<p>Studija se sastojala od dva dela &ndash; eksperimentalnog i kliničkog. Eksperimentalni deo je sproveden na Fakultetu tehničkih nauka u Novom Sadu na Departmanu za mehanizaciju i konstrukciono ma&scaron;instvo. Trideset dve zglobne povr&scaron;ine gornjeg okrajka golenjače sa pripojem prednje ukr&scaron;tene veze je uzeto tokom totalne aloartroplastike kolena kod trideset dva pacijenta kod kojih je preoperativno načinjena AP i profilna radiografija sa standardnim uvećanjem u cilju merenja veličine kolena a uz prethodno potpisanu saglasnost pacijenata. Zatim je načinjeno trodimenzionalno skeniranje prostorne povr&scaron;ine pripoja prednje ukr&scaron;tene veze na golenjači u odnosu na ravan zglobne povr&scaron;ine golenjače heptičkim uređajem &bdquo;Phantom Omni&reg;&ldquo; radi utvrđivanja korelacije između povr&scaron;ine pripoja prednje ukr&scaron;tene veze na golenjači i veličine platoa golenjače. U eksperimentalni deo su bili uključeni pacijenti oba pola metodom slučajnog izbora kod kojih je ugrađivana totalna proteza kolena a koji su prethodno potpisali informisani pristanak pacijenta na operativni zahvat na Klinici za ortopedsku hirurgiju i traumatologiju Kliničkog centra Vojvodine. Klinički deo studije je bio retrospektivno-prospektivnog karaktera i obuhvatio je ukupno 60 pacijenata izabranih metodom slučajnog izbora od kojih je ispitivanu grupu činilo 30 pacijenata u kojih je do&scaron;lo do ponovne rupture prednje ukr&scaron;tene veze levog ili desnog kolena nakon urađene primarne rekonstrukcije te je načinjena ponovna rekonstrukcija veze, i kontrolnu grupu koju je činilo 30 pacijenata u kojih je zbog rupture prednje ukr&scaron;tene veze načinjena primarna rekonstrukcija nakon koje nije do&scaron;lo do ponovne rupture. Kod svih pacijenata je rekonstrukcija prednje ukr&scaron;tene veze kolena rađena kalemom kost-tetiva-kost. Ishod rekonstrukcije je procenjivan na osnovu Tegner bodovne skale, Lysholm i IKDC bodovne skale za koleno, artrometrijskog merenja Lachman testa, Pivot shift testa, poloţaja kalema i urađeno je poređenje dobijenih rezultata u ispitivanoj (revizionoj) i kontrolnoj grupi. U klinički deo istraţivanja su bili uključeni pacijenti oba pola, ţivotne dobi od 18 do 40 godina koji su operisani na Klinici za ortopedsku hirurgiju i traumatologiju Kliničkog centra Vojvodine u Novom Sadu a koji su dali informisani pristanak za uključivanje. Kriterijumi za isključivanje pacijenata iz kliničkog dela istraživanja su bili životna dob manja od 18 i veća od 40 godina, pojava težih op&scaron;te-hirur&scaron;kih komplikacija i prestanak želje pacijenta da dalje učestvuje u ovom istraživanju. Nakon sveobuhvatne analize dobijenih rezultata istraţivanja, zaključeno je da postoji korelacija između povr&scaron;ine pripoja prednje ukr&scaron;tene veze na golenjači i veličine platoa golenjače. Formula, načinjena matematičko-statističkim metodama za ovo istraživanje, adekvatna je i praktično primenljiva za predikciju povr&scaron;ine pripoja prednje ukr&scaron;tene veze na golenjači u velikom procentu slučajeva a na osnovu samo dva radiografska parametra izmerenih preoperativno &ndash; prednje-zadnjeg i unutra&scaron;nje-spolja&scaron;njeg dijametra platoa golenjače. Kori&scaron;ćenje ove formule može da doprinese pobolj&scaron;anju rezultata hirur&scaron;kog lečenja pacijenata sa pokidanom prednjom ukr&scaron;tenom vezom kolena. Takođe, zaključeno je da je uzrok neuspeha primarne rekonstrukcije multifaktorijalan kao i da nema statistički značajne razlike u ishodu između ispitanika sa dobrom i ispitanika sa lo&scaron;om pozicijom kalema. Potvrđena je pretpostavka da je ishod ponovne rekonstrukcije prednje ukr&scaron;tene veze kolena slabiji u odnosu na ishod primarne.</p> / <p>This study consisted of two parts &ndash; experimental and clinical. Experimental part was conducted at the Department of Mechanization and Design Engineering of The Faculty of Technical Sciences, University of Novi Sad. Thirty two proximal tibial articular surfaces together with the anterior cruciate ligament insertion of thirty two patients were harvested during total knee arthroplasty. All patients had standard preoperative AP and profile radiographs with standard magnification in order to acquire the knee measurements. All patients previously signed the informed consent. The harvested proximal tibial articular surfaces were 3D scanned by a haptic device called &bdquo;Phantom Omni&reg;&ldquo; in order to determine the correlation between the size of the anterior cruciate ligament insertion site and the size of the tibial plateau. Thirty two randomly chosen patients of both sexes which had a knee arthroplasty were included in the experimental part of this study. All of the patients signed the informed consent at The Clinic for Orthopedic Surgery and Traumatology of The Clinical Centre of Vojvodina. The clinical part was a retrospective-prospective study. This part included 60 randomly chosen patients