Mani S., Shankle W.R., Dick M.B., Pazzani M.J.: Two stage Machine Learning model for guideline development, , Artif Intell Med, 16 (1999) 51-71. Home/Search Document Details and Download
Summary Related Articles Check |
This paper is cited in the following contexts:
Mining Data From a Knowledge Management.. - Bellazzi, Azzini, .. (2001) (Correct)
....anced data set of 11 (10 survived and 1 died) new patients (100 accuracy) Such results were not obtained in our data set. Finally, it is important to note that the work carried on in this paper has similar goals of the one presented in [14] on the use of confirmation rules, and in the work in [15] on the use of two stage models for guidelines development. As a future work, we plan to extend our work on hepatocellular carcinoma prognosis, by resorting to the technique proposed in [16] for taking into account censored data. ....
Mani S., Shankle W.R., Dick M.B., Pazzani M.J.: Two stage Machine Learning model for guideline development, , Artif Intell Med, 16 (1999) 51-71.
Refinement of Neuro-psychological tests for.. - Mani, Dick.. Self-citation (Mani Dick Pazzani) (Correct)
....algorithms, experimental protocol and post processing of the output. See [11] for a detailed discussion on this. Some recent applications of these techniques in the medical domain include differential diagnosis of abdominal pain [12] screening and severity staging models for dementia [13] [14] and learning from a database of sports injuries [15] Using ML and KDD techniques, we are attempting to refine the CCNB with two explicit goals. First, we are interested in identifying a clinically usable subset of CASI (CASI SUBSET) whichwillsave time and cost retaining or improving the accuracy ....
....Hence they have the potential to be muchmore useful in clinical practice. The basic factors in model selection are its accuracy, comprehensibilityand stability, and in medical domains comprehensibility is particularly important. Wehave addressed these issues in further detail elsewhere [14]. Here wepresent some interesting properties of our models. In general CART models scored high on comprehensibility compared to C4.5 trees. They were smaller and had fewer domain constraint violations. 5.1 Highlights of our CASI MMSE M model Table 2 (last 3 columns) gives the accuracy, ....
Subramani Mani, William R. Shankle, Malcolm B. Dick, and Michael J. Pazzani. Two-Stage Machine Learning Model for Guideline Development. Artificial IntelligenceinMedicine, 1998. In Press.
Refinement of Neuro-psychological tests for.. - Mani, Dick.. Self-citation (Mani Dick Pazzani) (Correct)
No context found.
Subramani Mani, William R. Shankle, Malcolm B. Dick, and Michael J. Pazzani. Two-Stage Machine Learning Model for Guideline Development. Arti#cial IntelligenceinMedicine, 1998. In Press.
Guideline Generation from Data by Induction of Decision Tables .. - Mani, Pazzani (1998) (1 citation) Self-citation (Mani Pazzani) (Correct)
.... eliminate inter observer variability in applying the Alzheimer s Disease Cooperative Study Unit (ADCSU) criteria [10] for scoring the CDRS global and category scores, the ADRC clinicians spenttwoyears developing and validating a computerized scoring algorithm of the CDRS category and global scores [11] and these derived scores served as the gold standard for generating and evaluating our models. Component Architecture The various components incorporated in our architecture included the Train Test Partitioner, Discretizer, CPB Module, CAP module, HUGIN and the Classification module. Figure 2 ....
Subramani Mani, William R. Shankle, Malcolm B. Dick, and Michael J. Pazzani. TwoStage Machine Learning Model for Guideline Development. (In Press), 1998.
Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback
CiteSeer.IST - Copyright Penn State and NEC