5YS of LCP after radical procedures significantly depended on: PT early-invasive cancer; PT N0--N12; cell ratio factors; blood cell circuit; biochemical factors; hemostasis system; AT; LC characteristics; LC cell dynamics; surgery type; anthropometric data.

1. Non­Small Cell Lung Cancer: Artificial
Intelligence, Complex System Analysis and
Computer Simulation for Best Management.
#79
Kshivets Oleg, MD, PhD
Roshal Hospital, Roshal, Moscow
Russia
No Disclosures
Kshivets Oleg, Roshal Hospital, Russia

2. Abstract
Non­Small Cell Lung Cancer: Artificial Intelligence, Complex System Analysis and Computer Simulation for Best Management.
Kshivets Oleg Surgery Department, Roshal Hospital, Moscow, Russia
�OBJECTIVE: 5­survival (5YS) and life span after radical surgery for non­small cell lung cancer (LC) pa­tients (LCP) (T1­4N0­2M0) was analyzed.
METHODS: We analyzed data of 771 consecutive LCP (age=57.6±8.3 years; tumor size=4.1±2.4 cm) radically operated and monitored in 1985­
2022 (m=662, f=109; upper lobectomies=278, lower lobectomies=178, middle lobectomies=18, bilobectomies=42, pneumonectomies=255,
mediastinal lymph node dissection=771; combined procedures with resection of trachea, carina, atrium, aorta, VCS, vena azygos,
pericardium, liver, diaphragm, ribs, esophagus=194; only surgery­S=620, adjuvant chemoimmunoradiotherapy­AT=151: CAV/gemzar +
cisplatin + thymalin/taktivin + radiotherapy 45­50Gy; T1=322, T2=255, T3=133, T4=61; N0=518, N1=131, N2=122, M0=771; G1=195, G2=243,
G3=333; squamous=418, adenocarcinoma=303, large cell=50; early LC=215, invasive LC=556; right LC=413, left LC=358; central=291;
peripheral=480. Variables selected for study were input levels of 45 blood parameters, sex, age, TNMG, cell type, tumor size. Regression
modeling, clustering, SEPATH, Monte Carlo, bootstrap and neural networks computing were used to determine significant dependence.
RESULTS: Overall life span (LS) was 2240.9±1748.8 days and cumulative 5­year survival (5YS) reached 73%, 10 years – 64.2%, 20 years – 43%.
503 LCP lived more than 5 years (LS=3126.6±1536 days), 145 LCP – more than 10 years (LS=5068.5±1513.2 days).199 LCP died because of
LC (LS=562.7±374.5 days). 5YS of LCP after bi/lobectomies was significantly superior in comparison with LCP after pneumonectomies
(77.7% vs.63.4%, P=0.00001 by log­rank test). AT significantly improved 5YS (64.4% vs. 34.8%) (P=0.00003 by log­rank test) only for LCP
with N1­2. Cox modeling displayed that 5YS of LCP significantly depended on: phase transition (PT) early­invasive LC in terms of
synergetics, PT N0—N12, cell ratio factors (ratio between cancer cells­ CC and blood cells subpopulations), G1­3, histology, glucose, AT,
blood cell circuit, prothrombin index, heparin tolerance, recalcification time (P=0.000­0.035). Neural networks, genetic algorithm selection
and bootstrap simulation revealed relationships between 5YS and PT early­invasive LC (rank=1), PT N0—N12 (rank=2), thrombocytes/CC
(3), eosinophils/CC (4), erythrocytes/CC (5),healthy cells/CC (6), segmented neutrophils/CC (7), lymphocytes/CC (8), stick neutrophils/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: 5YS of LCP after radical procedures significantly depended on: PT early­invasive cancer; PT N0­­N12; cell ratio factors; blood
cell circuit; biochemical factors; hemostasis system; AT; LC characteristics; LC cell dynamics; surgery type; anthropometric data. Best
management for LCP is: 1) screening and early detection of LC; 2) availability of experienced thoracic 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 LCP with unfavorable prognosis.
Kshivets Oleg, Roshal Hospital, Russia

3. Data:
Males…………………………………….………………………………………………………...662
Females…….......................................................................................................................109
Age=57.6±8.3 years; Tumor Size=4.1±2.4 cm
Upper Lobectomies……………………….…………….……………………………………...278
Lower Lobectomies.………..............................................................................................178
Middle Lobectomies.………………………………………….………………………………….18
Bilobectomies.………………………………………………….………………………………....42
Pneumonectomies………………………………………………………..………………..……255
Combined Procedures with Resection of Trachea, Carina, Atrium, Aorta, Vena Cava
Superior, Vena Azygos, Pericardium, Liver, Diaphragm, Ribs,
Esophagus…………………………………..……………………………………………….194
Mediastinal Lymphadenectomy.……………………………..…...……771
Kshivets Oleg, Roshal Hospital, Russia