divided into two groups. The test group consisted of 30 patients who had undergone a revision anterior cruciate ligament reconstruction. The control group consisted of 30 patients who had undergone only primary anterior cruciate ligament reconstruction. A bone-tendon-bone graft was used for the reconstruction in all cases. The outcome was assessed by using Tegner activity scale, Lysholm knee scoring scale, IKDC score, arthrometric evaluation, Pivot shift test and the position of the graft. The results were compared between the test group and the control group. The clinical part of the study included 60 patients of both sexes, age 18-40 which were operated at The Clinic for Orthopedic Surgery and Traumatology of The Clinical Centre of Vojvodina. All of the patients signed the informed consent for participation in this study. The exclusion criteria were age under 18 and above 40, occurrence of severe general surgical complications and a patient wish to be excluded from further investigation. After a thorough analysis of the results, we concluded that the correlation between the size of the anterior cruciate ligament tibial insertion site and the size of the tibial plateau exists. Formula which was created for this study by using mathematical and statistical methods, is adequate and practically applicable for the prediction of size of the anterior cruciate ligament tibial insertion site in the majority of cases based on just two preoperative radiographic parameters &ndash; AP and profile diameter of the tibial plateau. The use of this formula may improve the outcome of the anterior cruciate ligament reconstruction. We also concluded that the cause of the primary anterior cruciate ligament reconstruction failure is multifactorial as well as that there is no statistically significant difference between the patients with good and the patients with poor graft position. We confirmed the assumption that the outcome of the revision anterior cruciate ligament reconstruction is poorer than the outcome of the primary anterior cruciate ligament reconstruction.</p>

Les maladies neuromusculaires génétiques (MNMs) sont des maladies rares et à ce titre elles ont été longtemps négligées. À l’heure actuelle, il existe peu de traitements pour les MNMs et ceux-ci sont encore symptomatiques. La prise en charge est donc principalement axée sur l'accompagnement et la prévention des atteintes fonctionnelles. Les mesures rapportées par les patients permettent d'évaluer le bénéfice perçu par les malades concernant leur prise en charge par les services de soins. Les mesures rapportées par les patients sont des indicateurs importants pour juger de l'efficacité des programmes de soins ou de réadaptation fonctionnelle. Pour mesurer la qualité de vie liée à la santé des patients adultes français atteints d'une MNM il n'existait que des outils génériques. Ce travail de doctorat a été réalisé sur les données recueillies dans huit centres de référence sur les MNMs français (Angers, Créteil, Garches, Lille, Nancy, Nice, Paris myologie, Reims) depuis 2006. Il a été réalisé en trois phases successives. Phase I: une analyse principalement qualitative des interactions verbales entre les participants de cinq groupes de discussion de patients atteints d'une MNM a permis de construire une banque d'items. Phase II: une analyse exploratoire principalement quantitative a permis de sélectionner les items de la banque afin de créer un nouveau questionnaire: le QoL-NMD. Phase III: une analyse de confirmation purement quantitative sur un échantillon distinct a permis de vérifier la validité des propriétés psychométriques du questionnaire QoL-NMD. / Due to their rarity genetic neuromuscular diseases (NMDs) have been neglected for a long time. Currently, there are few treatments available for NMDs and they are still symptomatic. The care is thus focus on the support and the prevention of health-related functional limitations. Patient reported outcome measures enable assessing patients' perceived benefit in medical care units. Patient-reported outcome measures are important indicators to assess the efficiency of medical care or rehabilitation programs. Only generic tools were available to measure quality of life for french adult patients with a NMD. This PhD work was carried out using data gathered from eight French NMD reference centers (Angers, Créteil, Garches, Lille, Nancy, Nice, Paris myologie, Reims) since 2006. It was realised into three successive phases. Phase I: a mainly qualitative analysis of verbal interactions between participants of five focus groups composed of patients with a NMD enabled the construction of an item bank. Phase II: a mainly quantitative exploratory analysis enabled to select the items from the bank in order to construct a new questionnaire: the QoL-NMD. Phase III: a purely quantitative confirmatory analysis on an independant sample enabled to verrify the Qol-NMD psychometric properties validity.

