5-year survival of ECP after radical procedures significantly depended on: 1) PT “early-invasive cancer”; 2) PT N0--N12; 3) Cell Ratio Factors; 4) blood cell circuit; 5) biochemical factors; 6) hemostasis system; 7) AT; 8) EC cell dynamics; 9) EC characteristics; 10) tumor localization; 11) anthropometric data; 12) surgery type. Optimal diagnosis and treatment strategies for EC are: 1) screening and early detection of EC; 2) availability of experienced thoracoabdominal surgeons because of complexity of radical procedures; 3) aggressive en block surgery and adequate lymph node dissection for completeness; 4) precise prediction; 5) adjuvant chemoimmunoradiotherapy for ECP with unfavorable prognosis.

1. Esophageal Cancer: Artificial Intelligence,
Synergetics, Complex System Analysis,
Statistics and Modeling for Optimal
Management.
Kshivets Oleg Surgery Department, Bagrationovsk Hospital,
Bagrationovsk, Kaliningrad, Russia

2. ABSTRACT
OBJECTIVE: 5-survival (5YS) and life span after radical surgery for esophageal cancer (EC) patients (ECP)(T1-4N0-
2M0) - alive supersysems was analyzed. The importance must be stressed of using complex system analysis, artificial
intelligence (neural networks computing), simulation modeling and statistical methods in combination, because the
different approaches yield complementary pieces of prognostic information.
METHODS: We analyzed data of 563 consecutive ECP (age=56.6±8.9 years; tumor size=6±3.5 cm) radically operated
(R0) and monitored in 1975-2024 (m=419, f=144; esophagogastrectomies (EG) Garlock=289, EG Lewis=274, combined
EG with resection of pancreas, liver, diaphragm, aorta, VCS, colon transversum, lung, trachea, pericardium,
splenectomy=170; adenocarcinoma=323, squamous=230, mix=10; T1=131, T2=119, T3=185, T4=128; N0=285, N1=71,
N2=207; G1=161, G2=143, G3=259; early EC=112, invasive=451; only surgery=428, adjuvant
chemoimmunoradiotherapy-AT=135: 5-FU+thymalin/taktivin+radiotherapy 45-50Gy). Multivariate Cox modeling,
clustering, SEPATH, Monte Carlo, bootstrap and neural networks computing were used to determine any significant
dependence.
RESULTS: Overall life span (LS) was 1915.4±2284.8 days and cumulative 5-year survival (5YS) reached 52.6%, 10
years – 46.3%, 20 years – 33.3%, 30 years – 27.5%. 193 ECP lived more than 5 years (LS=4309.1±2507.4 days), 105 ECP
– more than 10 years (LS=5860.8±2469.2 days). 228 ECP died because of EC (LS=629.8±324.1 days). AT significantly
improved 5YS (69% vs. 49.1%) (P=0.0007 by log-rank test). 5YS of ECP of upper/3 was significantly better than others
(65.3% vs.50.3%) (P=0.003). Cox modeling displayed that 5YS of ECP significantly depended on: phase transition (PT)
N0—N12 in terms of synergetics, cell ratio factors (ratio between cancer cells- CC and blood cells subpopulations), T,
G, histology, age, AT, localization, prothrombin index, hemorrhage time, residual nitrogen, protein (P=0.000-0.019).
Neural networks, genetic algorithm selection and bootstrap simulation revealed relationships between 5YS and
healthy cells/CC (rank=1), PT N0—N12 (2), PT early-invasive EC (3), erythrocytes/CC (4), thrombocytes/CC (5);
segmented neutrophils/CC (6), stick neutrophils/CC (7), lymphocytes/CC (8), eosinophils/CC (9), monocytes/CC (10),
leucocytes/CC (11). Correct prediction of 5YS was 100% by neural networks computing (area under ROC curve=1.0;
error=0.0).
CONCLUSIONS: 5-year survival of ECP after radical procedures significantly depended on: 1) PT “early-invasive
cancer”; 2) PT N0--N12; 3) Cell Ratio Factors; 4) blood cell circuit; 5) biochemical factors; 6) hemostasis system; 7) AT;
8) EC cell dynamics; 9) EC characteristics; 10) tumor localization; 11) anthropometric data; 12) surgery type. Optimal
diagnosis and treatment strategies for EC are: 1) screening and early detection of EC; 2) availability of experienced
thoracoabdominal surgeons because of complexity of radical procedures; 3) aggressive en block surgery and
adequate lymph node dissection for completeness; 4) precise prediction; 5) adjuvant chemoimmunoradiotherapy for
ECP with unfavorable prognosis.

