Background: Today, cardiovascular diseases cause 47% of all deaths among the European population, which is 4 million cases every year. In Ukraine, CAD accounts for 65% of the mortality rate from circulatory system diseases of the able-bodied population and is the main cause of disability. The aim of this study is to develop a medical expert system based on fuzzy sets for assessing the degree of coronary artery lesions in patients with coronary artery disease. Methods: The method of using fuzzy sets for the implementation of an information expert system for solving the problems of medical diagnostics, in particular, when assessing the degree of anatomical lesion of the coronary arteries in patients with various forms of coronary artery disease, has been developed. Results: The paper analyses the main areas of application of mathematical methods in medical diagnostics, and formulates the principles of diagnostics, based on fuzzy logic. The developed models and algorithms of medical diagnostics are based on the ideas and principles of artificial intelligence and knowledge engineering, the theory of experiment planning, the theory of fuzzy sets and linguistic variables. The expert system is tested on real data. Through research and comparison of the results of experts and the created medical expert system, the reliability of supporting the correct decision making of the medical expert system based on fuzzy sets for assessing the degree of anatomical lesion of the coronary arteries in patients with various forms of coronary artery disease with the assessment of experts was 95%, which shows the high efficiency of decision making. Conclusions: The practical value of the work lies in the possibility of using the automated expert system for the solution of the problems of medical diagnosis based on fuzzy logic for assessing the degree of anatomical lesion of the coronary arteries in patients with various forms of coronary artery disease. The proposed concept must be further validated for inter-rater consistency and reliability. Thus, it is promising to create expert medical systems based on fuzzy sets for assessing the degree of disease pathology.
Ìåòà. Îö³íêà õàðàêòåðó óðàaeåííÿ êîðîíàðíîãî ðóñëà ïðè íå Q-³íôàðêò³ ì³îêàðäà â çàëåaeíîñò³ â³ä ãåíäåðíî-â³êîâèõ â³äì³ííîñòåé ³ âèçíà÷åííÿ êîðåëÿö³éíèõ çâ'ÿçê³â ì³ae öèìè ïîðóøåííÿìè òà ³íøèìè êë³í³êî-³íñòðóìåíòàëüíèìè ïàðàìåòðàìè. Ìàòåð³àë ³ ìåòîäè. Îáñòåaeåíî 40 ïàö³ºíò³â (62,5% ÷î-ëîâ³êè) ³ç íå Q-³íôàðêòîì ì³îêàðäà â³êîì â³ä 52 äî 79 (â ñåðåäíüîìó 67,1±1,4) ðîê³â çà ïåð³îä 2011-2016 ðð. Óñ³ì õâîðèì ïðîòÿãîì â³ä 1 äî 70 (â ñåðåäíüîìó 