Background: Patient reports of pain and function are used to inform the need for and timing of total knee replacement (TKR) and evaluate TKR outcomes. This dissertation compared measurement properties of commonly-used patient surveys in TKR and explored ways to develop more efficient knee-specific function measures. Methods: 1,179 FORCE-TJR patients (mean age=66.1, 61% female) completed questionnaires before and 6 months after TKR. Patient surveys included the knee-specific Knee injury and Osteoarthritis Outcome Score (KOOS) and Western Ontario and McMaster Universities Osteoarthritis Index (WOMAC) and generic SF-36 Health Survey. Tests of KOOS and WOMAC measurement properties included evaluations of scaling assumptions and reliability. Item response theory methods were used to calibrate 22 KOOS function items in one item bank; simulated computerized adaptive tests (CAT) then were used to evaluate shorter function scores customized for each patient. Validity and responsiveness of measures varying in attributes (knee-specific versus generic, longer versus shorter, CAT versus fixed-length) were compared. Results: KOOS and WOMAC scales generally met tests of scaling assumptions, although many pain items were equally strong measures of pain and physical function. Internal consistency reliability of KOOS and WOMAC scales exceeded minimum levels of 0.70 recommended for group-level comparisons across sociodemographic and clinical subgroups. Function items could be calibrated in one item bank. CAT simulations indicated that reliable knee-specific function scores could be estimated for most patients with a 55-86% reduction in respondent burden, but one-third could not achieve a reliable (≥ 0.95) CAT score post-TKR because the item bank did not include enough items vi measuring high function levels. KOOS and WOMAC scales were valid and responsive. Short function scales and CATs were as valid and responsive as longer KOOS and WOMAC function scales. The KOOS Quality of Life (QOL) scale and SF-36 Physical Component Summary discriminated best among groups evaluating themselves as improved, same or worse at 6 months. Conclusions: Results support use of the KOOS and WOMAC in TKR. Improved knee-specific function measures require new items that measure higher function levels. TKR outcomes should be evaluated with a knee-specific quality of life scale such as KOOS QOL, as well as knee-specific measures of pain and function and generic health measures.

<p>U savremenoj hirurgiji imperativ je da hirur&scaron;ka procedura bude efikasna, ali i da obezbedi kvalitetan i brz oporavak. Najbitniji segment operativnog lečenja je obezbediti maksimalan učinak kako bi se osobi omogućio brz i potpun povratak aktivnostima dnevnog života. Posebno je pojačano&nbsp;&nbsp; interesovanje za rekonstrukciju prednjeg ukr&scaron;tenog ligamenta kod mlađe i sporsko aktivne populacije. Trendovi u medicini kao i u ortopedskoj hirurgiji idu u pravcu smanjenja postoperativnog krvarenja, bola i skraćenja postoperativnog oporavka. Supstancija sa antifibrinolitičkim delovanjem, kao &scaron;to je traneksamična kiselina, svakako je na&scaron;la svoje mesto u smanjenju postoperativnog krvarenja. Ciljevi istraživanja su se odnosili na utvrđivanje uticaja lokalno aplikovane traneksamične kiseline tokom rekonstrukcije prednjeg ukr&scaron;tenog ligamenta kolena na postoperativno krvarenje, posmatrane laboratorijske parametre, mere obima kolena, učestalosti postoperativnih komplikacija i kvaliteta postoperativnog oporavka između dve grupe ispitanika (ispitivana i kontrolna grupa). Studija je bila eksprimentalnog karaktera i sprovedena je u Kliničkom centru Vojvodine u Novom Sadu uz odobrenje etičke komisije. U istraživanje, metodom slučajnog izbora, bila su uključena 124 ispitanika oba pola raspoređena u dve grupe (ispitivana i kontrolna), a kod kojih je indikovana operativno zbrinjavanje prekida prednjeg ukr&scaron;tenog ligamenta kolena i koji su dali pristanak da budu uključeni u studiju. Svi prikupljeni podaci su beleženi u protokol, koji je za ovo istraživanje posebno dizajniran. Ispitanici su bili podvrgnuti operativnom zahvatu, uz primenu op&scaron;te ili spinalne anestezije, sa postavljenom pneumatskom poveskom na operisanom ekstremitetu. Ispitivanoj grupi bilo je lokalno aplikovano 20 