Artificial Neural Network Approach in Laboratory Test Reporting:  Learning Algorithms.

OBJECTIVES In the field of laboratory medicine, minimizing errors and establishing standardization is only possible by predefined processes. The aim of this study was to build an experimental decision algorithm model open to improvement that would efficiently and rapidly evaluate the results of biochemical tests with critical values by evaluating multiple factors concurrently. METHODS The experimental model was built by Weka software (Weka, Waikato, New Zealand) based on the artificial neural network method. Data were received from Dokuz Eylül University Central Laboratory. "Training sets" were developed for our experimental model to teach the evaluation criteria. After training the system, "test sets" developed for different conditions were used to statistically assess the validity of the model. RESULTS After developing the decision algorithm with three iterations of training, no result was verified that was refused by the laboratory specialist. The sensitivity of the model was 91% and specificity was 100%. The estimated κ score was 0.950. CONCLUSIONS This is the first study based on an artificial neural network to build an experimental assessment and decision algorithm model. By integrating our trained algorithm model into a laboratory information system, it may be possible to reduce employees' workload without compromising patient safety.

[1]  Matthew D. Krasowski,et al.  Autoverification in a core clinical chemistry laboratory at an academic medical center , 2014, Journal of pathology informatics.

[2]  Jay B Jones,et al.  A strategic informatics approach to autoverification. , 2013, Clinics in laboratory medicine.

[3]  J. Niland,et al.  Improving patient safety via automated laboratory-based adverse event grading , 2011, J. Am. Medical Informatics Assoc..

[4]  N. Tien,et al.  Building and Validating an Autoverification System in the Clinical Chemistry Laboratory , 2011 .

[5]  Rhona J. Souers,et al.  Critical values comparison: a College of American Pathologists Q-Probes survey of 163 clinical laboratories. , 2007, Archives of pathology & laboratory medicine.

[6]  A. Wu.  Tietz clinical guide to laboratory tests. , 2006 .

[7]  Sandra Meneghelli,et al.  The DNSev™ expert system in the auto-verification of tumour markers and hormones results , 2006 .

[8]  Anand S Dighe,et al.  Analysis of laboratory critical value reporting at a large academic medical center. , 2006, American journal of clinical pathology.

[9]  Narayan Torke,et al.  Process improvement and operational efficiency through test result autoverification. , 2005, Clinical chemistry.

[10]  Lorne L Holland,et al.  Reducing laboratory turnaround time outliers can reduce emergency department patient length of stay: an 11-hospital study. , 2005, American journal of clinical pathology.

[11]  Callum G. Fraser,et al.  Biological variation data are necessary prerequisites for objective autoverification of clinical laboratory data , 2002 .

[12]  Lucila Ohno-Machado,et al.  Logistic regression and artificial neural network classification models: a methodology review , 2002, J. Biomed. Informatics.

[13]  D. Lobo,et al.  Dilution and redistribution effects of rapid 2-litre infusions of 0.9% (w/v) saline and 5% (w/v) dextrose on haematological parameters and serum biochemistry in normal subjects: a double-blind crossover study. , 2001, Clinical science.

[14]  M. Ringnér,et al.  Classification and diagnostic prediction of cancers using gene expression profiling and artificial neural networks , 2001, Nature Medicine.

[15]  W. Oosterhuis,et al.  Evaluation of LabRespond, a new automated validation system for clinical laboratory test results. , 2000, Clinical chemistry.

[16]  Silas Franco dos Reis Alves,et al.  Artificial Neural Networks , 2017, Encyclopedia of Machine Learning and Data Mining.

[17]  S. Wellstood.  Diagnostic Mycobacteriology: Current Challenges and Technologies , 1993 .

[18]  J. Ross Quinlan,et al.  C4.5: Programs for Machine Learning , 1992 .

[19]  Geoffrey E. Hinton,et al.  Learning representations by back-propagating errors , 1986, Nature.

[20]  J. R. Landis,et al.  The measurement of observer agreement for categorical data. , 1977, Biometrics.

[21]  N. de Jonge,et al.  Automated processing of serum indices used for interference detection by the laboratory information system. , 2005, Clinical chemistry.

[22]  David J. C. MacKay,et al.  Information Theory, Inference, and Learning Algorithms , 2004, IEEE Transactions on Information Theory.

[23]  P. J. Lisboa,et al.  Invited Article , 2001 .

[24]  W. Guder,et al.  The Haemolytic, Icteric and Lipemic Sample Recommendations Regarding their Recognition and Prevention of Clinically Relevant Interferences. Recommendations of the Working Group on Preanalytical Variables of the German Society for Clinical Chemistry and the German Society for Laboratory Medicine , 2000 .

[25]  J. Corberand,et al.  The Performance of the Knowledge-Based System VALAB Revisited: An Evaluation after Five Years , 1996, European journal of clinical chemistry and clinical biochemistry : journal of the Forum of European Clinical Chemistry Societies.

[26]  P M Valdiguié,et al.  VALAB: expert system for validation of biochemical data. , 1992, Clinical chemistry.