A Prospective Study on the Progression, Recurrence, and Regression of Cervical Lesions: Assessing Various Screening Approaches.

(1) Background: The prediction of cervical lesion evolution is a challenge for clinicians. This prospective study aimed to determine and compare the predictive accuracy of cytology, HPV genotyping, and p16/Ki67 dual staining alone or in combination with personal risk factors in the prediction of progression, regression, or persistence of cervical lesions in human papillomavirus (HPV)-infected patients; (2) Methods: This prospective study included HPV-positive patients with or without cervical lesions who underwent follow-up in a private clinic. We calculated the predictive performance of individual tests (cervical cytology, HPV genotyping, CINtecPlus results, and clinical risk factors) or their combination in the prediction of cervical lesion progression, regression, and persistence; (3) Results: The highest predictive performance for the progression of cervical lesions was achieved by a model comprising a Pap smear suggestive of high-grade squamous intraepithelial lesion (HSIL), the presence of 16/18 HPV strains, a positive p16/Ki67 dual staining result along with the presence of at least three clinical risk factors, which had a sensitivity (Se) of 74.42%, a specificity of 97.92%, an area under the receiver operating curve (AUC) of 0.961, and an accuracy of 90.65%. The prediction of cervical lesion regression or persistence was modest when using individual or combined tests; (4) Conclusions: Multiple testing or new biomarkers should be used to improve HPV-positive patient surveillance, especially for cervical lesion regression or persistence prediction.

Machine Learning-Based Algorithms for Enhanced Prediction of Local Recurrence and Metastasis in Low Rectal Adenocarcinoma Using Imaging, Surgical, and Pathological Data.

(1) Background: Numerous variables could influence the risk of rectal cancer recurrence or metastasis, and machine learning (ML)-based algorithms can help us refine the risk stratification process of these patients and choose the best therapeutic approach. The aim of this study was to assess the predictive performance of 4 ML-based models for the prediction of local recurrence or distant metastasis in patients with locally advanced low rectal adenocarcinomas who underwent neoadjuvant chemoradiotherapy and surgical treatment; (2) Methods: Patients who were admitted at the first Oncologic Surgical Clinic from the Regional Institute of Oncology, Iasi, Romania were retrospectively included in this study between November 2019 and July 2023. Decision tree (DT), naïve Bayes (NB), support vector machine (SVM), and random forest (RF) were used to analyze imagistic, surgical, and pathological data retrieved from the medical files, and their predictive performance was assessed; (3) Results: The best predictive performance was achieved by RF when used to predict disease recurrence (accuracy: 90.85%) or distant metastasis (accuracy: 89.63%). RF was closely followed by SVM (accuracy for recurrence 87.8%; accuracy for metastasis: 87.2%) in terms of predictive performance. NB and DT achieved moderate predictive power for the evaluated outcomes; (4) Conclusions: Complex algorithms such as RF and SVM could be useful for improving the prediction of adverse oncological outcomes in patients with low rectal adenocarcinoma.

Predicting the Feasibility of Curative Resection in Low Rectal Cancer: Insights from a Prospective Observational Study on Preoperative Magnetic Resonance Imaging Accuracy.