ml traneksamične kiseline, dok je u kontolnoj grupi na isti način aplikovano 20 ml NaCl 0,9 % rastvora. Postoperativni gubici krvi su praćeni i beleženi tokom 24 h od operacije, dok su laboratorijki nalazi uzorkovani preoperativno i sedmog postoperativnog dana. U posmatranom periodu (preoperativno, sedmog postoperativnog dana, treće i &scaron;este postoperativne nedelje) kod ispitanika je praćen obim kolena i pojava komplikacija (hematom, hemartroza). Nakon sprovedenog istraživanje, prikupljeni podaci su dokumentovani i statistički obrađeni. Rezultati istraživanja jasno ukazuju da postoji statistički značajna razlika (t=7.181, p&lt;0.001) u količni postoperativnog krvarenja između grupa. Prosečno postoperativno krvarenje u ispitivanoj grupi je bilo 71.29&plusmn;40.76 ml, u odnosu na kontrolnu grupu gde je postoperativno krvarenje iznosilo 154.35&plusmn;81.45 ml. U kontrolnoj grupi, postoperativno se beleže niže vrednosti hemoglobina (t=9.608, p&lt;0.001) i hematokrita (t=8.325, p&lt;0.001), i vi&scaron;e vrednosti trombocita (t=2.201, p=0.032) nego u ispitivanoj grupi. Podaci o postoperativnom bolu ispitanika govore u prilog statistički značajnoj razlici u jačini bola prve nedelje nakon operacije između ispitivane i kontrolne grupe (t=2.405, p=0.018) i treće nedelje nakon operacije (t=3.700, p&lt;0.001). U ispitivanoj grupi zabeležena je ređa pojava hematoma 6.45% (n=4), dok je u kontrolnoj grupi 19.35% (n=12). Svi pacijenti u uzorku su popunili upitnik o postoperativnom kvalitetu oporavka. Nije zabeležena statistički značajna razlika u kvalitetu postoperativnog oporavka nakon operacije između dve analizirane grupe ispitanika. Dobijeni rezultati o postoperativnom krvarenju, nakon aplikovane traneksamične kiseline, ukazuju na efikasnost leka i pri lokalnoj primeni tokom rekonstrukcije prednjeg ukr&scaron;tenog ligamenta kolena. S obzirom na insuficijentnost podataka, ovo ispitivanje stvara &scaron;iru osnovu za dalja istraživanja.</p> / <p>In modern surgery, we need an effective surgical procedure, which provides quality and rapid recovery. The most important segment of surgical treatment is to provide maximum impact to allow a person to return quickly and fully to the activities of daily living. There has been particular interest in the reconstruction of the anterior cruciate ligament in the younger and sport active population. Trends in medicine, as well as in orthopedic surgery, are heading towards reducing postoperative bleeding, pain, and postoperative recovery. A substance with antifibrinolytic activity, such as tranexamic acid, has certainly found its place in reducing postoperative bleeding. The objectives of the study were to determine the effect of locally applied tranexamic acid during the reconstruction of the anterior cruciate knee ligament on postoperative bleeding, observed laboratory parameters, measures of knee circumference, frequency of postoperative complications, and quality of postoperative recovery between the two groups of subjects (study and control group). The study was prospective, conducted at the Clinical Center of Vojvodina in Novi Sad with the approval of the ethics committee. The study, by random selection method, included 124 subjects of both sexes, divided into two groups (tested and control), which indicated operative management of the anterior cruciate ligament rupture and gave informed consent for inclusion in the study. All data collected were recorded in a protocol, which was specifically designed for this research. Subjects underwent surgery, with general or spinal anesthesia, with pneumatic attachment placed on the extremity undergoing surgery. The test group was given topically 20 ml of tranexamic acid, while the control group was administered 20 ml in the same way. NaCl 0.9% solution. Postoperative blood losses were monitored and recorded within 24 h of surgery, while laboratory findings were sampled preoperatively and on the seventh postoperative day. During the observed period (preoperatively, on the seventh postoperative day, on the third and sixth postoperative weeks), the knee volume and the occurrence of complications (hematoma, hemarthrosis) were monitored in the subjects. Following the survey, the data collected were documented and statistically processed. The study results indicate that