Artificial Intelligence, Synergetics, Complex System Analysis and Simulation of Alive Supersystems for Optimal Management of Local Advanced Lung Cancer

5YS of local advanced non-small cell LCP after combined radical procedures significantly depended on: tumor characteristics, LC cell dynamics, blood cell circuit, cell ratio factors, biochemical factors, hemostasis system, anthropometric data, adjuvant treatment and procedure type. Optimal strategies for local advanced LCP are: 1) availability of very experienced thoracic surgeons because of complexity radical procedures; 2) aggressive en block surgery and adequate lymph node dissection for completeness; 3) precise prediction; 4) AT for LCP with unfavorable prognosis.

1. Artificial Intelligence, Synergetics, Complex
System Analysis and Simulation of Alive
Supersystems for Optimal Management of
Local Advanced Lung Cancer
Kshivets Oleg Surgery Department, BagrationovskHospital,
Bagrationovsk, Kaliningrad, Russia

2. ABSTRACT

OBJECTIVE: The survival of patients with local advanced of lung cancer (LC) takes several months. Radical operations are extremely complex and
remain the prerogative of several top thoracic surgeons of the world. The search of optimal treatment plan for LC patients (LCP) with stage T3-4N0-2M0
was realized. We examined factors in terms of precise prediction of 5- year survival (5YS) of local advanced LCP after complete (R0) combined
lobectomies/pneumonectomies (LP).
METHODS: We analyzed data of 198 consecutive LCP (age=58.1± 8.2 years; tumor size=6.8± 2.6 cm) radically operated and monitored in 1985- 2024
(m=173, f=25; bi/lobectomies=84, pneumonectomies=114, mediastinal lymph node dissections=198; combined LP with resection of trachea, carina,
atrium, aorta, VCS, vena azygos, pericardium, liver, diaphragm, ribs, esophagus=198; only surgery-S=117, adjuvant chemoimmunoradiotherapy -AT=81:
CAV/gemzar + cisplatin + thymalin/taktivin + radiotherapy 45- 50Gy; T3=137, T4=61; N0=94, N1=44, N2=60, M0=198; G1=42, G2=53, G3=103;
squamous=118, adenocarcinoma=65, large cell=15, central=115, peripheral=83. Multivariate Cox modeling, clustering, SEPATH, Monte Carlo,
synergetics, bootstrap and neural networks computing were used to determine any significant dependence.
RESULTS: Overall life span (LS) was 1671.7±1721.6 days and cumulative 5YS reached 62.4%, 10 years – 50.4%, 20 years – 44.6%. 94 LCP lived more
than 5 years without cancer (LS=2958.6± 1723.6 days), 22 – more than 10 years (LS=5571± 1841.8 days). 67 LCP died because of LC (LS=471.9± 344 days).
AT significantly improved 5YS (68% vs. 53.7%) (P=0.028 by log-rank test). Cox modeling displayed that 5YS of LCP significantly depended on: N0 -N12,
T3-4, blood cell circuit, cell ratio factors (ratio between cancer cells- CC and blood cells subpopulations), LC cell dynamics, recalcification time, heparin
tolerance, prothrombin index, protein, AT, procedure type (P=0.000-0.031). Neural networks, genetic algorithm selection and bootstrap simulation
revealed relationships between 5YS and N0- 12 (rank=1), thrombocytes/CC (rank=2), segmented neutrophils/CC (3), eosinophils/CC (4), erythrocytes/CC
(5), healthy cells/CC (6), lymphocytes/CC (7), stick neutrophils/CC (8), leucocytes/CC (9), monocytes/CC (10). Correct predictio n of 5YS was 100% by
neural networks computing (error=0.000; area under ROC curve=1.0).
CONCLUSIONS: 5YS of local advanced non- small cell LCP after combined radical procedures significantly depended on: tumor characteristics, LC
cell dynamics, blood cell circuit, cell ratio factors, biochemical factors, hemostasis system, anthropometric data, adjuvant treatment and procedure
type. Optimal strategies for local advanced LCP are: 1) availability of very experienced thoracic surgeons because of complexity radic al procedures; 2)
aggressive en block surgery and adequate lymph node dissection for completeness; 3) precise prediction; 4) AT for LCP with unfav orable prognosis.