Background and Objectives: A positive pathological circumferential resection margin is a key prognostic factor in rectal cancer surgery. The point of this prospective study was to see how well different MRI parameters could predict a positive pathological circumferential resection margin (pCRM) in people who had been diagnosed with rectal adenocarcinoma, either on their own or when used together. Materials and Methods: Between November 2019 and February 2023, a total of 112 patients were enrolled in this prospective study and followed up for a 36-month period. MRI predictors such as circumferential resection margin (mCRM), presence of extramural venous invasion (mrEMVI), tumor location, and the distance between the tumor and anal verge, taken individually or combined, were evaluated with univariate and sensitivity analyses. Survival estimates in relation to a pCRM status were also determined using Kaplan-Meier analysis. Results: When individually evaluated, the best MRI predictor for the detection of a pCRM in the postsurgical histopathological examination is mrEMVI, which achieved a sensitivity (Se) of 77.78%, a specificity (Sp) of 87.38%, a negative predictive value (NPV) of 97.83%, and an accuracy of 86.61%. Also, the best predictive performance was achieved by a model that comprised all MRI predictors (mCRM+ mrEMVI+ anterior location+ < 4 cm from the anal verge), with an Se of 66.67%, an Sp of 88.46%, an NPV of 96.84%, and an accuracy of 86.73%. The survival rates were significantly higher in the pCRM-negative group (p < 0.001). Conclusions: The use of selective individual imaging predictors or combined models could be useful for the prediction of positive pCRM and risk stratification for local recurrence or distant metastasis.

Prediction of Intrauterine Growth Restriction and Preeclampsia Using Machine Learning-Based Algorithms: A Prospective Study.

(1) Background: Prenatal care providers face a continuous challenge in screening for intrauterine growth restriction (IUGR) and preeclampsia (PE). In this study, we aimed to assess and compare the predictive accuracy of four machine learning algorithms in predicting the occurrence of PE, IUGR, and their associations in a group of singleton pregnancies; (2) Methods: This observational prospective study included 210 singleton pregnancies that underwent first trimester screenings at our institution. We computed the predictive performance of four machine learning-based methods, namely decision tree (DT), naïve Bayes (NB), support vector machine (SVM), and random forest (RF), by incorporating clinical and paraclinical data; (3) Results: The RF algorithm showed superior performance for the prediction of PE (accuracy: 96.3%), IUGR (accuracy: 95.9%), and its subtypes (early onset IUGR, accuracy: 96.2%, and late-onset IUGR, accuracy: 95.2%), as well as their association (accuracy: 95.1%). Both SVM and NB similarly predicted IUGR (accuracy: 95.3%), while SVM outperformed NB (accuracy: 95.8 vs. 94.7%) in predicting PE; (4) Conclusions: The integration of machine learning-based algorithms in the first-trimester screening of PE and IUGR could improve the overall detection rate of these disorders, but this hypothesis should be confirmed in larger cohorts of pregnant patients from various geographical areas.

Investigating the Association between Serum and Hematological Biomarkers and Neonatal Sepsis in Newborns with Premature Rupture of Membranes: A Retrospective Study.

(1) Background: Neonatal early-onset sepsis (EOS) is associated with important mortality and morbidity. The aims of this study were to evaluate the association between serum and hematological biomarkers with early onset neonatal sepsis in a cohort of patients with prolonged rupture of membranes (PROM) and to calculate their diagnostic accuracy. (2) Methods: A retrospective cohort study was conducted on 1355 newborns with PROM admitted between January 2017 and March 2020, who were divided into two groups: group A, with PROM ≥ 18 h, and group B, with ROM < 18 h. Both groups were further split into subgroups: proven sepsis, presumed sepsis, and no sepsis. Descriptive statistics, analysis of variance (ANOVA) and a Random Effects Generalized Least Squares (GLS) regression were used to evaluate the data. (3) Results: The statistically significant predictors of neonatal sepsis were the high white blood cell count from the first (p = 0.005) and third day (p = 0.028), and high C-reactive protein (CRP) values from the first day (p = 0.004). Procalcitonin (area under the curve-AUC = 0.78) and CRP (AUC = 0.76) measured on the first day had the best predictive performance for early-onset neonatal sepsis. (4) Conclusions: Our results outline the feasibility of using procalcitonin and CRP measured on the first day taken individually in order to increase the detection rate of early-onset neonatal sepsis, in the absence of positive blood culture.

Oncolytic Virotherapy: A New Paradigm in Cancer Immunotherapy.