there was a statistically significant difference (t = 7.181, p &lt;0.001) in the amount of postoperative bleeding between groups. The mean postoperative bleeding in the study group was 71.29 &plusmn; 40.76 ml, compared to the control group where postoperative bleeding was 154.35 &plusmn; 81.45ml. In the control group, lower hemoglobin values (t = 9.608, p &lt;0.001) and hematocrit (t = 8.325, p &lt;0.001) were observed postoperatively, and higher platelet counts (t = 2.201, p = 0.032) than in the study group. The data on the postoperative pain of the respondents support a statistically significant difference in the severity of pain on the first week after surgery between the study and the control group (t = 2.405, p = 0.018) and the third week after surgery (t = 3.700, p &lt;0.001). In the study group, the incidence of hematoma was less than 6.45% (n = 4), while in the control group it was 19.35% (n = 12). All patients in the sample completed a questionnaire on postoperative quality of recovery. There was no statistically significant difference in the quality of postoperative recovery after surgery between the two analyzed groups of subjects. The results of post-operative bleeding, after administrated tranexamic acid, indicate the efficacy of the drug and at a local application during the reconstruction of the anterior cruciate ligament. Due to the insufficiency of data, this study creates a broad basis for further research.</p>

<p>Uvod: Stratifikacija rizika je postala integralna komponenta savremenog pristupa tretmanu u kliničkoj praksi. Danas se u dijagnostici i lečenju akutnog infarkta miokarda (AIM) koriste različiti skorovi rizika kao prognostički instrumenti za kratkoročan i dugoročan ishod bolesti. Nužni proceduralni procesi, u toku primarne perkutane koronarne intervencije (pPKI), kao i saznanja o distribuciji i vrstama lezija koronarnih arterija su od velikog značaja, te se preporučuje finalna evaluacija rizika neposredno nakon izvr&scaron;ene pPKI. Metode istraživanja podataka omogućavaju pronalaženje skrivenih obrazaca u podacima, otkrivanje njihovih uzročno-posledičnih veza I odnosa, te razvoj savremenih prediktivnih modela. Cilj: Kreiranje i testiranje jednostavnog, praktičnog i u svakodnevnoj praksi upotrebljivog prediktivnog modela za procenu intra-hospitalnog ishoda lečenja pacijenata obolelih od AIM sa ST-elevacijom (STEMI) lečenih pPKI. Metode: Istraživanje je unicentrična, retrospektivna, ali I prospektivna studija. U retrospektivnu studiju je uključeno 1495 pacijenta sa STEMI koji su lečeni na Klinici za kardiologiju Instituta za kardiovaskularne bolesti Vojvodine (IKVBV) kod kojih je u cilju rekanalizacije infarktne arterije izvr&scaron;ena pPKI, u periodu od decembra 2008. godine do decembra 2011. godine. Svaki pacijent je inicijalno predstavljen sa 629 obeležja sadržanih u postojećem IKVBV informacionom sistemu, koja čine demografske karakteristike, podaci iz anamneze i kliničkog nalaza, parametri biohemijskih analiza krvi priprijemu, parametri ehokardiografskog pregleda, angiografski i proceduralni detalji i &scaron;ifre prijemnih dijagnoza. U svrhu istraživanja podataka kori&scaron;ćeno je programsko re&scaron;enje otvorenog koda Weka. Tokom evaluacije različitih algoritama izabran je algoritam koji daje najbolje rezultate po tačnosti predikcije i ROC parametru. U sklopu retrospektivnog dela izvr&scaron;ena je validacija prediktivnog modela&nbsp; desetostrukom unakrsnom validacijom na celom skupu podataka. Prospektivnom studijom je na uzorku od 400 pacijenata sa STEMI lečenih pPKI u toku 2015. godine izvr&scaron;ena dodatna validacija razvijenog prediktivnog modela. Za iste pacijente je izračunavat i GRACE skor rizika, te je upoređena njegova, i prediktivna moć razvijenog modela. Rezultati: Alternativno stablo odluke (ADTree) izdvojen je kao algoritam sa najboljim performansama u odnosu na ostale evaluirane algoritme. Cost sensitive klasifikacija je kori&scaron;ćena kao dodatna metodologija da bi se pojačala tačnost. ADTree stablo odluke izdvojilo je osam ključnih parametara koji najvi&scaron;e utiču na ishod intra-hospitalnog lečenja: sistolni krvni pritisak pri prijemu, ejekciona frakcija leve komore, udarni volumen leve komore, troponin, kreatinin fosfokinaza, ukupni bilirubin, T talas i<br />rezultat