Search Results (357)

Tuberculosis (TB) is an ancient and re-emerging granulomatous infectious disease that continues to challenge public health. Early diagnosis and prompt effective treatment are crucial for preventing disease progression and reducing both morbidity and mortality. These steps play a vital role in infection control and in lowering death rates at both individual and population levels. Although diagnostic methods have improved sufficiently in recent decades, TB can still present with ambiguous laboratory and imaging features. This ambiguity can lead to diagnostic pitfalls and potentially disastrous outcomes due to delayed diagnosis. In this article, we present a case of TB that was difficult to diagnose. The disease had invaded the mediastinum, right atrium, right coronary artery, and inferior vena cava (IVC), resulting in Budd–Chiari syndrome. This rare presentation created clinical, laboratory, and radiological confusion, resulting in a diagnostic dilemma that ultimately led to open cardiac surgery. The patient initially presented with progressive shortness of breath on exertion and fatigue, which suggested possible heart disease. This suspicion was reinforced by computed tomography (CT) imaging, which showed infiltrative mass lesions predominantly in the right side of the heart, invading the right coronary artery and IVC, with imaging features mimicking angiosarcoma. Although laboratory findings revealed an exudative effusion with lymphocyte predominance and elevated adenosine deaminase (ADA), the Gram stain was negative for bacteria, and an acid-fast bacilli (AFB) smear was also negative. These findings contributed to diagnostic uncertainty and delayed the confirmation of TB. Open surgery with excisional biopsy and histopathological analysis ultimately confirmed TB. We conclude that TB should not be ruled out solely based on negative Mycobacterium bacteria in pericardial effusion or AFB smear. TB can mimic aggressive tumors such as angiosarcoma or lymphoma with invasion of the surrounding tissues and blood vessels. Awareness of the clinical presentation, imaging findings, and potential diagnostic pitfalls of TB is essential, especially in endemic regions. Full article

Background: Pleural mesothelioma (PM) is a type of cancer that is difficult to diagnose and treat. Patients may have vastly varying prognoses, and prognostic factors may help guide the clinical approach. As a recently identified biomarker, the pan-Immune-Inflammation-Value (PIV) is a simple, comprehensive, and peripheral blood cell-based biomarker. Methods: The present study represents a retrospective observational analysis carried out within a single-center setting. Ninety-five patients with PM stages I–IV were enrolled in the study. We analyzed the correlation between patients’ demographic characteristics, clinicopathological factors such as histological subtypes, surgery status, tumor thickness, blood-based parameters, and treatment options with their prognoses. PIV was calculated by the following formula: (neutrophil count × monocyte count × platelet count)/lymphocyte count. Additionally, blood-based parameters were used to calculate the platelet-to-lymphocyte ratio (PLR), neutrophil-to-lymphocyte ratio (NLR), and systemic immune inflammation index (SII). Results: We categorized the patients into two groups, low PIV group (PIV ≤ 732.3) and high PIV group (PIV > 732.3) according to the determined cut-off value, which was defined as the median. It was revealed that high PIV was associated with poor survival outcomes. The median follow-up period was 15.8 months (interquartile range, IQR, 7.1 to 29.8 months). The median overall survival (OS) was significantly longer in patients in the low PIV group (median 29.8 months, 95% confidence interval (CI), 15.6 to 44) than the high PIV group (median 14.7 months, 95% CI, 10.8 to 18.6 p < 0.001). Furthermore, the study revealed that patients with low PIV, NLR, and SII values were more likely to be eligible for surgery and were diagnosed at earlier stages. Additionally, these markers were identified as potential predictors of disease-free survival (DFS) in the surgical cohort and of treatment response across the entire patient population. Conclusions: In addition to well-established clinical factors such as stage, histologic subtype, resectability, and Eastern Cooperative Oncology Group (ECOG) performance status (PS), PIV emerged as an independent and significant prognostic factor of overall survival (OS) in patients with PM. Moreover, PIV also demonstrated a remarkable independent prognostic value for disease-free survival (DFS) in this patient population. Additionally, some clues are provided for conditions such as treatment responses, staging, and suitability for surgery. As such, in this cohort, it has outperformed the other blood-based markers based on our findings. Given its ease of calculation and cost-effectiveness, PIV represents a promising and practical prognostic tool in the clinical management of pleural mesothelioma. It can be easily calculated using routinely available laboratory parameters for every cancer patient, requiring no additional cost or complex procedures, thus facilitating its integration into everyday clinical practice. Full article