Oncolytic viruses (OVs) are emerging as potential treatment options for cancer. Natural and genetically engineered viruses exhibit various antitumor mechanisms. OVs act by direct cytolysis, the potentiation of the immune system through antigen release, and the activation of inflammatory responses or indirectly by interference with different types of elements in the tumor microenvironment, modification of energy metabolism in tumor cells, and antiangiogenic action. The action of OVs is pleiotropic, and they show varied interactions with the host and tumor cells. An important impediment in oncolytic virotherapy is the journey of the virus into the tumor cells and the possibility of its binding to different biological and nonbiological vectors. OVs have been demonstrated to eliminate cancer cells that are resistant to standard treatments in many clinical trials for various cancers (melanoma, lung, and hepatic); however, there are several elements of resistance to the action of viruses per se. Therefore, it is necessary to evaluate the combination of OVs with other standard treatment modalities, such as chemotherapy, immunotherapy, targeted therapies, and cellular therapies, to increase the response rate. This review provides a comprehensive update on OVs, their use in oncolytic virotherapy, and the future prospects of this therapy alongside the standard therapies currently used in cancer treatment.

Pregnancy Outcomes in Patients with Urosepsis and Uncomplicated Urinary Tract Infections-A Retrospective Study.

Background and Objectives: Urinary tract infections (UTIs) are an important cause of perinatal and maternal morbidity and mortality. The aim of this study was to describe and compare the main pregnancy outcomes among pregnant patients with complicated and uncomplicated UTIs; Materials and Methods: This retrospective study included 183 pregnant patients who were evaluated for uncomplicated UTIs and urosepsis in the Urology Department of 'C.I. Parhon' University Hospital, and who were followed up at a tertiary maternity hospital-'Cuza-voda' from Romania between January 2014 and October 2023. The control group (183 patients) was randomly selected from the patient's cohort who gave birth in the same time frame at the maternity hospital without urinary pathology. Clinical and paraclinical data were examined. Descriptive statistics and a conditional logistic regression model were used to analyze our data. Results: Our results indicated that patients with urosepsis had increased risk of premature rupture of membranes (aOR: 5.59, 95%CI: 2.02-15.40, p < 0.001) and preterm birth (aOR: 2.47, 95%CI: 1.15-5.33, p = 0.02). We could not demonstrate a statistically significant association between intrauterine growth restriction and pre-eclampsia with the studied urological pathologies. Conclusions: Careful UTI screening during pregnancy is needed for preventing maternal-fetal complications.

Theoretical-Experimental Approach of Chitosan/Quaternized Chitosan Nanofibers' Behavior in Wound Exudate Media.

This study aimed to investigate the behavior of chitosan/quaternized chitosan fibers in media mimicking wound exudates to understand their capacities as wound dressing. Fiber analysis of the fibers using dynamic vapor sorption proved their ability to adsorb moisture up to 60% and then to desorb it as a function of humidity, indicating their outstanding breathability. Dissolution analyses showed that quaternized chitosan leached from the fibers in water and PBS, whereas only small portions of chitosan were solubilized in water. In media containing lysozyme, the fibers degraded with a rate determined by their composition and pH, reaching a mass loss of up to 47% in media of physiologic pH. Notably, in media mimicking the wound exudate during healing, they adsorbed moisture even when their mass loss due to biodegradation was high, whereas they were completely degraded in the media of normal tissues, indicating bioabsorbable dressing capacities. A mathematical model was constructed, which characterized the degradation rate and morphology changes of chitosan/quaternized chitosan fibers through analyses of dynamics in scale space, using the Theory of Scale Relativity. The model was validated using experimental data, making it possible to generalize it to the degradation of other biopolymeric systems that address wound healing.

The Effects of Perilla frutescens Extracts on IgA Nephropathy: A Systematic Review and Meta-Analysis.