19,4±3,0) ãîäèí ç ìîìåíòó íàäõîäaeåííÿ â ñòàö³îíàð áóëà ïðîâåäåíà êî-ðîíàðî´ðàô³ÿ íà àïàðàò³ SIEMENS Axiom Artis (ͳìå÷-÷èíà). Ïàö³ºíòè ïðîéøëè îáñòåaeåííÿ çã³äíî ïðîòîêîëó, ÿêèé â³äïîâ³äຠðåêîìåíäàö³ÿì Àñîö³àö³¿ êàðä³îëî´³â Óêðà¿íè ùîäî ä³à´íîñòèêè òà ë³êóâàííÿ ãîñòðîãî ³íôàðêòó ì³îêàðäà (2016) ç âèçíà÷åííÿì çàãàëüíîïðèéíÿòèõ êë³í³êî-ëàáîðàòîðíèõ òà ³íñòðóìåíòàëüíèõ ïîêàç-íèê³â. Ñòàòèñòè÷íó îáðîáêó ðåçóëüòàò³â äîñë³äaeåííÿ ïðîâåäåíî çà äîïîìîãîþ íåïàðàìåòðè÷íèõ ìåòîä³â âà-ð³àö³éíî¿ ñòàòèñòèêè. Äîñòîâ³ðí³ñòü ð³çíèö³ ì³ae ê³ëü-ê³ñíèìè ïîêàçíèêàìè ðîçðàõîâàíî çà Mann-Whitney U test ³ ÿê³ñíèìè -çà êðèòåð³ºì χ 2 . Íàÿâí³ñòü çâ'ÿçê³â ì³ae ïîêàçíèêàìè âèçíà÷åíî çà ðàíãîâèì êîðåëÿö³éíèì àíàë³çîì Ñï³ðìåíà (Spearman Rank Order Correlations). Ðåçóëüòàòè é îáãîâîðåííÿ. Àíàë³ç äàíèõ êîðîíàðî´ðàô³¿ ñâ³ä÷èâ ïðî äîâîë³ ñóòòºâ³ ñòðóêòóðí³ çì³íè êîðîíàðíèõ àðòåð³é â ïàö³ºíò³â ³ç íå Q-³íôàðêòîì ì³îêàðäà ïðè â³ä-ñóòíîñò³ äîñòîâ³ðíèõ ãåíäåðíèõ â³äì³ííîñòåé â õàðàê-òåð³ àíàòîì³÷íîãî óðàaeåííÿ êîðîíàðíèõ àðòåð³é.  ãðó-ï³ õâîðèõ ñòàðøèõ 70-è ðîê³â, íà â³äì³íó â³ä á³ëüø ìîëîäèõ ïàö³ºíò³â, ñïîñòåð³ãàëè äîñòîâ³ðíå çá³ëüøåííÿ ÷àñòîòè ðåºñòðàö³¿ îêëþç³é â áàñåéí³ ë³âî¿ êîðîíàðíî¿ àð-òåð³¿, ñåðåäíüî¿ äîâaeèíè âèçíà÷åíèõ ñòåíîç³â ³ çá³ëüøåííÿ ÷àñòîòè âèïàäê³â ³ç ñòåíîçàìè >10 ìì. ²ç ³íøîãî áîêó, ïðè àíàë³ç³ àíàòîì³÷íèõ îñîáëèâîñòåé óðàaeåííÿ ïðàâî¿ êîðîíàðíî¿ àðòå𳿠âèÿâëåí³ çàêîíîì³ðíîñò³ çì³íèëèñü íà ðàäèêàëüíî çâîðîòí³, à ñàìå á³ëüø òÿaeêà ñòóï³íü ñòåíîçó áóëà çàô³êñîâàíà ñàìå â ãðóï³ á³ëüø ìîëîäèõ ïàö³-ºíò³â. Àíàë³ç âèïàäê³â äâîõ-³ òðüîõñóäèííèõ óðàaeåíü ïîêàçàâ, ùî àíàòîì³÷íå óðàaeåííÿ äâîõ êîðîíàðíèõ àð-òåð³é ðåºñòðóâàëè îäíàêîâî ÷àñòî, â òîé ÷àñ ÿê óðàaeåííÿ òðüîõ êîðîíàðíèõ àðòåð³é -äåùî ÷àñò³øå â ïà-ö³ºíò³â ñòàðøèõ 70-è ðîê³â. Òàêèì ÷èíîì, àíàë³ç äàíèõ êîðîíàðî´ðàô³¿ ñâ³ä÷èâ ïðî ïåâí³ ïðèíöèïîâ³ îñîáëèâîñò³ àíàòîì³÷íîãî óðàaeåííÿ êîðîíàðíîãî ðóñëà â õâîðèõ ³ç íå Q-³íôàðêòó ì³îêàðäà ð³çíîãî â³êîâîãî öåíçó. Âèñíîâêè. Äîâåäåíà â³äñóòí³ñòü ñóòòºâèõ ãåíäåðíèõ â³äì³ííîñòåé â õàðàêòåð³ àíàòîì³÷íîãî óðàaeåííÿ êîðîíàðíèõ àðòåð³é. Á³ëüø òÿaeê³ àíàòîì³÷í³ óðàaeåííÿ ñïîñòåð³ãàëèñü ó õâîðèõ ³ç íå Q-³íôàðêòîì ì³îêàðäà â³-ÕÀÐÀÊÒÅÐ ÓÐÀAEÅÍÍß ÊÎÐÎÍÀÐÍÎÃÎ ÐÓÑËÀ Ó ÕÂÎÐÈÕ ²Ç ÍÅ Q-²ÍÔÀÐÊÒÎÌ Ì²ÎÊÀÐÄÀ  ÃÅÍÄÅÐÍÎ-²ÊÎÂÎÌÓ ÀÑÏÅÊÒ² ²âàíîâ Â.Ï., Ùåðáàê Î.Â., Ìàñëîâñüêèé Â.Þ. ³ííèöüêîãî íàö³îíàëüíîãî ìåäè÷íîãî óí³âåðñèòåòó ³ì. Ì.². Ïèðîãîâà Êàôåäðà âíóòð³øíüî¿ ìåäèöèíè ¹3 (çàâ. -ïðîô. ²âàíîâ Â.Ï.) ÓÄÊ: 612.1:616.127-005.8:79-055/-053 êîì ñòàðø³ 70-è ðîê³â. Ó ïîð³âíÿíí³ ç á³ëüø ìîëîäèìè ïàö³ºíòàìè öå õàðàêòåðèçóâàëîñü äîñòîâ³ðíèì çá³ëüøåííÿì ÷àñòîòè ðåºñòðàö³¿ îêëþç³é â áàñåéí³ ë³âî¿ êî-ðîíàðíî¿ àðòå𳿠³ ñåðåäíüî¿ äîâaeèíè ñ...
