Raul Mihailov

Dr. Raul Mihailov

orcid

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 August 2023 in Journal of Multidisciplinary Healthcare
Verified
Journal Article
Open access
PDF file
GȚGeorge Țocu
George Țocu
RMRaul Mihailov
Raul Mihailov
CSCristina Serban
Cristina Serban
BSBogdan Ioan Stefanescu
Bogdan Ioan Stefanescu
DTDana Tutunaru
Dana Tutunaru
DFDorel Firescu
Dorel Firescu
Background: Sepsis affects over 30 million people worldwide each year, causing approximately 6 million deaths. Challenges in clinical diagnosis and the need for an early diagnosis to prevent mortality due to sepsis have led to dependence on inflammatory biomarkers like Procalcitonin (PCT), C-reactive protein (CRP), and Interleukin-6 (IL-6). Objective: This study was performed to observe the contribution of inflammatory biomarkers in the diagnosis and prognosis of patients with surgical sepsis. Methods: We performed a retrospective observational study in a Clinical Emergency Hospital, which included a number of 125 patients with surgical sepsis admitted between January 2020 and December 2021. The patients were included in the study based on the Sepsis-3 definition. PCT, CRP, IL-6, Sepsis-related Organ Failure Assessment (SOFA) score, Charlson Comorbidity Index (CCI), the time up to surgery, the days of treatment in Intensive Care Unit (ICU) and the total days of hospitalization had been statistically analyzed. Results: The mean age of all patients was 65.14 years. The mean value in all patients for PCT was 20.08 ng/mL, for CRP was 175.42 mg/l, and for IL-6 was 799.6 pg/mL. The strongest correlation between biomarkers was between CRP and IL-6 (r = 0.425; p < 0.0001). Of all biomarkers, the CRP correlated the strongest with patient outcomes (r = 0.544; p < 0.0001). The area under curve (AUC) for the mean values of the inflammatory biomarkers was calculated and the best diagnostic performance was for CRP with 0.816 (95% CI: 0.744– 0.887). Conclusion: CRP and IL-6 were the most efficient in sepsis diagnosis. The association of PCT, CRP and IL-6 has increased the range of certainty in sepsis diagnosis. CRP was the most efficient biomarker in the prognosis of sepsis.

25 April 2024 in Journal of Clinical Medicine
Verified
Journal Article
Open access
PDF file
VLValerii Lutenco
Valerii Lutenco
GȚGeorge Țocu
George Țocu
MGMădălin Guliciuc
Mădălin Guliciuc
MMMonica Moraru
Monica Moraru
ICIuliana Laura Candussi
Iuliana Laura Candussi
RMRaul Mihailov
Raul Mihailov
Background: Ideas about Artificial intelligence appeared about half a century ago, but only now is it becoming an essential element of everyday life. The data provided are becoming a bigger pool and we need artificial intelligence that will help us with its superhuman powers. Its interaction with medicine is improving more and more, with medicine being a domain that continues to be perfected. Materials and Methods: The most important databases were used to perform this detailed search that addresses artificial intelligence in the medical and surgical fields. Discussion: Machine learning, deep learning, neural networks and computer vision are some of the mechanisms that are becoming a trend in healthcare worldwide. Developed countries such as Japan, France and Germany have already implemented artificial intelligence in their medical systems. The help it gives is in medical diagnosis, patient monitoring, personalized therapy and workflow optimization. Artificial intelligence will help surgeons to perfect their skills, to standardize techniques and to choose the best surgical techniques. Conclusions: The goal is to predict complications, reduce diagnostic times, diagnose complex pathologies, guide surgeons intraoperatively and reduce medical errors. We are at the beginning of this, and the potential is enormous, but we must not forget the impediments that may appear and slow down its implementation.

