Use of Artificial Neural Networks in the Prediction of Kidney Transplant Outcomes

Fariba Shadabi, Robert Cox, Dharmendra Sharma

    Research output: A Conference proceeding or a Chapter in BookConference contribution

    Abstract

    Traditionally researchers have used statistical methods to predict medical outcomes. However, statistical techniques do not provide sufficient in-formation for solving problems of high complexity. Recently more attention has turned to a variety of artificial intelligence modeling techniques such as Artificial Neural Networks (ANNs), Case Based Reasoning (CBR) and Rule Induction (RI). In this study we sought to use ANN to predict renal transplantation outcomes. Our results showed that although this was possible, the positive predictive power of the trained ANN was low, indicating a need for improvement if this approach is to be useful clinically. We also highlight potential problems that may arise when using incomplete clinical datasets for ANN train-ing including the danger of pre-processing data in such a way that misleading high predictive value is obtained
    Original languageEnglish
    Title of host publicationInternational Conference on Knowledge-Based and Intelligent Information and Engineering Systems KES 2004
    EditorsFariba Shdabi, Dharmendra Sharma, Nikolai Petrovsky
    Place of PublicationGermany
    PublisherSpringer
    Pages566-572
    Number of pages7
    ISBN (Print)9783540232056
    DOIs
    Publication statusPublished - 2004
    EventKnowledge-Based Intelligent Information and Engineering Systems - Wellington, New Zealand
    Duration: 22 Sep 200424 Sep 2004

    Conference

    ConferenceKnowledge-Based Intelligent Information and Engineering Systems
    CountryNew Zealand
    CityWellington
    Period22/09/0424/09/04

    Fingerprint

    Transplants
    Neural networks
    Case based reasoning
    Artificial intelligence
    Statistical methods

    Cite this

    Shadabi, F., Cox, R., & Sharma, D. (2004). Use of Artificial Neural Networks in the Prediction of Kidney Transplant Outcomes. In F. Shdabi, D. Sharma, & N. Petrovsky (Eds.), International Conference on Knowledge-Based and Intelligent Information and Engineering Systems KES 2004 (pp. 566-572). Germany: Springer. https://doi.org/10.1007/978-3-540-30134-9_76
    Shadabi, Fariba ; Cox, Robert ; Sharma, Dharmendra. / Use of Artificial Neural Networks in the Prediction of Kidney Transplant Outcomes. International Conference on Knowledge-Based and Intelligent Information and Engineering Systems KES 2004. editor / Fariba Shdabi ; Dharmendra Sharma ; Nikolai Petrovsky. Germany : Springer, 2004. pp. 566-572
    @inproceedings{c5bea211606b4959ac746b002f87b06e,
    title = "Use of Artificial Neural Networks in the Prediction of Kidney Transplant Outcomes",
    abstract = "Traditionally researchers have used statistical methods to predict medical outcomes. However, statistical techniques do not provide sufficient in-formation for solving problems of high complexity. Recently more attention has turned to a variety of artificial intelligence modeling techniques such as Artificial Neural Networks (ANNs), Case Based Reasoning (CBR) and Rule Induction (RI). In this study we sought to use ANN to predict renal transplantation outcomes. Our results showed that although this was possible, the positive predictive power of the trained ANN was low, indicating a need for improvement if this approach is to be useful clinically. We also highlight potential problems that may arise when using incomplete clinical datasets for ANN train-ing including the danger of pre-processing data in such a way that misleading high predictive value is obtained",
    author = "Fariba Shadabi and Robert Cox and Dharmendra Sharma",
    year = "2004",
    doi = "10.1007/978-3-540-30134-9_76",
    language = "English",
    isbn = "9783540232056",
    pages = "566--572",
    editor = "Fariba Shdabi and Dharmendra Sharma and Nikolai Petrovsky",
    booktitle = "International Conference on Knowledge-Based and Intelligent Information and Engineering Systems KES 2004",
    publisher = "Springer",
    address = "Netherlands",

    }

    Shadabi, F, Cox, R & Sharma, D 2004, Use of Artificial Neural Networks in the Prediction of Kidney Transplant Outcomes. in F Shdabi, D Sharma & N Petrovsky (eds), International Conference on Knowledge-Based and Intelligent Information and Engineering Systems KES 2004. Springer, Germany, pp. 566-572, Knowledge-Based Intelligent Information and Engineering Systems, Wellington, New Zealand, 22/09/04. https://doi.org/10.1007/978-3-540-30134-9_76

    Use of Artificial Neural Networks in the Prediction of Kidney Transplant Outcomes. / Shadabi, Fariba; Cox, Robert; Sharma, Dharmendra.

    International Conference on Knowledge-Based and Intelligent Information and Engineering Systems KES 2004. ed. / Fariba Shdabi; Dharmendra Sharma; Nikolai Petrovsky. Germany : Springer, 2004. p. 566-572.

    Research output: A Conference proceeding or a Chapter in BookConference contribution

    TY - GEN

    T1 - Use of Artificial Neural Networks in the Prediction of Kidney Transplant Outcomes

    AU - Shadabi, Fariba

    AU - Cox, Robert

    AU - Sharma, Dharmendra

    PY - 2004

    Y1 - 2004

    N2 - Traditionally researchers have used statistical methods to predict medical outcomes. However, statistical techniques do not provide sufficient in-formation for solving problems of high complexity. Recently more attention has turned to a variety of artificial intelligence modeling techniques such as Artificial Neural Networks (ANNs), Case Based Reasoning (CBR) and Rule Induction (RI). In this study we sought to use ANN to predict renal transplantation outcomes. Our results showed that although this was possible, the positive predictive power of the trained ANN was low, indicating a need for improvement if this approach is to be useful clinically. We also highlight potential problems that may arise when using incomplete clinical datasets for ANN train-ing including the danger of pre-processing data in such a way that misleading high predictive value is obtained

    AB - Traditionally researchers have used statistical methods to predict medical outcomes. However, statistical techniques do not provide sufficient in-formation for solving problems of high complexity. Recently more attention has turned to a variety of artificial intelligence modeling techniques such as Artificial Neural Networks (ANNs), Case Based Reasoning (CBR) and Rule Induction (RI). In this study we sought to use ANN to predict renal transplantation outcomes. Our results showed that although this was possible, the positive predictive power of the trained ANN was low, indicating a need for improvement if this approach is to be useful clinically. We also highlight potential problems that may arise when using incomplete clinical datasets for ANN train-ing including the danger of pre-processing data in such a way that misleading high predictive value is obtained

    U2 - 10.1007/978-3-540-30134-9_76

    DO - 10.1007/978-3-540-30134-9_76

    M3 - Conference contribution

    SN - 9783540232056

    SP - 566

    EP - 572

    BT - International Conference on Knowledge-Based and Intelligent Information and Engineering Systems KES 2004

    A2 - Shdabi, Fariba

    A2 - Sharma, Dharmendra

    A2 - Petrovsky, Nikolai

    PB - Springer

    CY - Germany

    ER -

    Shadabi F, Cox R, Sharma D. Use of Artificial Neural Networks in the Prediction of Kidney Transplant Outcomes. In Shdabi F, Sharma D, Petrovsky N, editors, International Conference on Knowledge-Based and Intelligent Information and Engineering Systems KES 2004. Germany: Springer. 2004. p. 566-572 https://doi.org/10.1007/978-3-540-30134-9_76