3. Data:
•Males………………………………………………….......173
•Females………..……………………………....................25
•Age=58.1±8.2years
•Tumor Size=6.8±2.6cm
•Only Surgery.………………………………… …...........117
•AdjuvantChemoimmunoradiotherapy(CAV/gemzar+
cisplatin+thymalin/taktivin, 5- 6 cycles+Radiotherapy
•45-50Gy)……………………….......................................81

4. :Radical Procedures
•Bi/Lobectomies (R0)……………………………………….…..84
•Pneumonectomies (R0)………...........................................114
•Combined Lobectomies/Pneumonecomies with Resection
•of Carina, Trachea, Atrium, Aorta, Vena Cava Superior,
Liver, Diaphragm, Pericardium, Vena Azygos, Ribs,
Esophagus (R0)……………................................................198
•Mediastinal Lymph Node Dissection………..…………….198

5. Staging:
•T3……137 N0..…...94 G1……….….42
•T4……..61 N1….....44 G2……….….53
• M0…..198 N2….....60 G3…………103
•Adenocarcinoma………………………….…..65
•Squamos Cell Carcinoma……………….….118
•Large Cell……….....…………………..............15

6. Survival Rate:
•Alive……………………………………….......119 (60.1%)
•5-Year Survivors…………..…………..……...94 (47.5%)
•10-Year Survivors………………………….....22 (11.1%)
•Losses………………………………………….67 (33.8%)
•General Life Span=1671.7±1721.6 days
•For 5-Year Survivors=2958.6±1723.6 days
•For 10-Year Survivors=5571±1841.8 days
•For Losses=471.9±344 days
•Cumulative 5-Year Survival……………………….62.4%
•Cumulative 10- Year Survival…………………......50.4%
•Cumulative 20- Year Survival…………………......44.6%

7. General Lung Cancer Patients
(T3-4) Survival after Complete
Combined Lobectomies/Pneumon-
ectomies (Kaplan-Meier) (n=198):
Survival Function
5YS=62.4%; 10YS=50.4%; 20YS=44.6%.
Complete Censored
-5 0 5 10 15 20 25 30
Years after Surgery
0.3
0.4
0.5
0.6
0.7
0.8
0.9
1.0
1.1
1.2
Cumulative Proportion Surviving

8. Results of Univariate Analysis of
Phase Transition N0—N1 -2 in
Prediction of Lung Cancer
Patients (T3-4)Survival (n=198):
Cumulative Proportion Surviving (Kaplan-Meier)
5YS LCP with N0=74.5%; 5YS LCP wih N1-2=50.7% P=0.00086.
Complete Censored
0 5 10 15 20 25 30 35
Years after Surgery
0.3
0.4
0.5
0.6
0.7
0.8
0.9
1.0
Cumulative Proportion Surviving
N12
N0

9. Results of Univariate Analysis of
Adjuvant Treatment (Adjuvant
Chemoimmunoradiotherapy vs
Surgery along) in Prediction of
Lung CancerPatients (T3-4)
Survival (n=198):
Cumulative Proportion Surviving (Kaplan-Meier)
5YS LCP after AT=74.5%; 5YS LCP after Surgery along=55% P=0.00195.
Complete Censored
0 5 10 15 20 25 30 35
Years after Surgery
0.2
0.3
0.4
0.5
0.6
0.7
0.8
0.9
1.0
Cumulative Proportion Surviving
Only Surgery
Adjuvant Chemoimmunoradiotherapy

10. Results of Cox Regression Modeling
in Prediction of Lung Cancer
Patients (T3-4) Survival after
Complete Lobectomies/Pneumon-
ectomies (n=198):
Cox Regression, n=198
Parameter
Estimate
Standard
Error
Chi-
square
P value
95%
LowerCL
95%
UpperCL
T3-4 0.93365 0.3142248.828510.0029660.317781.54951
N0---N12 0.61808 0.15601915.694040.0000740.312290.92387
LC Cell Dynamics 0.29571 0.06978617.955200.0000230.158930.43249
Eosinophils (abs) 17.67339 4.62518214.600980.0001338.6082026.73858
Prothrombin Index 0.04784 0.0154369.603780.0019420.017580.07809
Protein 0.04103 0.0168735.912470.0150340.007960.07410
Recalcification Time -0.00720 0.0031055.375610.020420-0.01329-0.00111
Heparin Tolerance 0.00420 0.00118912.479490.0004110.001870.00653
Adjuvant Chemoimmunoradiotherapy -0.76183 0.3546514.614340.031706-1.45693-0.06672
Thrombocytes/Cancer Cells 0.00870 0.00204018.188900.0000200.004700.01270
Eosinophils (tot) -3.65060 0.97235914.095310.000174-5.55638-1.74481
Lymphocytes (tot) -0.08709 0.0382805.176140.022899-0.16212-0.01206
Pneumonectomies/Lobectomies -0.63257 0.2612205.864180.015452-1.14455-0.12059