Background and Objectives: Flexible ureteroscopic surgery is a common minimally invasive procedure utilized for the management of various urological conditions. While effective, postoperative complications such as fever can occur, necessitating the identification of reliable biomarkers for early detection and management. In this study, we specifically evaluated the predictive performance of three preoperative hematologic indices: the neutrophil-to-lymphocyte ratio (NLR), platelet-to-lymphocyte ratio (PLR), and systemic immune–inflammation index (SII). Materials and Methods: By systematically comparing these biomarkers through receiver operating characteristic (ROC) curve analysis and logistic regression modeling, we aimed to identify the most accurate predictor of postoperative fever development. Our cohort included patients who developed postoperative fever, many of whom exhibited normal WBC counts, allowing us to evaluate the discriminatory power of alternative inflammatory biomarkers. Results: Among the 150 patients, 32 developed postoperative fever. Conventional WBC counts did not predict fever, with 91% of feverish individuals having normal WBC values. In the ROC curve analysis, NLR outperformed SII (AUC 0.847, cutoff 796) and PLR (AUC 0.743, cutoff 106), with an AUC of 0.996 at 2.96. A combined logistic model achieved 100% sensitivity and 91% specificity (AUC = 0.996). Conclusions: This study addresses a critical gap in perioperative monitoring by validating readily available complete blood count-derived ratios as clinically meaningful predictors of postoperative inflammatory responses. Full article

Background: Sternal wound infections (SWIs) remain a significant complication following cardiac surgery. Inflammatory and nutritional status are increasingly recognized as key contributors to their development. This study aimed to investigate the predictive utility of immunonutritional biomarkers and to evaluate the protective effect of combining sternal irrigation with an antibiotic-impregnated membrane. Methods: This retrospective cohort study included 480 patients undergoing off-pump coronary artery bypass grafting. Patients were categorized based on sternal management strategy (standard closure or local prophylaxis using gentamicin-enriched irrigation combined with an antibiotic-impregnated fascia lata membrane) and according to the severity of SWIs, classified as superficial or deep. Inflammatory and nutritional markers—including C-reactive protein (CRP), neutrophils, lymphocytes, albumin, neutrophil-to-lymphocyte ratio (NLR), C-reactive protein-to-albumin ratio (CAR), and prognostic nutritional index (PNI)—were assessed at three time points: preoperatively, on postoperative day 3, and after week 1. Results: SWIs were observed in 93 patients, including 75 superficial and 18 deep infections. The combined prophylactic approach was associated with a nearly 1.8-fold reduction in deep SWIs (OR: 0.55; 95% CI: 0.15–0.87) and a modest reduction in superficial infections (OR: 0.89; 95% CI: 0.5–1.3; p = 0.061). Threshold values of 3.75 for preoperative NLR, 9.8 for ΔNLR, and 16.7 for ΔCAR demonstrated strong predictive capacity for identifying patients at increased risk of developing deep SWIs. Patients receiving local prophylaxis exhibited significantly lower CRP, NLR, and CAR values and higher PNI levels at all time points. Conclusions: The combination of sternal irrigation and local antibiotic prophylaxis appears to confer protection against SWIs, potentially by mitigating postoperative inflammation. Immunonutritional biomarkers offer a promising means for early risk stratification. To confirm their clinical utility and broader applicability, these results should be validated in prospective, multicenter studies encompassing a wider range of cardiac surgical procedures. Full article