(1) Background: Chronic renal disorders (CRD) are associated with significant comorbidities and necessitate complex therapeutic management. As time passed, Perilla frutescens (PF) became a promising therapeutic option for CRD. The aim of this systematic review and meta-analysis was to outline the therapeutic effects of PF extracts on various models of immunoglobulin a (IgA) nephropathy; (2) Methods: Medline, Embase, and Cochrane databases were used to find relevant studies. All prospective interventional studies that evaluated the effect of PF extract versus placebo on rat models of chronic renal disorders were assessed according to the international guidelines; (3) Results: Our search yielded 23 unique records, out of which only five were included in the analysis. Our results showed that administration of PF extracts led to a statistically significant reduction in proteinuria and PCNA levels in rats that received high doses of the extract as well as in the PCNA level and DNA synthesis in rats that received low doses of the extract. The evaluated outcomes benefited from a low degree of heterogeneity; (4) Conclusions: Some of the evaluated outcomes were significantly reduced by both high and low doses of extracts from Perilla frutescens. Further studies are needed to determine the exact effect over IgA nephropathy in human subjects.

Maternal Fever and Reduced Fetal Movement as Predictive Risk Factors for Adverse Neonatal Outcome in Cases of Congenital SARS-CoV-2 Infection: A Meta-Analysis of Individual Participant Data from Case Reports and Case Series.

OBJECTIVES: To determine risk factors for primary and secondary adverse neonatal outcomes in newborns with congenital SARS-CoV-2 infection. DATA SOURCES: PubMed/MEDLINE and Google Scholar from January 2020 to January 2022. STUDY ELIGIBILITY CRITERIA: newborns delivered after 24 weeks of gestation with confirmed/possible congenital SARS-CoV-2 infection, according to standard classification criteria. METHODS: Execution of the IPD analyses followed the PRISMA-IPD statement. Univariate non-parametric tests compared numerical data distributions. Fisher's exact or Chi-square test determined categorical variables' statistical significance. Multivariate logistic regression revealed risk factors for adverse neonatal outcome. RESULTS: Maternal fever was associated with symptomatic congenital infection (OR: 4.55, 95% CI: 1.33-15.57). Two-thirds of women that reported decreased fetal movements were diagnosed with IUFD (p-value = 0.001). Reduced fetal movement increased the risk of intrauterine fetal death by 7.84 times (p-value = 0.016, 95% CI: 2.23-27.5). The risk of stillbirth decreased with gestational age at the time of maternal infection (p-value < 0.05, OR: 0.87, 95% CI: 0.79-0.97). CONCLUSIONS: Maternal fever and perception of reduced fetal movement may be predictive risk factors for adverse pregnancy outcome in cases with congenital SARS-CoV-2 infection.

COVID-19 in Pregnant Patients at Term: Evolution of Coagulation Factors in Mild Forms throughout the Pandemic: Conventional Analysis and Logistic Regression.

Aim: The evolution of coagulation factors in pregnant patients infected with SARS-CoV-2 during the pandemic is still debated. However, few studies have been carried out to evaluate the silent alterations of blood values in mild forms of the disease. Methods:A total of 153 pregnant patients with an asymptomatic form of COVID-19 and 306 healthy pregnant patients, who were admitted for delivery in our hospital between April 1, 2020 and March 1, 2022, were studied. The blood values harvested closest to the time of delivery were considered. Results:There was a significant variability in values of fibrinogen, prothrombin time, though these were still within normal limits. Conclusions:Pregnant patients with mild forms of COVID-19 displayed some blood alterations, even if they were asymptomatic for COVID-19.

Predicting Preterm Birth with Strain Ratio Analysis of the Internal Cervical Os: A Prospective Study.

