Bayesian statistical theory in the preoperative diagnosis of pulmonary lesions.

We used a computerized Bayesian algorithm to assist in the preoperative diagnosis of pulmonary lesions. One hundred consecutive patients who were undergoing exploratory thoracotomy for newly discovered pulmonary lesions were prospectively evaluated. The Bayesian model used a total of 44 preoperative clinical and roentgenographic factors to categorize the lesions as benign or malignant. The Bayesian algorithm correctly categorized 96 of the 100 lesions, thereby providing an accuracy of 96 percent. The sensitivity of the model was 98 percent and the specificity was 87 percent. All but two of the 85 malignant lesions were correctly categorized and 13 of the 15 benign lesions were correctly analyzed by the model. These results indicate that computer-assisted diagnosis using the Theorem of Bayes may provide valuable preoperative information for the management of selected patients.

[1]  Edwards Fh,et al.  Use of a Bayesian algorithm in the computer-assisted diagnosis of appendicitis. , 1984 .

[2]  de Dombal Ft,et al.  Computer based assistance for medical decision making. , 1984 .

[3]  S. Cummings,et al.  Estimating the probability of malignancy in solitary pulmonary nodules. A Bayesian approach. , 1986, The American review of respiratory disease.

[4]  F H Edwards,et al.  Use of a Bayesian algorithm in the computer-assisted diagnosis of appendicitis. , 1984, Surgery, gynecology & obstetrics.

[5]  W. Rogers,et al.  Computer-aided medical diagnosis: literature review. , 1979, International journal of bio-medical computing.

[6]  K. Rotte,et al.  Results of computer-aided diagnosis of peripheral bronchial carcinoma. , 1977, Radiology.

[7]  F H Edwards,et al.  The theorem of Bayes as a clinical research tool. , 1987, Surgery, gynecology & obstetrics.

[8]  A Wardle,et al.  Computer Aided Diagnosis – A Review of Research , 1978, Methods of Information in Medicine.

[9]  P. D. Wilson,et al.  Simplified computer-aided diagnosis of acute abdominal pain. , 1975, British medical journal.

[10]  J L Lehr,et al.  Solitary pulmonary lesions. Computer-aided differential diagnosis and evaluation of mathematical methods. , 1967, Radiology.

[11]  F T de Dombal,et al.  Computers and the surgeon--a matter of decision. , 1979, Surgery annual.

[12]  de Dombal Ft,et al.  Computers and the surgeon--a matter of decision. , 1979 .

[13]  E. Davis,et al.  The solitary pulmonary nodule. , 1964, The Medical annals of the District of Columbia.

[14]  Daniel Ww.  An introduction to computer-assisted diagnosis. , 1979 .

[15]  Edwards Fh,et al.  The theorem of Bayes as a clinical research tool. , 1987 .

[16]  D E Raeside.  Bayesian statistics: a guided tour. , 1976, Medical physics.