This study evaluates the influence of general anesthesia (GA) and spinal anesthesia (SA) on physiological and oxidative stress in parturients undergoing elective cesarean section, one of the most frequently performed surgical procedures worldwide. A total of 101 pregnant women were included, categorized into GA (n = 51) and SA (n = 50) groups. Blood samples were collected at three time points: one hour before surgery (Measurement 1), at umbilical cord clamping (Measurement 2), and two hours post-surgery (Measurement 3). Biomarkers of oxidative stress, complete blood count, and levels of biochemical parameters were measured. In second and/or third measurement, biochemical blood analysis showed increased prolactin and cortisol levels, followed by spike of glucose and insulin in the GA group. However, levels of tri-iodothyronine were reduced in both groups in the third measurement. Glutathione S-transferase (GST) activity was increased in both groups in third measurement. The results showed increased concentrations of total SH groups and decreased concentrations of non-protein SH groups in the GA group during Measurement 2. Lymphocyte count was found to be predictor of GST levels. The results indicate more a pronounced endocrine response in GA group and speak in favor of spinal anesthesia. Both kinds of anesthesia are equally safe in terms of the oxidative status of the tissue. Full article

Background: The benefit of surgery for malignant pleural mesothelioma is highly debated, as few robust clinical trials show its effectiveness. Objective: To examine the long-term survival of patients with malignant pleural mesothelioma who underwent surgical treatment combined with neoadjuvant chemotherapy versus those who received chemotherapy alone. Methods: We analyzed a historical cohort of 122 patients diagnosed with mesothelioma, confirmed through histopathological examination. We compared the clinical and laboratory characteristics of the surgery and chemotherapy groups at baseline. We calculated Kaplan–Meier survival curves and used Cox’s proportional hazards model to evaluate the relationship between surgery and mortality. Results: Surgery was performed in 16 out of 122 cases. Pleurectomy/decortication (PD) represented 8 cases, while extrapleural pneumonectomy (EPP) accounted for the remaining 8 cases. At five years, survival rates for those who underwent surgery compared to chemotherapy alone were 53% (95% CI 15–81%) versus 23% (95% CI 10–40%), respectively. Survival among those who had PD was 67%, compared to 40% for those who had EPP. Surgical treatment was associated with improved survival, with a hazard ratio (HR) of 0.34 (95% CI 0.19–0.61) after adjusting for factors such as age over 65, the duration from symptom onset to diagnosis, hemoglobin levels below 10 g, a neutrophil-to-lymphocyte ratio over 6, and ECOG scores greater than 2. Conclusions: Mesothelioma surgery, whether it be PD or EPP, enhances patients’ survival compared to chemotherapy. PD produces better outcomes than EPP. Full article

Background/Objectives: Primary hyperparathyroidism (PHPT) has been associated with systemic inflammation and metabolic disturbances. This study aimed to evaluate changes in the Systemic Immune-Inflammation Index (SII) and Prognostic Nutritional Index (PNI) following parathyroidectomy (PTX) in PHPT patients, and to assess their return toward healthy control values. Materials and Methods: This retrospective study was conducted between January 2010 and March 2022. It analyzed the demographic characteristics, clinical findings, and laboratory results of patients diagnosed with and operated for PHPT, with comparisons to healthy controls. Postoperative values were recorded at least six months after surgery. Bone mineral density was classified according to World Health Organization criteria, and nephrolithiasis was assessed with imaging. Results: After applying exclusion criteria, 415 PHPT patients and 410 controls were included. PHPT patients were older (p < 0.001) and had a higher proportion of females (p = 0.016). Compared to controls, they had lower phosphorus, albumin, high-density lipoprotein cholesterol, total cholesterol, hemoglobin, and PNI (p < 0.001 for all), while triglycerides, monocytes, platelets, CRP, and SII were higher (p < 0.05). Postoperatively, albumin, platelets, total cholesterol, and triglycerides increased (p < 0.001), while calcium, white blood cell count, neutrophils, lymphocytes, and CRP decreased (p < 0.05), approaching healthy control values. In age- and sex-matched comparisons (propensity score matching, n = 259 in each group), platelets (p = 0.002) and hemoglobin (p = 0.018) were found to be higher postoperatively. Conclusions: Preoperative SII and PNI levels were significantly altered in PHPT patients compared to healthy controls. Following PTX, both of these markers and other parameters showed significant improvements, reflecting positive changes in systemic inflammation and nutritional status. Full article

