scholarly journals Effectiveness of multi-agent technology in three-day campaign for early diagnosis of cutaneous melanoma

2021 ◽  
Vol 9 (3) ◽  
pp. 433-446
Author(s):  
E.Yu. Neretin ◽  
◽  
S.Kh. Sadreyeva ◽  
◽  

BACKGROUND: Melanoma — is a tumor that in most cases affects the skin and is characterized by an extremely aggressive course and a steadily increasing morbidity in the world. However, diagnosed at an early stage, cutaneous melanoma (CM) has a good prognosis with correct treatment. The results of the diagnosis of CM can be improved by joint the efforts of dermatologists and artificial intelligence (AI). AIM: Cutaneous melanoma is a tumor with an unpredictable course. The article discusses ways to solve the problem of early diagnosis using multi-agent technology and an expert system based on AI. MATERIALS AND METHODS: In a large industrial city with more than three million population, a three-day campaign for the early diagnostics of cutaneous melanoma was carried out, which revealed 4 cases of CM (4.35%) at pT1a stage in 96 patients registered in 2019. A total of 800 people were examined. RESULTS: As a result of diagnostics, the following data were obtained: specificity of self-diagnostics of the region was 6.78% by the inhabitants, 78.89% by dermatologists, and 95.24% by expert oncologists. In prospective quality control of diagnostics within 6 months, such parameters as the sensitivity of diagnosing cutaneous melanoma by oncologists and dermatologists were both 100%. As a result of the study, it was found that the multi-agent technology is necessary to improve the results of CM diagnostics, and also for a more complete assessment of the onco-epidemiological situation, and for forecasting of the necessary resources in the region. CONCLUSIONS: The multi-agent technology can improve diagnostic results, but for a more complete assessment of the onco-epidemiological situation, a large-scale population screening in the region is required.

2021 ◽  
Vol 65 (6) ◽  
pp. 557-564
Author(s):  
Evgeniy Yu. Neretin ◽  
Sergey V. Kozlov ◽  
Tatyana G. Zolotareva

Introduction. The most significant problem is the early diagnosis of skin melanoma (SM). In many countries of the world, there is a constant increase in the incidence rate, and the organization of population screening can help solve this problem. Purpose of the study. Evaluation of the use of multi-agent technology in the diagnosis of SM. Material and methods. Study design: at the 1st stage, primary medical documentation was studied - Charts No. 090/y; 027-2/y, statistical reports of the Samara Regional Clinical Oncological Dispensary - Charts No. 7, No. 35, according to the results revealed at stage 2. There was developed and implemented multi-agent technology for SM diagnostics, including various agents of both qualified and specialized levels, these were both individuals and teams of departments who worked in close contact: a public relations agent; artificial intelligence secondary prevention planning agent; agent for training doctors and nurses, patients in the basics of early diagnosis and assessing their level of training; an agent for evaluating performance indicators. Results. After introducing the multi-agent system, the indicator of the share of 1-2 stages of MC in 2010-2019. increased by 48.3% compared to the period 2000-2009 and outpaced the growth in the total number of patients with SM by 6.96%; from 2010 to 2019 the proportion of patients with SM who were actively identified began to increase; one-year mortality rate from 2010 to 2019 decreased in waves (y = 0.0003x5 - 0.0104x4 - 0.2647x3 + 1.4818x2 - 1.8942x + 10.585; R2 = 0.554). Conclusion. The use of multi-agent technology makes it possible to reduce the one-year mortality rate, to achieve a faster growth rate of the newly detected number of patients with an early stage of SM (stage 1-2) compared to the increase in the number of cases, to improve the indicators of early diagnosis, active detection of skin melanoma, which is a positive result.


Author(s):  
Li Yang ◽  
Junlin Liu ◽  
Yun Zhang

Supervisory Control and Data Acquisition (SCADA) system in the modern industrial automation control network is facing an increasing number of serious security threats. In order to meet the security defense requirements of oil and gas SCADA system, an intelligent security defense model based on multi-agent was designed by analyzing the security risks in oil and gas SCADA system and combining the advantages of multi-agent technology in distributed intrusion detection system. First, the whole structure of this model was divided into three layers: monitoring layer, decision layer and control layer. Then, the defense model was verified by C4.5 decision tree algorithm, and obtained a good result. Finally, the security defense prototype system of large-scale oil and gas SCADA system based on this model was realized. Results demonstrate that the application of multi-agent technology in the security defense of oil and gas SCADA system can achieve more comprehensive defense, more accurate detection, which can handle large-scale distributed attacks and improve the robustness and stability of security defenses. This study makes full use of the multi-agent architecture and has the advantage of accurate detection, high detection efficiency and timely response.


