ARTIFICIAL INTELLIGENCE, SYSTEM ANALYSIS AND ARTIFICIAL INTELLIGENCE, SYSTEM ANALYSIS AND SIMULATION MODELING IN OPTIMIZATION OF TREATMENT SIMULATION MODELING IN OPTIMIZATION OF TREATMENT FOR ESOPHAGOGASTRIC CANCER PATIENTS FOR ESOPHAGOGASTRIC CANCER PATIENTS Oleg Kshivets, MD, PhD Oleg Kshivets, MD, PhD Department of Surgery, Siauliai Public Hospital Department of Surgery, Siauliai Public Hospital & & Cancer Center, Siauliai, Lithuania Cancer Center, Siauliai, Lithuania The 2006 Gastrointestinal Cancers Simposium, The 2006 Gastrointestinal Cancers Simposium, January 26-28, 2006, San Francisco, CA, the USA January 26-28, 2006, San Francisco, CA, the USA
This document is posted to help you gain knowledge. Please leave a comment to let me know what you think about it! Share it to your friends and learn new things together.
Transcript
ARTIFICIAL INTELLIGENCE, SYSTEM ANALYSIS AND ARTIFICIAL INTELLIGENCE, SYSTEM ANALYSIS AND SIMULATION MODELING IN OPTIMIZATION OF SIMULATION MODELING IN OPTIMIZATION OF
TREATMENT FOR ESOPHAGOGASTRIC CANCER PATIENTSTREATMENT FOR ESOPHAGOGASTRIC CANCER PATIENTS
Oleg Kshivets, MD, PhD Oleg Kshivets, MD, PhD Department of Surgery, Siauliai Public Hospital & Department of Surgery, Siauliai Public Hospital &
Cancer Center, Siauliai, LithuaniaCancer Center, Siauliai, LithuaniaThe 2006 Gastrointestinal Cancers Simposium, The 2006 Gastrointestinal Cancers Simposium,
January 26-28, 2006, San Francisco, CA, the USAJanuary 26-28, 2006, San Francisco, CA, the USA
AbstractAbstract
ARTFICIAL INTELLIGENCE, SYSTEM ANALYSIS AND SIMULATION MODELING IN OPTIMIZATION OF TREATMENT FOR ESOPHAGOGASTRIC
CANCER PATIENTSOleg Kshivets Department of Surgery, Siauliai Public Hospital & Cancer Center,
Siauliai, Lithuania • OBJECTIVE: The search of optimal treatment plan for esophagogastric cancer (EGC) patients (EGCP) with stage T1-4N1-3M0 was
realized. We examined the clinicomorphologic factors associated with the low- and high-risk of generalization of EGCP after complete en block (R0) esophagogastrectomies (EG) through left and right thoracoabdominal incision.METHODS: We analyzed data of 187 consecutive EGCP (age=55.7±8.8 years; tumor size=6.8±3.3 cm) radically operated and monitored in 1975-2005 (males=138, females=49; EG Ivor-Lewis=60, EG Garlock=127; combined EG with resection of pancreas, liver, diaphragm, colon transversum, splenectomies=74; lymphadenectomy D2=80, D3=107; adenocarcinoma=109, squamos=68, mix=10; T1=27, T2=43, T3=67, T4=50; N0=75, N1=24, N2=85; N3=3; G1=54, G2=41, G3=92; only surgery-S=154, adjuvant chemoimmunotherapy-AT=33: 5-FU + thymalin/taktivin). Variables selected for 5-year survival (5YS) study were input levels of 45 blood parameters, sex, age, TNMG, cell type, tumor size. Survival curves were estimated by the Kaplan-Meier method. Differences in curves between groups of CECP were evaluated using a log-rank test. Multivariate Cox modeling, multi-factor clustering, discriminant analysis, structural equation modeling, Monte Carlo, bootstrap simulation and neural networks computing were used to determine any significant dependence.RESULTS: General cumulative 5YS was 34.9%, 10-year survival – 26.1%. 72 EGCP (38.5%) were alive, 39 EGCP (life span: LS=3699.7±1617.6 days) lived more than 5 years without any features of CEC progressing. LS for AT was 2255.9±211.7 days, for S – 1324.8±1550.4 days (P=0.032, by log-rank test P=0.036). Cox modeling displayed that 5YS of EGCP (n=187) after complete EG significantly depended on: combined procedures, age, blood cell subpopulations, cell ratio factors, lymphoid infiltration of EGC, T (P=0.000-0.029). Neural networks computing, genetic algorithm selection and bootstrap simulation revealed relationships between 5YS of EGCP and combined procedures (rank=1), lymphoid infiltration of EGC (2), EGC growth (3), T1-4 (4), histology (5), G1-3 (6), N0-3 (7), procedure type (8), gender (9), Rh-factor (10), blood coagulation time (11), blood lymphocytes (12), protein (13), neutrophils (14), age (15), blood leucocytes (16), tumor size (17), ESS (18), blood chlorides (19), prothrombin index (20). Correct prediction of EGCP survival after radical procedures was 91.7% by logistic regression (odds ratio=98.8), 92.4% by discriminant analysis and 100% by neural networks computing (area under ROC curve=1.0; error=0.0018).CONCLUSIONS: Optimal treatment strategies for EGCP are: 1) screening and early detection of EGC; 2) aggressive en block
surgery for completeness; 3) precise prediction; 4) AT for EGCP with unfavorable prognosis.