Background and Objectives: The prognostic nutritional index (PNI), a marker reflecting both nutritional and immune status, has been associated with prognosis in various malignancies. However, evidence in metastatic castration-resistant prostate cancer (mCRPC), particularly from non-Asian populations, remains limited. This study aimed to evaluate the prognostic value of baseline PNI and to develop a blood-based prognostic model in mCRPC patients treated with abiraterone acetate (AA), enzalutamide (ENZA), or cabazitaxel (CABA). Materials and Methods: This retrospective study included mCRPC patients treated with AA, ENZA, or CABA before or after docetaxel. PNI was calculated as: 10 × serum albumin (g/dL) + 0.005 × total lymphocyte count (/mm³). Patients were classified into low-PNI (≤40.8) and high-PNI (>40.8) groups using the median PNI value. Survival outcomes were analyzed using Kaplan–Meier and Cox regression methods. Results: A total of 299 patients were analyzed: 133 (44.5%) received AA, 106 (35.5%) ENZA, and 60 (20.0%) CABA. Patients with high PNI had significantly longer median overall survival (OS; 30.2 vs. 12.6 months, p < 0.001), radiologic progression-free survival (rPFS; 13.5 vs. 6.7 months, p < 0.001), and PSA progression-free survival (PSA-PFS; 10.2 vs. 5.1 months, p < 0.001). These associations remained significant across all treatment subgroups. In multivariate analysis, prostate surgery (HR: 0.6), high PNI (HR: 0.5), PSA response (HR: 0.5), and elevated ALP (HR: 1.6) were independent predictors of OS. A prognostic model incorporating PNI, alkaline phosphatase, and anemia stratified patients into four risk groups with distinct OS: 49.1, 30.8, 18.8, and 9.1 months, respectively. Conclusions: This is the largest study to date in a non-Asian mCRPC population showing that baseline PNI is a strong, independent prognostic factor for survival. The proposed blood-based tool may aid in clinical risk stratification, pending prospective validation. Full article

Background: Pediatric acute appendicitis (AAP) is a common cause of abdominal pain in children, yet accurate classification into negative, uncomplicated, and complicated forms remains clinically challenging. Misclassification may lead to unnecessary surgeries or delayed treatment. This study aims to evaluate and compare the diagnostic accuracy of five machine learning models (AdaBoost, XGBoost, Stochastic Gradient Boosting, Bagged CART, and Random Forest) for classifying pediatric AAP subtypes. Methods: In this retrospective observational study, a dataset of 590 pediatric patients was analyzed. Demographic information and laboratory parameters—including C-reactive protein (CRP), white blood cell (WBC) count, neutrophils, lymphocytes, and appendiceal diameter—were included as features. The cohort consisted of negative (19.8%), uncomplicated (49.2%), and complicated (31.0%) AAP cases. Five ensemble machine learning models (AdaBoost, XGBoost, Stochastic Gradient Boosting, Bagged CART, and Random Forest) were trained on 80% of the dataset and tested on the remaining 20%. Model performance was evaluated using accuracy, sensitivity, specificity, and F1 score, with cross-validation employed to ensure result stability. Results: Random Forest demonstrated the highest overall accuracy (90.7%), sensitivity (100.0%), and specificity (61.5%) for distinguishing negative and uncomplicated AAP cases. Meanwhile, XGBoost outperformed other models in identifying complicated AAP cases, achieving an accuracy of 97.3%, sensitivity of 100.0%, and specificity of 78.3%. The most influential biomarkers were neutrophil count, appendiceal diameter, and WBC levels, highlighting their predictive value in AAP classification. Conclusions: ML models, particularly Random Forest and XGBoost, exhibit strong potential in aiding pediatric AAP diagnosis. Their ability to accurately classify AAP subtypes suggests that ML-based decision support tools can complement clinical judgment, improving diagnostic precision and patient outcomes. Future research should focus on multi-center validation, integrating imaging data, and enhancing model interpretability for broader clinical adoption. Full article