(1) Background: Cervical elastography is a new concept that could allow clinicians to assess cervical consistency in various clinical scenarios. We aimed to evaluate the predictive performance of the strain ratio (SR) at the level of the internal os, either individually or in combination with other parameters, in the prediction of spontaneous preterm birth (PTB) at various gestational ages. (2) Methods: This prospective study included 114 pregnant patients with a high-risk profile for PTB who underwent cervical elastography during the second trimester. Clinical and paraclinical data were assessed using univariate analysis, logistic regression, and sensitivity analysis. (3) Results: The SR achieved an area under the receiver operating curve (AUROC) value of 0.850, a sensitivity of 85.71%, and a specificity of 84.31% in the prediction of PTB before 37 weeks of gestation. The combined model showed superior results in terms of accuracy (AUROC = 0.938), sensitivity (92.31%), and specificity (95.16%). When considering PTB subtypes, the highest AUROC value (0.80) and accuracy (95.61%) of this marker were achieved in the prediction of extremely preterm birth, before 28 weeks of gestation. (4) Conclusions: The SR achieved an overall good predictive performance in the prediction of PTB and could be further evaluated in various cohorts of patients.

Unraveling the Efficacy of Therapeutic Interventions for Short Cervix: Insights from a Retrospective Study for Improved Clinical Management.

Background and Objectives: Preterm birth (PTB) is associated with important neonatal mortality and morbidity. The aim of this study was to retrospectively evaluate the average treatment effects on the treated and the efficacity of various therapeutic interventions for PTB in a cohort of patients with singleton pregnancies and short cervical lengths. Materials and Methods: This observational retrospective study included 1146 singleton pregnancies at risk of PTB that were segregated into the following groups: intravaginal progesterone (group 1), Arabin pessary (group 2), McDonald cerclage (group 3), intravaginal progesterone and Arabin pessary (group 4), and intravaginal progesterone and cerclage (group 5). Their treatment effects were evaluated and compared. Results: All evaluated therapeutic interventions significantly reduced the occurrence of late and early preterm births. The risk of late and early PTB was lowered for those pregnant patients who received progesterone and pessaries or progesterone and cerclage in comparison with those who received only progesterone. The extremely PTB risk of occurrence was significantly lowered only by the administration of progesterone in association with cervical cerclage in comparison with progesterone monotherapy. Conclusions: The combined therapeutic interventions had the highest efficacy in preventing preterm birth. An individualized evaluation is needed to establish the best therapeutic approach in particular cases.

Managing Fetal Ovarian Cysts: Clinical Experience with a Rare Disorder.

Background and Objectives: Fetal ovarian cysts (FOCs) are a very rare pathology that can be associated with maternal-fetal and neonatal complications. The aim of this study was to assess the influence of ultrasound characteristics on FOC evolution and therapeutic management. Materials and Methods: We included cases admitted to our perinatal tertiary center between August 2016 and December 2022 with a prenatal or postnatal ultrasound evaluation indicative of FOC. We retrospectively analyzed the pre- and postnatal medical records, sonographic findings, operation protocols, and pathology reports. Results: This study investigated 20 cases of FOCs, of which 17 (85%) were diagnosed prenatally and 3 (15%) postnatally. The mean size of prenatally diagnosed ovarian cysts was 34.64 ± 12.53 mm for simple ovarian cysts and 55.16 ± 21.01 mm for complex ovarian cysts (p = 0.01). The simple FOCs ≤ 4 cm underwent resorption (n = 7, 70%) or size reduction (n = 3, 30%) without complications. Only 1 simple FOC greater than 4 cm reduced its size during follow-up, while 2 cases (66.6%) were complicated with ovarian torsion. Complex ovarian cysts diagnosed prenatally underwent resorption in only 1 case (25%), reduced in size in 1 case (25%), and were complicated with ovarian torsion in 2 cases (50%). Moreover, 2 simple (66.6%) and 1 complex (33.3%) fetal ovarian cysts were postnatally diagnosed. All of these simple ovarian cysts had a maximum diameter of ≤4 cm, and all of them underwent size reduction. The complex ovarian cyst of 4 cm underwent resorption during follow-up. Conclusions: Symptomatic neonatal ovarian cysts, as well as those that grow in size during sonographic follow-up, are in danger of ovarian torsion and should be operated on. Complex cysts and large cysts (with >4 cm diameter) could be followed up unless they become symptomatic or increase in dimensions during serial ultrasounds.