1995 ◽  
Vol 62 (2) ◽  
pp. 300-304
Author(s):  
M. Fini ◽  
G. Vagliani

From September 1992 to February 1994, 1441 men aged between 50 and 70 years underwent screening with PSA and ER measurement for early diagnosis of prostatic carcinoma. A neoplasm was diagnosed in 1.73% (25/1441) of cases, which being found at an early stage, made it possible to perform prostatectomy and radical radiotherapy on 37.5% and 16.6% of patients respectively. The incidence of the disease was higher than in a previous screening with just ER dosage (1.73% vs 1.1%). Combined PSA and ER also gave higher sensitivity, specificity, overall accuracy and predictiveness compared to the methods taken individually. This combination seems preferable, in view of the greater efficacy and “practicability” compared to protocols which involve the use of USTR, which is less practicable on a large scale due to the length of time required and high costs. The utility of periodic determination of PSA levels in those over fifty years old is emphasised, both for oncological screening controls and to increase the diagnostic accuracy of other clinical tests.


Author(s):  
E.Yu. Neretin ◽  
S.Kh. Sadreeva

Skin melanoma (SM) is a malignant tumor that is quite rarely diagnosed in Russia. However, both absolute and relative numbers (incidence) of patients with this diagnosis are growing. The trend persists for many years, but the official incidence rate does not reflect the true picture, so it is likely to be lower than the true one. The aim of the study was to calculate the assumed incidence of skin melanoma based on the data from a large-scale early diagnosis campaign. Materials and Methods. In 2019, 800 patients were examined during a 3-day campaign in the Samara region. A non-invasive diagnostic method (digital dermatoscopy), a multi-agent technology based on artificial intelligence and a proprietary technology (patent No. 2018620399, No. 2018613016) were used during the campaign. Four skin melanomas were identified at an early, pre-invasive stage. Results. Two different methods (depending on the percentage of population coverage and the campaign duration), made it possible to calculate a true indicator of the skin melanoma incidence. Conclusion. It was possible to adjust the "true" incidence rate of skin melanoma. In 2019, it ranged from 9.65 to 15.31 per 100 000 people, which is significantly higher than the official rate registered that year (8.11 per 100 000 population). Keywords: skin melanoma, true incidence, large-scale campaign, multi-agent system, skin melanoma modeling. Меланома кожи (МК) является злокачественной опухолью, которая встречается в РФ довольно редко, причем растет как абсолютное количество пациентов с данным диагнозом, так и относительное (заболеваемость). Данная тенденция стабильно сохраняется на протяжении многих лет, однако официальный показатель заболеваемости не отражает реальной картины и вполне вероятно, что он несколько ниже «истинного». Целью исследования был расчет предполагаемой заболеваемости меланомой кожи на основании данных, полученных в результате масштабной кампании по ранней диагностике. Материалы и методы. В Самарской области в 2019 г. была проведена 3-дневная кампания, которая позволила обследовать 800 обратившихся пациентов с помощью неинвазивного метода диагностики (цифровой дерматоскопии) и мультиагентной технологии, основанной на искусственном интеллекте и авторской методике (патент на изобретение № 2018620399, № 2018613016). Всего было выявлено 4 меланомы кожи на ранней, доинвазивной, стадии. Результаты. В ходе расчета по 2 различным методикам (в зависимости от процента охвата населения и продолжительности акции) был получен «истинный» показатель заболеваемости МК. Выводы. «Истинный» показатель заболеваемости МК был скорректирован и составил от 9,65 до 15,31 на 100 тыс. населения, что значительно больше официального, зарегистрированного в отчетном 2019 г. (8,11 на 100 тыс. населения). Ключевые слова: меланома кожи, «истинная» заболеваемость, масштабная кампания, мультиагентная система, моделирование заболеваемости меланомы кожи.