Background/Objectives: Adenocarcinomas of the esophagogastric and gastric areas are often managed with a multimodal treatment including neoadjuvant chemotherapy and surgery. The impact of neoadjuvant chemotherapy on the host’s antitumoral immune response remains largely unknown. Methods: A retrospective review of a single-institution cohort of patients with adenocarcinoma of the stomach or esophagogastric area undergoing curative intent surgery after neoadjuvant chemotherapy FLOT (Fluorouracil, Leucovorin, Oxaliplatin, Docetaxel) was reviewed. After institutional ethics approval, pathologic slides were re-reviewed and tumor-infiltrating lymphocyte scores were calculated. Tumor-infiltrating lymphocytes (TILs) were studied in conjunction with tumor regression scores (TRG) and the degree of regression in the involved lymph nodes as well as in correlation with the lymph node ratio (the ratio of involved lymph nodes over the total number of lymph nodes resected). Results: A total of 106 patients were reviewed. No statistical correlation could be established between the tumor-infiltrating lymphocyte scores and the degree of regression in the primary tumor as well as with the partial response to chemotherapy of pathologically involved lymph nodes. The TIL score also did not correlate with the lymph node ratio in our patient cohort. A strong correlation was noted between TILs and lymph nodes that completely regressed after neoadjuvant chemotherapy. Conclusions: Tumor-infiltrating lymphocytes do not correlate with the response of the primary tumor or the partial response of the involved lymph nodes, but only with the complete response to neoadjuvant chemotherapy of tumor-involved lymph nodes. Our study focuses on the effects of neoadjuvant chemotherapy on tumor-infiltrating lymphocytes compared to the effects on the primary tumor and the involved lymph nodes. Full article

Background: Our study investigated the association between chronic lymphocytic thyroiditis (CLT) and thyroid cancer (TC). Methods: A retrospective review of 1670 patients who underwent thyroid surgery between October 2022 to February 2025 was performed. The clinicopathological characteristics of patients with TC and CLT were collected. CLT was diagnosed histopathologically. Results: Patients with a positive CLT result (60.39%) compared to a negative CLT result (34.12%) had more frequently TC (p < 0.001), predominantly PTC. In univariate analysis, patients with malignancy + CLT-positive compared to malignancy + CLT-negative were found to be younger in age (p < 0.001), female gender (p < 0.001), smaller tumours focus (p = 0. 013), smaller mass of thyroid removed (p < 0.001) and more often Bethesda category V and VI (p = 0.019), true positive fine needle aspiration biopsy (FNAB) for PTC (p = 0.009), and microcarcinoma (p = 0.021). There were no differences in multifocality, the presence of LNM, or the number of LNMs. The location of metastases at neck lymph nodes was at the borderline of significance (p = 0.065). In multivariate analysis, after accounting for Bethesda and age, CLT+ was found to increase the risk of TC by 73% (OR = 1.73; 95%CI, 1.15-2.29), while the risk of PTC increased more than 2-fold (OR = 2.12; 95% CI, 1.45–3.11). CLT had no statistically significant effect on the presence of LNM. Conclusions: We found that CLT is a risk factor for TC. One should be vigilant concerning the coexistence of these two diseases. We suggest that total thyroidectomy should be considered in patients referred for thyroid nodules and suspected CLT. However, this issue requires further research. Full article