27 August 2025 in Diagnostics
Verified
Journal Article
Open access
PDF file
GȚGeorge Țocu
George Țocu
ELElena Lacramioara Lisa
Elena Lacramioara Lisa
DTDana Tutunaru
Dana Tutunaru
RMRaul Mihailov
Raul Mihailov
CSCristina Serban
Cristina Serban
LMLoredana Matei
Loredana Matei
Background/Objectives: Sepsis is a severe medical condition characterized by a dysregulated host response to infection, with potentially fatal outcomes, requiring early diagnosis and rapid intervention. The limitations of traditional sepsis identification methods, as well as the complexity of clinical data generated in intensive care, have driven increased interest in applying artificial intelligence in this field. The aim of this narrative review article is to analyze how artificial intelligence is being used in the diagnosis and prognosis of sepsis, to present the most relevant current models and algorithms, and to discuss the challenges and opportunities related to integrating these technologies into clinical practice. Methods: We conducted a structured literature search for this narrative review, covering studies published between 2016 and 2024 in databases such as PubMed/Medline, Scopus, Web of Science, IEEE Xplore, and Google Scholar. The review covered models based on machine learning (ML), deep neural networks (DNNs), Recurrent Neural Networks (RNNs), and clinical alert systems implemented in hospitals. The clinical data sources used, algorithms applied, system architectures, and performance outcomes are presented. Results: Numerous artificial intelligence models demonstrated superior performance compared to conventional clinical scores (qSOFA, SIRS), achieving AUC values above 0.90 in predicting sepsis and mortality. Systems such as Targeted Real-Time Early Warning System (TREWS) and InSight have been clinically validated and have significantly reduced the time to treatment initiation. However, challenges remain, such as a lack of model transparency, algorithmic bias, difficulties integrating into clinical workflows, and the absence of external validation in multicenter settings. Conclusions: Artificial intelligence has the potential to transform sepsis management through early diagnosis, risk stratification, and personalized treatment. A responsible, multidisciplinary approach is necessary, including rigorous clinical validation, enhanced interpretability, and training of healthcare personnel to effectively integrate these technologies into everyday practice.

15 September 2023 in Life
Verified
Journal Article
Open access
PDF file
RMRaul Mihailov
Raul Mihailov
Alin Laurentiu TATUAlin Laurentiu TATU
Alin Laurentiu TATU
Elena NiculetElena Niculet
Elena Niculet
IOIulia Olaru
Iulia Olaru
CMCorina Manole
Corina Manole
FSFloris Cristian Stănculea
Floris Cristian Stănculea
Introduction: The Buschke–Löwenstein tumor (BLT) is an uncommon sexually transmitted ailment attributed to the human papillomavirus (HPV)—usually the 6 or 11 type (90%)—with male predominance and an overall infection rate of 0.1%. BLT or giant condyloma acuminatum is recognized as a tumor with localized aggressiveness, displaying distinctive features: the potential for destructive growth, benign histology, a rate of 56% malignant transformation, and a high rate of recurrence after surgical excision. There are several treatment choices which have been tried, including laser, cryotherapy, radiotherapy, electrocoagulation, immunotherapy, imiquimode, sincatechins, intralesional injection of 5-fluoruracil (5-FU), isolated perfusion, and local or systemic chemotherapy. In the case of an extensive tumor, preoperative chemotherapy or radiotherapy is used for tumor shrinkage, making the debulking procedure safer. HPV vaccines significantly decrease the incidence of genital warts, also decreasing the risk of BLT; HPV-6 and HPV-11 are included in these vaccines. Materials and methods: We present a 53-year-old heterosexual man, hospitalized in our department in June 2021 with a typical cauliflower-like tumor mass involving the perianal region, which progressively increased in size for almost 7 years. The perianal mass was completely removed, ensuring negative surgical margins. The large perianal skin defect which occurred was reconstructed with fascio-cutaneous V-Y advancement flap. There was no need for protective stoma. The literature review extended from January 1980 and December 2022, utilizing Pubmed and Google Scholar as search platforms. Results: Due to the disease’s proximity to the anal verge and the limited number of reported cases, arriving at a definitive and satisfactory treatment strategy becomes challenging. The optimal approach entails thorough surgical removal of the lesion, ensuring well-defined surgical margins and performing a wide excision to minimize the likelihood of recurrence. In order to repair the large wound defects, various rotation or advancement flaps can be used, resulting in reduced recovery time and a diminished likelihood of anal stricture or other complications. Our objective is to emphasize the significance of surgical excision in addressing BLT through the presentation of a case involving a substantial perianal condyloma acuminatum, managed successfully with complete surgical removal and the utilization of a V-Y advancement flap technique. In the present case, after 5 months post operation, the patient came back with a buttock abscess, which was incised and drained. After another 5 months, the patient returned for difficult defecation, with an anal stenosis being diagnosed. An anal dilatation and sphincterotomy were carried out, with good postoperative results. Conclusions: The surgical management of Buschke–Löwenstein tumors needs a multidisciplinary team with specialized expertise. The reconstruction techniques involved can be challenging and may introduce additional complications. We consider aggressive surgery, which incorporates reconstructive procedures, as the standard treatment for Buschke–Löwenstein tumors. This approach aims to achieve optimal surgical outcomes and prevent any recurrence.

