagnosis and management of malignant pleural effusions. , 2008, Mayo Clinic proceedings.

[9]  Anna Morley,et al.  Investigating unilateral pleural effusions: the role of cytology , 2018, European Respiratory Journal.

[10]  Gianni D'Angelo,et al.  A proposal for distinguishing between bacterial and viral meningitis using genetic programming and decision trees , 2019, Soft Computing.

[11]  Yanqiu Wu,et al.  Diagnostic value of tumor markers for lung adenocarcinoma-associated malignant pleural effusion: a validation study and meta-analysis , 2017, International Journal of Clinical Oncology.

[12]  Francesco Palmieri,et al.  Detecting unfair recommendations in trust-based pervasive environments , 2019, Inf. Sci..

[13]  S. Bielsa,et al.  Clinical impact and reliability of pleural fluid mesothelin in undiagnosed pleural effusions. , 2009, American journal of respiratory and critical care medicine.

[14]  Claudio Cortese,et al.  Tumor type M2-pyruvate-kinase levels in pleural fluid versus plasma in cancer patients: a further tool to define the need for invasive procedures. , 2008, European journal of cardio-thoracic surgery : official journal of the European Association for Cardio-thoracic Surgery.

[15]  Behrouz Shamsaei,et al.  Comparison of some machine learning and statistical algorithms for classification and prediction of human cancer type , 2016, 2016 IEEE-EMBS International Conference on Biomedical and Health Informatics (BHI).

[16]  Gianni D'Angelo,et al.  A NAT traversal mechanism for cloud video surveillance applications using WebSocket , 2018, Multimedia Tools and Applications.

[17]  R. Molina,et al.  Evaluation of two strategies for the interpretation of tumour markers in pleural effusions , 2017, Respiratory Research.

[18]  S J Mentzer,et al.  Malignant effusive disease of the pleura and pericardium. , 1997, Chest.

[19]  S. Neragi-Miandoab,et al.  Malignant pleural effusion, current and evolving approaches for its diagnosis and management. , 2006, Lung cancer.

[20]  David Shitrit,et al.  Diagnostic value of CYFRA 21-1, CEA, CA 19-9, CA 15-3, and CA 125 assays in pleural effusions: analysis of 116 cases and review of the literature. , 2005, The oncologist.

[21]  Maruf Pasha,et al.  Survey of Machine Learning Algorithms for Disease Diagnostic , 2017 .

[22]  Yuan Yang,et al.  Diagnostic Accuracy of Combinations of Tumor Markers for Malignant Pleural Effusion: An Updated Meta-Analysis , 2017, Respiration.

[23]  Gang Huang,et al.  Diagnostic utility of pleural fluid carcinoembryonic antigen and CYFRA 21‐1 in patients with pleural effusion: a systematic review and meta‐analysis , 2007, Journal of clinical laboratory analysis.

[24]  Gianni D'Angelo,et al.  Towards a HPC-oriented parallel implementation of a learning algorithm for bioinformatics applications , 2014, BMC Bioinformatics.

[25]  Nick A Maskell,et al.  Pleural biopsies in undiagnosed pleural effusions; Abrams vs image-guided vs thoracoscopic biopsies , 2016, Current opinion in pulmonary medicine.

[26]  Isaac Nuñez,et al.  Serum tumor markers CEA, CYFRA21-1, and CA-125 are associated with worse prognosis in advanced non-small-cell lung cancer (NSCLC). , 2011, Clinical lung cancer.

[27]  Ian H. Witten,et al.  Data mining: practical machine learning tools and techniques, 3rd Edition , 1999 .

[28]  Kirsten Simon,et al.  Carcinoembryonic antigen and cytokeratin-19 fragments for assessment of therapy response in non-small cell lung cancer: a systematic review and meta-analysis , 2017, British Journal of Cancer.

[29]  Dominic P. Searson.  GPTIPS 2: An Open-Source Software Platform for Symbolic Data Mining , 2014, Handbook of Genetic Programming Applications.

[30]  Georgia Hardavella,et al.  Does aggressive management of solitary pulmonary nodules pay off? , 2019, Breathe.

[31]  Kim-Kwang Raymond Choo,et al.  A smartphone-based wearable sensors for monitoring real-time physiological data , 2017, Comput. Electr. Eng..

[32]  Melanie Mitchell,et al.  An introduction to genetic algorithms , 1996 .

[33]  Yan Gu,et al.  The diagnostic value of parallel detection of cytokeratin 19 fragment-based tumor markers in malignant pleural effusion: a systematic review and metaanalysis , 2017 .

[34]  John R. Koza,et al.  Genetic programming as a means for programming computers by natural selection , 1994 .

[35]  Gianni D'Angelo,et al.  Toward a soft computing-based correlation between oxygen toxicity seizures and hyperoxic hyperpnea , 2018, Soft Comput..

[36]  Tomasz Dominik Gwiazda,et al.  Crossover for single-objective numerical optimization problems , 2006 .

[37]  Fang-Yie Leu,et al.  Healthcare-based on Cloud Electrocardiogram System: A Medical Center Experience in Middle Taiwan , 2018, Journal of Medical Systems.

[38]  Luc Boullart,et al.  Genetic programming: principles and applications , 2001 .

[39]  Francesco Palmieri,et al.  A data-driven approximate dynamic programming approach based on association rule learning: Spacecraft autonomy as a case study , 2019, Inf. Sci..

[40]  E. Duhig,et al.  Diagnostic molecular biomarkers for malignant pleural effusions. , 2011, Future oncology.

[41]  T. Hájek,et al.  Tumor markers in pleural effusions. , 2007, Anticancer research.