intervencije. Performanse razvijenog modela su: tačnost predikcije je 93.17%, ROC 0.94. Razvijeni model je na prospektivnoj validaciji zadržao performanse: tačnost predikcije 90.75%, ROC 0.93. &Scaron;iroko kori&scaron;ćeni GRACE skor je na prospektivnom skupu postigao ROC=0.86, &scaron;to pokazuje da je razvijeni prediktivni model superiorniji u odnosu na njega. Zaključak: Razvijeni prediktivni model je jednostavan i pouzdan. Njegova implementacija u svakodnevnu kliničku praksu, omogućila bi kliničarima da izdvoje visokorizične pacijente, nakon reperfuzionog tretmana, a potom kod njih intenziviraju tretman i kliničko praćenje, a sa ciljem smanjenja incidence intra-hospitalnih komplikacija i povećanja njihovog preživljavanja.</p> / <p>Introduction: Risk stratification has become an integral component of modern treatment in clinical practice. Today, the diagnosis and treatment of acute myocardial infarction (AMI) use different risk scores as a prognostic instruments for short-term and long-term outcome of the disease. The necessary procedural processes during primary percutaneous coronary intervention (pPCI) as well as knowledge about the distribution and types of lesions in coronary arteries are of great importance, and a final risk evaluation is recommended directly after the pPCI. Methods of data mining allow finding hidden patterns in data, disclosure of their causal connections and relationships, and the development of modern predictive models. Aim: To create and test a simple, practical and usable predictive model in daily practice for the&nbsp; assessment of intrahospital treatment outcome of patients with AMI with STsegment elevation (STEMI) treated with pPCI. Methods: Presented research is unicentric, retrospective but also prospective study. Retrospective study included 1495 patients with STEMI who were admitted to the Clinics of cardiology of the Institute of Cardiovascular Diseases Vojvodina (IKVBV). For the purpose of recanalization of the infarct artery, pPCI has been performed to these patients during the period from December 2008 to December 2011. Each patient was initially described with 629 attributes from the existing information system of IKVBV. Those attributes consist of demographic characteristics, data from history and clinical findings, biochemical parameters of blood tests on admission, the echocardiographic parameters, angiographic and procedural details and admission diagnosis codes. For model development, an open source software solution Weka was used. During the evaluation of different algorithms, algorithm that gives the best results in terms of accuracy and ROC parameter was chosen. As part of the retrospective study, in order to assess the models performance, ten-fold cross-validation on the entire data set was used. A prospective study, on a sample of 400 patients with STEMI, treated with pPCI in 2015, performed additional validation of the developed predictive model. GRACE risk score was calculated for the prospective study patients and comparison with the developed model has been performed. Results: Alternative decision tree (ADTree) was isolated as an algorithm with the best performance in relation to other algorithms evaluated. Cost sensitive classification was used as an additional methodology to enhance accuracy. ADTree selected eight key parameters that most influence the outcome of intra-hospital treatment: systolic blood pressure on admission, left ventricular ejection fraction, stroke volume of the left ventricle, troponin, creatine phosphokinase, total bilirubin, T wave and the result of the intervention. The performance of the developed model are: the accuracy of the prediction is 93.17%, ROC 0.94. The developed model kept its performance in prospective validation: accuracy of prediction 90.75%, ROC 0.93. Widely used GRACE score achieved ROC = 0.86 in the prospective study patients, indicating that developed predictive model is superior to him. Conclusion: Developed predictive model is simple and reliable. Its implementation in everyday clinical practice, would allow clinicians to distinguish high-risk patients after reperfusion treatment, and then for them to intensify treatment and clinical follow-up, with an aim of reducing the incidence of intra-hospital complications and increase their survival.</p>