Objectives: To evaluate the prognostic value of systemic inflammatory response (SIR) parameters in predicting the recurrence of cervical intraepithelial neoplasia (CIN2+) in women undergoing a loop electrosurgical excision procedure (LEEP). Methods: This retrospective study included women aged ≥18 years who underwent an LEEP at a tertiary center between 2013 and 2023. Patients who were pregnant and those who had malignancies, immune disorders, or prior cervical surgery were excluded. The data collected included age, parity, cervical cytology, HPV DNA status, histology, LEEP specimen size, and preoperative blood count parameters. Follow-up was performed every six months using cytology, colposcopy, and histology to assess recurrence. The SIR markers evaluated included the neutrophil-to-lymphocyte ratio (NLR), lymphocyte-to-monocyte ratio (LMR), platelet-to-lymphocyte ratio (PLR), and lymphocyte count. Statistical analyses included ROC curves and Cox regression. Results: Of the 1068 patients included, 726 had follow-up data, and 32 (4.4%) experienced a recurrence after a mean interval of 24 ± 20 months. Recurrence-negative patients had higher median lymphocyte counts (2.40 vs. 2.15, p = 0.031) and LMRs (4.57 vs. 3.86, p = 0.011). The disease-free survival period was longer in patients with high lymphocyte counts, a low NLR and PLR, and a high LMR. However, the discriminatory power of these markers was limited. In the multivariate analysis, only a PLR > 118.4 remained independently associated with an increased recurrence risk (HR 3.06, p = 0.011). Due to the small number of cases of recurrences and the small amount of HPV DNA results, the findings should be interpreted with caution. Conclusions: Preoperative SIR markers such as the PLR, NLR, LMR, and lymphocyte count showed statistical associations with CIN2+ recurrence after an LEEP, but their clinical utility appears to be limited. Further prospective studies are needed to validate these findings. Full article

Introduction: A potential prognostic biomarker for predicting the response to immunotherapy in breast cancer (BC) is tumor-infiltrating lymphocytes (TILs). The purpose of this research is to examine if preoperative characteristics of breast magnetic resonance imaging (MRI) may be used to predict TIL levels in a group of BC patients. In addition, we aimed to assess any potential relationship between the various tumor biology subgroups and MR imaging characteristics. Materials and Methods: This retrospective analysis comprised 145 participants with histologically confirmed BC who had preoperative DCE MRI. We collected and examined patient information as well as tumor MRI features, such as size and shape, edema, necrosis, multifocality/multicentricity, background parenchymal enhancement (BPE), and apparent diffusion coefficient (ADC) values. We divided patients into two groups based on their TIL levels: low-TIL (<10%) and high-TIL groups (≥10%). Following core needle biopsy, tumors were categorized as Luminal A, Luminal B, HER2+, and Triple Negative using immunohistochemical analysis. TIL levels were correlated with tumor biological profiles and MRI features using both parametric and non-parametric tests. Results: Patients were categorized as having a high TIL level (≥10%; 54/145 patients) and a low TIL level (<10%; 91/145 patients) based on the median TIL level of 10%. Of the lesions, 13 were HER2-positive, 16 were Triple Negative, 49 were Luminal A, and 67 were Luminal B. Higher TIL levels were statistically correlated with TNBC (11/16 individuals, p: 0.007). ADC values (p = 0.01), BPE levels (p = 0.008), and TIL levels were all significantly negatively correlated. Significantly more homogenous enhancement was seen in tumors with elevated TIL levels (p = 0.001). The ADC values and the enhancing characteristics were the most important factors in predicting TIL levels, according to logistic regression analysis, and when combined, they demonstrated the strongest ability to distinguish between the two groups (AUC = 0.744). Conclusions: MRI features, particularly ADC values and enhancement characteristics, may play a pivotal role in the assessment of TIL levels in BC before surgery. This could help patients to better customize treatments to the features of their tumors. Full article