RMRaul Mihailov
Raul Mihailov
DFDOREL FIRESCU
DOREL FIRESCU
GCGeorgiana Bianca Constantin
Georgiana Bianca Constantin
OMOana Mariana Mihailov
Oana Mariana Mihailov
PHPetre Hoara
Petre Hoara
EPEugenia Panaitescu
Eugenia Panaitescu
Background: The increased rates of postoperative mortality after emergency surgery for obstructive colon cancer (OCC) require the use of risk-stratification scores. The study purpose is to external validate the surgical risk calculator (SRC) and the AFC/OCC score and to create a score for risk stratification. Patients and methods: Overall, 435 patients with emergency surgery for OCC were included in this retrospective study. We used statistical methods suitable for the aimed purpose. Results: Postoperative mortality was 11.72%. SRC performance: strong discrimination (AUC = 0.864) and excellent calibration (11.80% predicted versus 11.72% observed); AFC/OCC score performance: adequate discrimination (AUC = 0.787) and underestimated mortality (6.93% predicted versus 11.72% observed). We identified nine predictors of postoperative mortality: age > 70 years, CHF, ECOG > 2, sepsis, obesity or cachexia, creatinine (aN) or platelets (aN), and proximal tumors (AUC = 0.947). Based on the score, we obtained four risk groups of mortality rate: low risk (0.7%)—0–2 factors, medium risk (12.5%)—3 factors, high risk (40.0%)—4 factors, very high risk (84.4%)—5–6 factors. Conclusions: The two scores were externally validated. The easy identification of predictors and its performance recommend the mortality score of the Clinic County Emergency Hospital of Galați/OCC for clinical use.

29 May 2025 in Life
Verified
Journal Article
Open access
PDF file
VLValerii Lutenco
Valerii Lutenco
ABAdrian Beznea
Adrian Beznea
RMRaul Mihailov
Raul Mihailov
GȚGeorge Țocu
George Țocu
VLVerginia Luțenco
Verginia Luțenco
LBLiliana Baroiu
Liliana Baroiu
Generalized secondary peritonitis is a life-threatening intra-abdominal infection requiring urgent surgical intervention. Despite advances in surgical and antimicrobial therapy, morbidity and mortality remain high. Identifying key prognostic factors is crucial for improving patient outcomes. This review examines significant prognostic indicators and explores the potential role of scoring systems and artificial intelligence in risk stratification. A review was conducted using PubMed, Web of Science, Scopus, and Medline databases. Studies published from 2000 to 2024 focusing on prognostic factors in secondary peritonitis were included. A total of 145 studies were identified, with 40 selected based on relevance and methodological quality. Data extraction included patient demographics, comorbidities, severity scores, microbiological profiles, and artificial intelligence applications in peritonitis management. Poor prognosis was associated with advanced age, severe sepsis, organ failure, chronic kidney disease, cardiovascular comorbidities, and diabetes mellitus. The Mannheim Peritonitis Index (MPI) remains a widely validated prognostic tool, while APACHE II and SOFA scores also provide valuable risk estimates. Increasing multidrug-resistant infections further complicate management and impact outcomes. Emerging evidence suggests that machine learning algorithms may improve early risk stratification and individualized outcome prediction when integrated with conventional scoring systems. Identifying prognostic factors remains essential for optimizing outcomes in secondary peritonitis, and future research should prioritize the clinical validation and integration of AI-based models into perioperative management protocols.