Ìåòà. Âèçíà÷èòè êë³í³êî-ïðî´íîñòè÷íó ðîëü ïëàçìîâîãî ð³âíÿ ñòèìóëþþ÷îãî ôàêòîðó ðîñòó ïðè ð³çí³é ñåðöåâî-ñóäèíí³é ïàòîëî´³¿. Ìàòåð³àë ³ ìåòîäè. Ïðîàíàë³çîâàíî äaeåðåëà ë³òåðàòóðè, ó ÿêèõ âèñâ³òëåíà êë³í³êî-ïðî´íîñòè÷íà ðîëü ïëàçìîâîãî ð³âíÿ ñòèìóëþþ÷îãî ôàêòîðó ðîñòó ïðè ñåðöåâî-ñóäèíí³é ïàòîëî´³¿ Ðåçóëüòàòè é îáãîâîðåííÿ. Àíàë³ç ñó÷àñíî¿ ë³òåðàòóðè çàñâ³ä÷óº ï³äâèùåíó óâàãó â÷åíèõ äî çíà÷åííÿ ³ ðîë³ ð³çíèõ íå³íâàç³éíèõ á³îìàðêåð³â, òàêèõ ÿê òðî-ïîí³í ², íàòð³éóðåòè÷íèé ïåïòèä, ãàëåêòèí-3, ñòè-ìóëþþ÷èé ôàêòîð ðîñòó, ùî åêñïðåñóºòüñÿ ´åíîì 2 (ST2). Îñòàíí³é ST2 º îäíèì ç îñíîâíèõ á³îìàðêåð³â, ùî ñèãíàë³çóº ïðî íàÿâí³ñòü ³ âàaeê³ñòü ñòðóêòóðíîãî ðåìîäåëþâàííÿ ñåðöÿ, íàñàìïåðåä, â ïàö³ºíò³â ç ãîñòðèì ³íôàðêòîì ì³îêàðäà ³ ñåðöåâîþ íåäîñòàò-í³ñòþ. Äîâåäåíî, ùî ST2 âîëî䳺 øèðîêèì ñïåêòðîì á³îëî´³÷íèõ åôåêò³â, çîêðåìà, â³ä³ãðຠâàaeëèâó ðîëü â ïàòî´åíåòè÷íèõ ìåõàí³çìàõ ðîçâèòêó ñåðöåâî-ñóäèííèõ çàõâîðþâàíü. Äàíèé á³îìàðêåð º ïîòóaeíèì ïðåäèêòîðîì ðîçâèòêó ð³çíèõ ñåðöåâî-ñóäèííèõ çàõâîðþâàíü òà ìຠâñ³ õàðàêòåðèñòèêè, ùî äîçâîëÿº ðåêîìåíäóâàòè éîãî âèçíà÷åííÿ äëÿ ïðî´íîçóâàííÿ ñåðöåâî-ñóäèííèõ çàõâîðþâàíü ó ïàö³ºíò³â áåç âèðàaeåíèõ êë³í³÷íèõ ñèìïòîì³â. Âèñíîâîê. Íîâèé á³îìàðêåð ST2 ïîêàçàâ ñåáå â ÿêîñò³ âèñîêî³íôîðìàö³éíîãî ïðî´íîñòè÷íîãî ÷èííèêà ó ïà-ö³ºíò³â ç ãîñòðîþ ³ õðîí³÷íîþ ñåðöåâîþ íåäîñòàò-í³ñòþ ³ ²ÕÑ, âêëþ÷àþ÷è STEMI ³ NSTEMI. Øèðîêå âèêîðèñòàííÿ ïëàçìîâîãî ð³âíÿ ST2 äîçâîëèòü â ïåðñ-ïåêòèâ³ ç âèñîêîþ éìîâ³ðí³ñòþ ïðî´íîçóâàòè ðîçâèòîê ð³çíèõ ñåðöåâî-ñóäèííèõ óñêëàäíåíü ³ ñìåðò³. Çàñòîñóâàííÿ âêàçàíîãî á³îìàðêåðà äຠï³äñòàâè äëÿ ðîçðîáêè ïðîô³ëàêòè÷íèõ çàõîä³â, ñïðÿìîâàíèõ íà ïî-ë³ïøåííÿ ÿêîñò³ aeèòòÿ ïàö³ºíò³â, çìåíøåííÿ åêî-íîì³÷íèõ âèòðàò íà ë³êóâàííÿ ñåðöåâî-ñóäèííèõ çàõâîðþâàíü, à òàêîae çíèaeåííÿ ñìåðòíîñò³ â³ä ñåðöåâî-ñóäèííèõ çàõâîðþâàíü. Êëþ÷îâ³ ñëîâà: á³îìàðêåðè, ñòèìóëþþ÷èé ôàêòîð ðîñòó, ùî åêñïðåñóºòüñÿ ´åíîì 2, ïðî´íîçóâàííÿ ñåðöåâî-ñóäèííèõ óñêëàäíåíü
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.