2013 ◽  
Vol 273 ◽  
pp. 276-279
Author(s):  
Xiao Zhou Fan

Multi-agent technology combines the technology of computer, networking and distributed artificial intelligence together which is good at solving complex problems about large-scale distributed and open system. Multi-agent technology provides new ways for power system studies. This paper aims at finding a way to rationally use the multi-agent technology to solve complex problems due to improper protection or slow even wrong actions in the large power system.


Author(s):  
N. G. Artemeva ◽  
O. A. Romanova

Introduction. Russia has a high mortality rate of cutaneous melanoma – 2.5 per 100,000 population whereas the incidence rate is 7.7 per 100,000 population, i.e. one in every three patients dies. In the foreign countries (the USA, Australia), melanoma mortality rate is 10-15%. Such high rates are explained by the fact that patients with early-stage disease do not seek medical advice, as in early stages a tumour does not cause inconvenience to a patient and looks like an ordinary mole.The purpose of the study was to confirm the advisability of removing a progressive dysplastic nevus (grade 3 lentiginous melanocytic dysplasia) with a view to prevent and make early diagnosis of cutaneous melanoma.Materials and methods. The authors removed 180 pigmented lesions that were clinically diagnosed as a progressive dysplastic nevus in the Surgery Department of Central Polyclinic of Literary Fund from 2009 to March 2020. The patients were referred to the Surgery Department by physicians, dermatologists and other specialists of the polyclinic. Following an oncologist consultation, excisional biopsy of a nevus was performed under local anesthesia.Results. Histological examination revealed 29 (16%) dysplastic nevi with grade 3 LMD and 18 (10%) early-stage melanomas.Conclusions. If excisional biopsy of a dysplastic nevus becomes routine in Ambulatory Surgery practice, it will increase the early diagnosis of melanoma and significantly reduce mortality rates of this disease. For excisional biopsy, the authors recommend to excise at a distance of 0.5 to 1.0 cm from the lesion boundaries, since it is not possible to clinically distinguish a progressive dysplastic nevus from early melanoma.


2009 ◽  
Vol 160 (5) ◽  
pp. 114-123 ◽  
Author(s):  
Daniel Otto ◽  
Sven Wagner ◽  
Peter Brang

The competitive pressure of naturally regenerated European beech (Fagus sylvatica) saplings on planted pedunculate oak (Quercus robur) was investigated on two 1.8 ha permanent plots near Habsburg and Murten (Switzerland). The plots were established with the aim to test methods of artificial oak regeneration after large-scale windthrow. On both plots, 80 oaks exposed to varying levels of competitive pressure from at most 10 neighbouring beech trees were selected. The height of each oak as well as stem and branch diameters were measured. The competitive pressure was assessed using Schütz's competition index, which is based on relative tree height, crown overlap and distance from competing neighbours. Oak trees growing without or with only slight competition from beech were equally tall, while oaks exposed to moderate to strong competition were smaller. A threshold value for the competition index was found above which oak height decreased strongly. The stem and branch diameters of the oaks started to decrease even if the competition from beech was slight, and decreased much further with more competition. The oak stems started to become more slender even with only slight competition from beech. On the moderately acid beech sites studied here, beech grow taller faster than oak. Thus where beech is competing with oak and the aim is to maintain the oak, competitive pressure on the oak must be reduced at an early stage. The degree of the intervention should, however, take the individual competitive interaction into account, with more intervention if the competition is strong.


2015 ◽  
pp. 5-14
Author(s):  
Van Huy Tran ◽  
Quang Trung Tran

The prognosis of gastric cancer depends principally upon an early diagnosis. An early and accurate diagnosis of gastric cancer needs some basic knowledges about the endoscopic characteristics of white light endoscopy, chromoendoscopy, magnified endoscopy, FICE and NBI…A strategy of screening is also a key factor for early diagnosis. The treatment of early gastric cancer by endoscopy techniques have showed more and more advantages. Beside of EMR, the technique of ESD is now applied more widely and lead to a very good prognosis and nearly a curative treatment for the patients with early gastric cancer. Key words: gastric cancer, early gastric cancer, diagnosis, endoscopy


Sign in / Sign up

Export Citation Format

Share Document