3. Data:
• Males…………………………………………………...419
• Females………..……………………………...............144
• Age=56.6±8.9 years
• Tumor Size=6±3.5 cm
• Only Surgery.……………………………………........428
• Adjuvant Chemoimmunoradiotherapy
• (5FU+thymalin/taktivin, 5-6 cycles+ Radiotherapy
• 45-50Gy)………………………...................................135

4. :Radical Procedures
• Esophagogastrectomies Lewis (R0)…………………274
• Esophagogastrectomies Garlock (R0)………...........289
• Combined Esophagogastrectomies with Resection
• of Pancreas, Liver, Trachea, Lung, Aorta, Vena
• Cava Superior, Colon Transversum, Diaphragm,
Pericardium, Splenectomy (R0)……………...............170
• 2-Field Lymphadenectomy…………………………….362
• 3-Field Lymphadenectomy.………………………….…201

5. Staging:
• T1……131 N0..….285 G1…………161
• T2……119 N1….....71 G2…………143
• T3……185 N2…...207 G3…………259
• T4……128 M0…..563
• Adenocarcinoma…………………………….323
• Squamos Cell Carcinoma…………………..230
• Mix………………….....…………………...........10
• Early Cancer……………………………...…...112
• Invasive Cancer…………………………..…..451

6. Survival Rate:
• Alive……………………………………….....296 (52.6%)
• 5-Year Survivors…………..……………….193 (34.3%)
• 10-Year Survivors………………………….105 (18.7%)
• Losses………………………………………..228 (40.5%)
• General Life Span=1915.4±2284.8 days
• For 5-Year Survivors=4309.1±2507.4 days
• For 10-Year Survivors=5860.8±2469.2 days
• For Losses=629.8±324.1 days
• Cumulative 5-Year Survival……………………..52.6%
• Cumulative 10-Year Survival…………………....46.3%
• Cumulative 20-Year Survival…………………....33.3%
• Cumulative 30-Year Survival…………………....27.5%

7. General Esophageal Cancer Patients Survival after
Complete Esophagogastrectomies (Kaplan-Meier)
(n=563):
Survival Function
5YS=52.6%; 10YS=46.3%;
20YS=33.3%; 30YS=27.5%.
Complete Censored
-5 0 5 10 15 20 25 30 35 40 45
Years after Esophagogastrectomies
0.1
0.2
0.3
0.4
0.5
0.6
0.7
0.8
0.9
1.0
Cumulative
Proportion
Surviving

8. Results of Univariate Analysis of Phase
Transition Early—Invasive Cancer in Prediction
of Esophageal Cancer Patients Survival (n=563):
Cumulative Proportion Surviving (Kaplan-Meier)
P=0.000
Complete Censored
0 5 10 15 20 25 30 35 40 45 50
Years after Esophagogastrectomies
0.0
0.1
0.2
0.3
0.4
0.5
0.6
0.7
0.8
0.9
1.0
Cumulative
Proportion
Surviving
Invasive ECP
Early ECP

9. Results of Univariate Analysis of Phase Transition
N0—N1-2 in Prediction of Esophageal Cancer
Patients Survival (n=563):
Cumulative Proportion Surviving (Kaplan-Meier)
P=0.000
Complete Censored
0 5 10 15 20 25 30 35 40 45 50
Time
0.0
0.1
0.2
0.3
0.4
0.5
0.6
0.7
0.8
0.9
1.0
Cumulative
Proportion
Surviving
N0
N1-2

10. Results of Univariate Analysis of Localization
(Upper/3 vs. Others) in Prediction of
Esophageal Cancer Patients Survival (n=563):
Cumulative Proportion Surviving (Kaplan-Meier)
P=0.000
Complete Censored
0 5 10 15 20 25 30 35 40 45 50
Years after Esophagogastrectomies
0.1
0.2
0.3
0.4
0.5
0.6
0.7
0.8
0.9
1.0
Cumulative
Proportion
Surviving
Others
Upper/3