4. Staging:
T1……..322 N0..……518 G1…………195
T2……..255 N1…......131 G2…………243
T3……..133 N2…......122 G3…………333
T4………61 N1­2…...253 M0…….…...771
Adenocarcinoma………………………………………………………..303
Squamous Cell Carcinoma……………………………………..……..418
Large Cell Carcinoma………………………………………..................50
Kshivets Oleg, Roshal Hospital, Russia

5. Results of Univariate Analysis of Phase Transitions Early­Invasive Lung Cancer, N0—N1­2 in Prediction of Lung
Cancer Patients Survival (n=771):
Kshivets Oleg, Roshal Hospital, Russia

6. Results of Univariate Analysis of AT, gender and type of surgery in Prediction of Lung Cancer Patients Survival (n=771):
Kshivets Oleg, Roshal Hospital, Russia

7. �Cox Regression for Prediction of Lung Cancer Patients Survival (n=771):
Kshivets Oleg, Roshal Hospital, Russia

8. Results of Neural Networks Computing in Prediction of Lung Cancer Patients Survival (n=702):
Kshivets Oleg, Roshal Hospital, Russia

9. Results of Bootstrap Simulation in Prediction of Lung Cancer Patients Survival (n=702):
Kshivets Oleg, Roshal Hospital, Russia

10. Results of Kohonen Self­Organizing Neural Networks Computing in Prediction of Lung
Cancer Patients Survival (n=702):
Kshivets Oleg, Roshal Hospital, Russia

11. Prognostic Equation Models of Lung Cancer Patients Survival after Surgery (n=702):
Kshivets Oleg, Roshal Hospital, Russia

12. Prognostic Equation Models of Lung Cancer Patients Survival after Surgery (n=702):
Kshivets Oleg, Roshal Hospital, Russia

13. Prognostic Equation Models of Lung Cancer Patients Survival after Surgery (n=702):
Kshivets Oleg, Roshal Hospital, Russia

14. Prognostic Equation Models of Lung Cancer Patients Survival after Surgery (n=702):
Kshivets Oleg, Roshal Hospital, Russia

15. SEPATH­Model in Prediction of Lung Cancer Patients Survival (n=702):
Kshivets Oleg, Roshal Hospital, Russia

16. 5­YEAR SUVIVAL OF NON­SMALL CELL
LUNG CANCER PATIENTS AFTER
RADICAL PROCEDURES (R0)
SIGNIFICANTLY DEPENDED ON:
1) PHASE TRANSITION EARLY­INVASIVE
LUNG CANCER;
2) PHASE TRANSITION N0­­­N12;
3) CELL RATIO FACTORS;
4) BLOOD CELL CIRCUIT;
5) BIOCHEMICAL FACTORS;
6) HEMOSTASIS SYSTEM;
7) ADJUVANT
CHEMOIMMUNORADIOTHERAPY;
8) LUNG CANCER CHARACTERISTICS;
9) LUNG CANCER CELL DYNAMICS;
10) SURGERY TYPE;
11) ANTHROPOMETRIC DATA.
Conclusion:
Kshivets Oleg, Roshal Hospital, Russia

17. BEST MANAGEMENT FOR LCP IS:
1) SCREENING AND EARLY DETECTION OF
LC;
2) THE PRESENCE OF A SUFFICIENT
NUMBER OF OF EXPERIENCED THORACIC
SURGEONS BECAUSE OF COMPLEXITY OF
RADICAL PROCEDURES ESPECIALLY WITH
LOCALLY ADVANCED LC;
3) AGGRESSIVE EN BLOCK SURGERY AND
ADEQUATE LYMPH NODE DISSECTION FOR
COMPLETENESS;
4) PRECISE PREDICTION;
5) ADJUVANT
CHEMOIMMUNORADIOTHERAPY FOR LCP
WITH UNFAVORABLE PROGNOSIS.
Conclusion:
Kshivets Oleg, Roshal Hospital, Russia

18. Address: Oleg Kshivets, M.D., Ph.D.
Consultant Thoracic, Abdominal, General
Surgeon & Surgical Oncologist
e­mail: okshivets@yahoo.com
skype: olegks001
http: //www.ctsnet.org/home/okshivets
Kshivets Oleg, Roshal Hospital, Russia