Prediction of Morbidity After Lung Resection in Patients with Lung Cancer Using Fuzzy Logic[1]

Abstract

Background: Preoperative evaluation of patients with potentially resectable non-small cell lung cancer aims to estimate the risk of planned surgery. Evidence of several factors that identify patients at risk for complications from thoracotomy is controversial. The aim of this study was to introduce and implement in medical practice a fuzzy system used in risk assessment of pulmonary resection for lung cancer. Methods: Ninety-one consecutive patients who underwent pulmonary resection for lung cancer were investigated. The overall complication rate was 39.6 % (a total of 63 complications were seen in 36 patients). A fuzzy logic model was created with 9 input (presence of chest pain, weight loss, clinical T stage of the tumor, FEV₁, serum protein, preoperative arterial partial oxygen pressure and cigarette smoking, erythrocyte sedimentation rate and peripheral blood leukocyte count) and two output classes (high-risk and low-risk groups). The fuzzy classifier's performance was tested. Results: The model was able to predict correctly the occurrence of complications in 22 out of 29 patients in the high-risk group with a sensitivity of 76 %, while 9 out of the 52 patients from the low-risk group developed complications (17 %). Conclusion: The fuzzy classification system provides an accurate tool to predict complications of resections in patients with non-small cell lung cancer.

Key words

Lung cancer - surgical resection - complication - morbidity - fuzzy logic

1 Presented at the 10th Annual Meeting of the European Society of Thoracic Surgeons, Istanbul, Turkey, October 26 - 28, 2002

References

• 1 Flehinger B J, Kimmel M, Melamad M R. The effect of surgical treatment on survival in early lung cancer: implications for screening.  Chest. 1992;  101 1013-1018
• 2 Nagasaki F, Flehinger B J, Martini N. Complications of surgery in the treatment of carcinoma of the lung.  Chest. 1982;  82 25-29
• 3 Gaensler E A, Cugell D W, Lindgren I. et al . The role of pulmonary insufficiency in mortality and invalidism following surgery for pulmonary tuberculosis.  J Thorac Surg. 1955;  29 163-187
• 4 Didolkar M S, Moore R H, Takita H. Evaluation of the risk of pulmonary resection for bronchogenic carcinoma.  Am J Surg. 1974;  127 700-703
• 5 Bagg L R. The 12-min walking distance: its use in the preoperative assessment of patients with bronchial carcinoma before lung resection.  Respiration. 1984;  46 342-345
• 6 Motta G, Ratto G B. Complications of surgery in the treatment of lung cancer: their relationship with the extent of resection and preoperative respiratory function tests.  Acta Chir Belg. 1989;  89 161-165
• 7 Pate P, Tenholder M F, Griffin J P. et al . Preoperative assessment of the high-risk patient for lung resection.  Ann Thorac Surg. 1996;  61 1494-1500
• 8 Prause G, Offner A. Ratzenhofer-Komenda B et al. Comparison of two preoperative indices to predict perioperative mortality in non-cardiac thoracic surgery.  Eur J Cardiothorac Surg. 1997;  11 670-675
• 9 Boysen P G, Clark C A, Block A J. Graded exercise testing and post thoracotomy complications.  J Cardiovasc Anesth. 1990;  4 68-72
• 10 Dales R E, Dionne G, Leech J A. et al . Preoperative prediction of pulmonary complications following thoracic surgery.  Chest. 1993;  104 155-159
• 11 Zadeth L A. Fuzzy sets.  Inf Control. 1965;  8 338-353
• 12 Kory R G, Callahan R, Boren H G. et al . Clinical spirometry in normal man.  Am Med. 1961;  30 243-258
• 13 Mountain C F. Revisions in the international system for staging lung cancer.  Chest. 1997;  111 1710-1717
• 14 Bellazi R, Ironi L, Guglielmann R. et al . Qualitative models and fuzzy systems: an integrated approach for learning from data.  Artif Intell Med. 1998;  14 5-28
• 15 Yager R R, Filev D P. Essentials of Fuzzy Modeling and Control. New York; Wiley-Interscience 1994
• 16 Bortz J. Lehrbuch der empirischen Forschung. Heidelberg; Springer Verlag 1984
• 17 Ginsberg R J, Hill L D, Eagan R T. et al . Modern thirty-day operative mortality for surgical resections in lung cancer.  J Thorac Cardiovasc Surg. 1983;  86 654-658
• 18 Epstein S K, Faling L J, Daly B DT. et al . Predicting complications after pulmonary resection. Preoperative exercise testing vs. a multifactorial cardiopulmonary risk index.  Chest. 1993;  104 694-700
• 19 Keagy B A, Schorlemmer G R, Murray G F. et al . Correlation of preoperative pulmonary function testing with clinical course in patients after pneumonectomy.  Ann Thorac Surg. 1986;  91 551-554
• 20 Boushy S F, Billig D M, North L B. et al . Clinical course related to preoperative and postoperative pulmonary function in patients with bronchogenic carcinoma.  Chest. 1971;  59 383-391
• 21 Kuncheva L I, Steimann. Fuzzy diagnosis.  Artif Intell Med. 1999;  16 121-128
• 22 Beckles M A, Spiro S G, Colice G L. et al . The physiologic evaluation of patients with lung cancer being considered for resectional surgery.  Chest. 2003;  123 105S-114S
• 23 Nemoto T, Hatzakis G E, Thorpe C W. et al . Automatic control of pressure support mechanical ventilation using fuzzy logic.  Am J Respir Crit Care Med. 1999;  160 550-556
• 24 Keller T, Bitterlich N, Hilfenhaus S. et al . Tumour markers in the diagnosis of bronchial carcinoma: new options using fuzzy logic-based tumour marker profiles.  J Cancer Res Clin Oncol. 1998;  124 565-574
• 25 Schneider J, Bitterlich N, Velcovsky H G. et al . Fuzzy logic-based tumor-marker profiles improved sensitivity in the diagnosis of lung cancer.  Int J Clin Oncol. 2002;  7 145-151

1 Presented at the 10th Annual Meeting of the European Society of Thoracic Surgeons, Istanbul, Turkey, October 26 - 28, 2002