11. Results of Univariate Analysis of Localization
(Cardioesophageal vs. Esophageal) in
Prediction of Esophageal Cancer Patients
Survival (n=563):
Cumulative Proportion Surviving (Kaplan-Meier)
P=0.000
Complete Censored
0 5 10 15 20 25 30 35 40 45 50
Years after Esophagogastrectomies
0.0
0.1
0.2
0.3
0.4
0.5
0.6
0.7
0.8
0.9
1.0
Cumulative
Proportion
Surviving
Cardioesophageal CP
Esophageal CP

12. Results of Univariate Analysis of Adjuvant
Treatment (Adjuvant
Chemoimmunoradiotherapy vs Surgery along)
in Prediction of Esophageal Cancer Patients
Survival (n=563):
Cumulative Proportion Surviving (Kaplan-Meier)
P=0.00375
Complete Censored
0 5 10 15 20 25 30 35 40 45 50
Years after Esophagogastrectomies
0.1
0.2
0.3
0.4
0.5
0.6
0.7
0.8
0.9
1.0
Cumulative
Proportion
Surviving
Adjuvant Chemoradiotherapy
Surgery along

13. Results of Cox Regression Modeling in Prediction of Esophageal Cancer Patients
Survival after Complete Esophagogastrectomies (n=563):
Cox Regression, ECP=563
Parameter
Estimate
Standard
Error
Chi-
square
P value
95%
Lower CL
95%
Upper CL
Hazard
Ratio
Segmented Neutrophils (%) 0.060757 0.017913 11.50399 0.000694 0.02565 0.095867 1.062641
Hemorrhage of Blood 0.001559 0.000400 15.16684 0.000098 0.00077 0.002343 1.001560
Protein 0.020805 0.008677 5.74991 0.016489 0.00380 0.037811 1.021023
Residual Nitrogen 0.046396 0.010866 18.23261 0.000020 0.02510 0.067693 1.047490
Prothrombin Index 0.021704 0.006456 11.30163 0.000774 0.00905 0.034358 1.021942
Segmented Neutrophils (abs) -0.761788 0.204580 13.86576 0.000196 -1.16276 -0.360820 0.466831
Lymphocytes (abs) 0.546870 0.228784 5.71370 0.016833 0.09846 0.995277 1.727836
T1-4 0.418271 0.094110 19.75331 0.000009 0.23382 0.602724 1.519332
PT N0---N12 0.642382 0.161510 15.81930 0.000070 0.32583 0.958936 1.901004
Age 0.028998 0.007691 14.21475 0.000163 0.01392 0.044073 1.029423
Weight -0.034970 0.013244 6.97240 0.008278 -0.06093 -0.009013 0.965634
Histology -0.285581 0.125754 5.15725 0.023150 -0.53205 -0.039108 0.751577
G1-3 0.426268 0.091239 21.82750 0.000003 0.24744 0.605094 1.531532
Adjuvant Chemoimmunoradiotherapy -0.870165 0.190510 20.86250 0.000005 -1.24356 -0.496772 0.418882
Segmented Neutrophils (tot) 0.124208 0.040804 9.26585 0.002335 0.04423 0.204183 1.132252
Leucocytes/Cancer Cells -0.132461 0.037769 12.30035 0.000453 -0.20649 -0.058436 0.875937
Monocytes/Cancer Cells 1.046746 0.401192 6.80736 0.009078 0.26042 1.833067 2.848367
Upper/3 vs Others -0.456165 0.195540 5.44218 0.019656 -0.83942 -0.072914 0.633709
Eosinophils (abs) 0.887039 0.450614 3.87504 0.049009 0.00385 1.770226 2.427929