11. Results of Neural Networks and Monte
Carlo Computingin Prediction of
Lung Cancer Patients (T3-4) Survival
after Complete Lobectomies/Pneumon-
ectomies (n=192
):
Corect Classification Rate=100%
Error=0.000
Area under ROC Curve=1.000
Neural Networks: Baseline Error=0.000;Area
under ROC Curve=1.000; Correct
Classification Rate=100%; n=192
Rank Sensitivity
Phase Transition N0---N12 1 1199
Thrombocytes/Cancer Cells
Eosinophils/Cancer Cells
Healthy Cells/Cancer Cells
Stick Neutrophils/Cancer Cells
Lymphocytes/Cancer Cells
Segmented Neutrophils/Cancer Cells
2
3
4
5
6
7
637
474
437
376
372
333
Erythrocytes/Cancer Cells 8 299
Monocytes/Cancer Cells Leucocytes/Cancer Cells
9
10
261 159

12. Results of BootstrapSimulationin
Prediction of Lung Cancer
Patients Survival (T3-4) after Complete
Lobectomies/Pneumonectomies
(n=192
):
Significant Factors
(Number of Samples=3333)
RankKendal
Tau-A
P<
Prothrombin Index 1 -0.2090.001
Phase Transition N0---N12 2 -0.1760.01
Glucose 3 0.1330.05
Weight 4 0.1250.05
Erythrocytes/Cancer Cells 5 0.1240.05
Age 6 -0.1180.05
Heparin Tolerance 7 -0.1180.05
Healthy Cells/Cancer Cells 8 0.1170.05
Monocytes/Cancer Cells 9 0.1170.05
Eosinophils/Cancer Cells 10 0.1150.05
ESS 11 -0.1120.05
Erythrocytes tot. 12 0.1120.05

13. Results of Kohonen Self-
Organizing Neural Networks
Computing in Prediction of
Lung Cancer Patients (T3-4)
Survival after Complete
Lobectomies/Pneumonectomies (n=192):

14. Lung Cancer Cell Dynamics:

15. Prognostic Equation Models of
Lung Cancer Patients (T3-4)
Survival after Complete
Lobectomies/Pneumonectomies
(n=192):

16. Prognostic Equation Models of
Lung Cancer Patients (T3-4)
Survival after Complete
Lobectomies/Pneumonectomies
(n=192):

17. Prognostic Equation Models of
Lung Cancer Patients (T3-4)
Survival after Complete
Lobectomies/Pneumonectomies
(n=192):

18. Prognostic Equation Models of
Lung Cancer Patients (T3-4)
Survival after Complete
Lobectomies/Pneumonectomies
(n=192):

19. Prognostic Equation Models of
Lung Cancer Patients (T3-4)
Survival after Complete
Lobectomies/Pneumonectomies
(n=192):

20. Prognostic Equation Models of
Lung Cancer Patients (T3-4)
Survival after Complete
Lobectomies/Pneumonectomies
(n=192):

21. SEPATH Modeling in Prediction of
Lung Cancer Patients (T3-4)
Survival after Complete
Lobectomies/Pneumonectomies
(n=192):

22. 5YS of local advanced
non-small cell LCP (T3- 4)
after combined radical
procedures significantly
depended on:
1) tumor characteristics;
2) LC cell dynamics;
3) blood cell circuit;
4) cell ratio factors;
5) biochemical factors;
6) hemostasis system;
7) anthropometric data;
8) adjuvant treatment;
9) procedure type.
Conclusion:

23. Optimal Strategies for Local Advanced
LCP (T3- 4) are:
1) Availability of Sufficient Quantity of
Experienced Thoracic Surgeons because
of Complexity of Radical Procedures;
2) Aggressive En Block Surgery and
Adequate Lymph Node Dissection for
Completeness;
3) Precise Prediction;
4) AT for LCP with Unfavorable
Prognosis.
Conclusion:

24. Address: Oleg Kshivets, M.D.,Ph.D ., Consultant
Thoracic, Abdominal, General Surgeon & Surgical Oncologist
• e-mail: [email protected]
• skype: okshivets
• http: //www.ctsnet.org/home/okshivets