Factors:• 1) Antropometric Factors…………..4• 2) Blood Analysis…………………..26• 3) Hemostasis Factors……………....3• 4) Cell Ratio Factors………………...9 • 6) Esophagogastric Cancer
Survival:Survival:• Alive………..……………….….72 (38.5%)• 5-Year Survivors…………..…..39 (20.9%) • 10-Year Survivors……………...18 (9.6%)• Losses from Cancer………….115 (61.5%)• General Life Span=1276.1±108.3 days• Life Span of 5-Year Survivors=3699.7±1617.6 days• Life Span after Surgery=1324.8±1550.4 days• Life Span after Ad.CHIT=2255.9211.7±211.7 days• Cumulative 5-Year survival=34.9%• Cumulative 10-Year survival=26.1%
General Esopagogastric Cancer Patients SurvivalGeneral Esopagogastric Cancer Patients Survival after Complete after Complete Ivor-Lewis & Garlock Esophagogastrectomies (Kaplan-Meier) Ivor-Lewis & Garlock Esophagogastrectomies (Kaplan-Meier)
((n=187n=187))Survival Function
Complete CensoredGeneral Survival of Esophagogastric Cancer Patients
after Complete Ivor-Lewis & Garlock Esophagogastrectomies, n=1875-year Survival=34.9%; 10-Years Survival=26.1%;
Survival Time
Cum
ulat
ive
Prop
ortio
n Su
rviv
ing
0.1
0.2
0.3
0.4
0.5
0.6
0.7
0.8
0.9
1.0
0 5 10 15 20 25
Results of Univariate Analysis in Prediction of Esopagogastric Results of Univariate Analysis in Prediction of Esopagogastric Cancer Patients SurvivalCancer Patients Survival ( (n=187n=187))
Survival of Esophagogastric Cancer Patients after EsophagogastrectomiesP=0.016 by log-rank test, n=187
Years
Cum
ulat
ive
Prop
ortio
n Su
rviv
ing
0.1
0.2
0.3
0.4
0.5
0.6
0.7
0.8
0.9
1.0
0 5 10 15 20 25
only surgery, n=154 adjuvant chemoimmunotherapy, n=33
Results of Cox Regression Modeling in Prediction of Esophagogastric Cancer Results of Cox Regression Modeling in Prediction of Esophagogastric Cancer Patients Survival after Complete Esophagogastrectomies (n=187Patients Survival after Complete Esophagogastrectomies (n=187))
• Factors Wald df P Exp(B) 95%CI for Exp(B)Lower Upper
Results of Cox Regression Modeling in Prediction of Esophagogastric Cancer Results of Cox Regression Modeling in Prediction of Esophagogastric Cancer Patients Survival after Complete Esophagogastrectomies (n=187Patients Survival after Complete Esophagogastrectomies (n=187))
• Factors Wald df P Exp(B) 95%CI for Exp(B)Lower Upper
Results of Cox Regression Modeling in Prediction of Esophagogastric Cancer Results of Cox Regression Modeling in Prediction of Esophagogastric Cancer Patients Survival after Complete Esophagogastrectomies (n=187Patients Survival after Complete Esophagogastrectomies (n=187))
• Factors Wald df P Exp(B) 95%CI for Exp(B) LowerUpper
Results of Cox Regression Modeling in Prediction of Esophagogastric Cancer Results of Cox Regression Modeling in Prediction of Esophagogastric Cancer Patients Survival after Complete Esophagogastrectomies (n=187Patients Survival after Complete Esophagogastrectomies (n=187))
• Factors Wald df P Exp(B) 95%CI for Exp(B) LowerUpper
Results of Cox Regression Modeling in Prediction of Esophagogastric Cancer Results of Cox Regression Modeling in Prediction of Esophagogastric Cancer Patients Survival after Complete Esophagogastrectomies (n=187Patients Survival after Complete Esophagogastrectomies (n=187))
• Factors Wald df P Exp(B) 95%CI for Exp(B) LowerUpper
Ratio Lymphocytes to Cancer Cells Populations in Prediction 5-Year Survival of Esophagogastric Cancer Patients after Complete Esophagogastrectomies
(n=145)
Holling-Tenner Models of Esophagogastric Holling-Tenner Models of Esophagogastric Cancer Cell Population and Cytotoxic Cell Cancer Cell Population and Cytotoxic Cell
Population DynamicsPopulation Dynamics
0 2 4 6 8 10
0.1
10
Early CancerInvasive Cancer, Stage IIInvasive Cancer, Stage IIIGeneralization
Model "Early Cancer---Lymphocytes"
Gastroesophageal Cancer Cell Population
Lym
phoc
yte
Popu
latio
n
5
0.381
X1 3
X2 3
X3 3
X4 3
100.09 X1 2 X2 2
X3 2 X4 2
0 50 100 150 200 250
0.01
0.1
10
LymphocytesCancer Cells
Model "Early Cancer---Lymphocytes"
Time
Gas
tr.es
oph.
Cel
l Pop
ulat
ion
Dyn
amic
s
5
0.09
X1 2
X1 3
2000 X1 1
Esophagogastric Cancer Dynamics
Conclusions:Conclusions:• Optimal treatment strategies for esophagogastric
cancer patients are: • 1) screening and early detection of
esophagogastric cancer; • 2) aggressive en block surgery for completeness;
3) precise prediction;
• 4) adjuvant chemioimmunotherapy for esophagogastric cancer patients with unfavorable
prognosis.
• Oleg Kshivets, M.D., Ph.D. Consultant Thoracic/Abdominal/General Surgeon & Surgical Oncologist, Department of Surgery, Siauliai Public Hospital &
Cancer Center, Tilzes:42-16, LT78206 Siauliai, Lithuania• Tel. (37041)416614; Fax 1(270)9687098