14. Results of Neural Networks and Monte Carlo
Computing in Prediction of Esophageal Cancer
Patients Survival after Complete
Esophagogastrectomies (n=421):
Corect Classification Rate=100%
Error=0.000
Area under ROC Curve=1.000
Factors n=421 (Neural Networks) Rank Sensitivity
Healthy Cells/Cancer Cells 1 47967
Phase Transition N0---N12 2 32041
Phase Transition Early---Invasive Esophageal Cancer 3 32029
Erythrocytes/ Cancer Cells 4 21816
Thrombocytes/ Cancer Cells 5 20377
Segmented Neutrophils/ Cancer Cells 6 16849
Stick Neutrophils/ Cancer Cells 7 11869
Lymphocyes/ Cancer Cells 8 10648
Eosinophils/ Cancer Cells 9 10401
Monocytes/ Cancer Cells 10 9258
Leucocytes/ Cancer Cells 11 9196

15. Results of Bootstrap Simulation in Prediction
of Esophageal Cancer Patients Survival after
Complete Esophagogastrectomies (n=421):
Significant Factors (Number of Samples=3333) Rank Kendal Tau-A P
Tumor Size 1 -0.308 0.000
Healthy Cells/Cancer Cells 2 0.305 0.000
T1-4 3 -0.299 0.000
Erythrocytes/Cancer Cells 4 0.299 0.000
Leucocytes/Cancer Cells 5 0.290 0.000
Thrombocytes/Cancer Cells 6 0.285 0.000
Lymphocytes/Cancer Cells 7 0.281 0.000
Residual Nitrogen 8 -0.275 0.000
Segmented Neutrophils/Cancer Cells 9 0.273 0.000
Phase Transition N0---N12 10 -0.239 0.000
Hemorrhage Time 11 -0.228 0.000
Monocytes/Cancer Cells 12 0.227 0.000
Phase Transition Early---Invasive Cancer 13 -0.222 0.000
Esophageal/Cardioesophageal Cancer 14 -0.191 0.000
Operation Type 15 -0.187 0.000
Eosinophils/Cancer Cells 16 0.173 0.000
Stick Neutrophils/Cancer Cells 17 0.144 0.001
G1-3 18 -0.140 0.001
Tumor Growth 19 -0.113 0.01
Erythrocytes 20 0.100 0.01
Combined Procedure 21 0.095 0.01
Weight 22 0.092 0.01
Localization 23 0.069 0.05

16. Results of Kohonen Self-Organizing Neural
Networks Computing in Prediction of
Esophageal Cancer Patients Survival after
Complete Esophagogastrectomies (n=421):

17. Esophageal Cancer Cell Dynamics:

18. Prognostic Equation Models of Esophageal
Cancer Patients Survival after Complete
Esophagogastrectomies (n=421):

19. Prognostic Equation Models of Esophageal
Cancer Patients Survival after Complete
Esophagogastrectomies (n=421):

20. Prognostic Equation Models of Esophageal
Cancer Patients Survival after Complete
Esophagogastrectomies (n=421):

21. Prognostic Equation Models of Esophageal
Cancer Patients Survival after Complete
Esophagogastrectomies (n=421):

22. SEPATH Modeling in Prediction of Esophageal
Cancer Patients Survival after Complete
Esophagogastrectomies (n=421):

23. 5-year survival of ECP after radical
procedures significantly depended on:
1) PT “Early-Invasive Cancer”;
2) PT N0--N12;
3) Cell Ratio Factors;
4) Blood Cell Circuit;
5) Biochemical Factors;
6) Hemostasis System;
7) Adjuvant Treatment;
8) EC Characteristics;
9) EC Cell Dynamics;
10) Tumor Localization;
11) Anthropometric Data;
12) Surgery Type.
Conclusion:

24. Optimal diagnosis and treatment
strategies for ECP are:
1) Screening and Early Detection
of EC;
2) Availability of Sufficient
Quantity of Very Experienced
Thoracoabdominal Surgeons
because of Extreme Complexity of
Radical Procedures;
3) Aggressive en block Surgery
and Adequate Lymph Node
Dissection for Completeness;
4) Precise Prediction;
5) Adjuvant
Chemoimmunoradiotherapy for
ECP with Unfavorable Prognosis.
Conclusion:

25. Address:
Oleg Kshivets,
M.D.,Ph.D.
Consultant Thoracic, Abdominal,
General Surgeon & Surgical
Oncologist
• e-mail: okshivets@yahoo.com
• skype: okshivets
• http: //www.ctsnet.org/home/okshivets