Background and Objectives: Postoperative delirium (POD) is a common complication in elderly patients undergoing major surgery, associated with systemic inflammation and potentially influenced by anesthetic techniques. This study investigated whether remimazolam-based total intravenous anesthesia (R-TIVA) reduces the level of systemic inflammatory biomarkers and the incidence of POD more compared to inhalational anesthesia (IA) or balanced anesthesia (BA) in patients aged ≥ 65 years undergoing major non-neurosurgical, non-cardiac surgery. Materials and Methods: This retrospective cohort study analyzed the medical records of 340 patients categorized by anesthesia type: R-TIVA (n = 111), IA (n = 117), or BA (n = 112). Propensity score matching (PSM) created POD (n = 104) and No POD (n = 106) cohorts. Systemic inflammatory biomarkers—the systemic immune–inflammation index (SII), the neutrophil-to-lymphocyte ratio (NLR), the platelet-to-lymphocyte ratio (PLR), and C-reactive protein (CRP)—were measured pre- and postoperatively. POD was identified by clinical symptoms or the postoperative use of antipsychotics/sedatives. Results: The incidence of POD did not significantly differ among the R-TIVA, IA, and BA groups. However, the postoperative SII, NLR, PLR, and CRP levels were significantly lower in the R-TIVA group compared to those in the IA group (p < 0.05). Both the preoperative (r_pb = 0.72, p < 0.01) and postoperative (r_pb = 0.58, p < 0.01) NLRs were strongly correlated with POD. Higher NLR values predicted the incidence of POD, with odds ratios of 1.71 for preoperative and 1.32 for postoperative measurements. Conclusions: While R-TIVA did not significantly reduce the incidence of POD compared to that of IA or BA, it was associated with reduced levels of postoperative inflammatory biomarkers. The preoperative and postoperative NLRs emerged as strong predictors of POD, suggesting their potential utility in guiding prophylactic strategies for older surgical patients. These findings underscore the interplay between anesthesia type, systemic inflammation, and delirium risk. Full article

Background: Reconstructive surgery with free flaps is a fundamental component in head and neck surgery, but flap failure remains a significant concern. The hemoglobin, albumin, lymphocyte, and platelet (HALP) score is a prognostic factor commonly applied in the evaluation of patients suffering from malignant tumours. This score has emerged as a potential preoperative risk assessment tool; however, its predictive accuracy for free flap failure has not been fully evaluated. The potential of this formula, in the cervical–facial reconstructive area, has not yet been well studied in the international literature. Methods: This retrospective study included patients who had undergone free flap reconstruction in the maxillofacial surgery departments of Perugia and Ancona over the past ten years. To optimize the HALP formula, advanced machine learning technologies, mainly the Julius AI platform, were applied. The HALP formula was refined through three phases: the original formula, a weighted version, and the final “Modified HALP.” Predictive performance was assessed using ROC curve analysis, multivariate logistic regression, and internal validation. Results: The final version of the HALP score, created in the present study, achieved an AUC-ROC of 0.95 (95% CI: 0.91–0.99), outperforming the original and weighted versions. At the optimal cut-off, the final “Modified” HALP score demonstrated 90.91% sensitivity and 92.36% specificity, remaining an independent predictor of flap failure after adjusting for confounders. Conclusions: The aim of the study was to optimize the HALP score by integrating clinical information with the aim of making significant progress in the prediction of failure in reconstructive flaps. The Modified HALP score emerges as a powerful tool for preoperative risk stratification in free flap surgery, potentially improving patient outcomes through targeted interventions. Future research should focus on external validation and exploring the underlying biological mechanisms. Full article