Pregnancy Outcomes, Immunophenotyping and Immunohistochemical Findings in a Cohort of Pregnant Patients with COVID-19-A Prospective Study.

(1) Background: SARS-CoV-2 infection during pregnancy could determine important maternal and fetal complications. We aimed to prospectively assess placental immunohistochemical changes, immunophenotyping alterations, and pregnancy outcomes in a cohort of patients with COVID-19; (2) Methods: 52 pregnant patients admitted to a tertiary maternity center between October 2020 and November 2021 were segregated into two equal groups, depending on the presence of SARS-CoV-2 infection. Blood samples, fragments of umbilical cord, amniotic membranes, and placental along with clinical data were collected. Descriptive statistics and a conditional logistic regression model were used for data analysis; (3) Results: Adverse pregnancy outcomes such as preterm labor and neonatal intensive care unit admission did not significantly differ between groups. The immunophenotyping analysis indicated that patients with moderate-severe forms of COVID-19 had a significantly reduced population of T lymphocytes, CD4+ T cells, CD8+ T cells (only numeric), CD4+/CD8+ index, B lymphocytes, and natural killer (NK) cells. Our immunohistochemistry analysis of tissue samples failed to demonstrate positivity for CD19, CD3, CD4, CD8, and CD56 markers; (4) Conclusions: Immunophenotyping analysis could be useful for risk stratification of pregnant patients, while further studies are needed to determine the extent of immunological decidual response in patients with various forms of COVID-19.

Applications of Perilla frutescens Extracts in Clinical Practice.

(1) Background: Perilla frutescens (L.) Britt. is an important pharmaceutical crop that remains a focus point for researchers worldwide due to its complex phytochemical constituents, medicinal effects, and nutraceutical properties. The literature data are based on animal and cell culture studies, so the clinical evidence for the therapeutic effects is poorly outlined. The aim of this review was to provide an updated and thorough understanding of Perilla frutescens applications in clinical practice using data derived from human studies, and to outline the potential directions and perspectives for further studies on this crop. (2) Methods: Medline, Embase, and Cochrane databases were used to find relevant studies. All interventional studies that evaluated the effect of Perilla frutescens in human subjects were assessed. (3) Results: The main perspectives that can be contoured from the presented literature evaluation are an important clinical effect of Perilla frutescens extracts on allergic rhinoconjuctivitis, especially in young populations, a potent hypolipemiant effect that, in conjunction with increased serum biological antioxidant potential, determines significant improvements in cognitive function and a wide variety of miscellaneous clinical effects that need further exploration. (4) Conclusions: Supplementary research is needed in order to demonstrate the therapeutic effects of Perilla frutescens in controlled clinical settings.

The Influence of Maternal KIR Haplotype on the Reproductive Outcomes after Single Embryo Transfer in IVF Cycles in Patients with Recurrent Pregnancy Loss and Implantation Failure-A Single Center Experience.

(1) Background: Recurrent pregnancy loss (RPL) and recurrent implantation failure (RIF) have in common a deficient maternal adaptation to the semi-allogeneic fetus, in which killer immunoglobulin-like receptor (KIR) family expressed by natural killer (NK) cells play an important role. The aim of this study was to evaluate the influence of maternal KIR haplotype on the reproductive outcomes after single embryo transfer in IVF cycles in patients with RPL and RIF. (2) Methods: Patients with RIF and RPL who presented at Origyn Fertility Center from Iasi, Romania, were prospectively enrolled between January 2020 and December 2022. Clinical and paraclinical data was examined. Descriptive statistics and a conditional logistic regression model were used to analyze our data. (3) Results: Patients with a KIR AA haplotype had significantly more chances of miscarriage if they underwent an IVF procedure (aOR: 4.15, 95% CI: 1.39-6.50, p = 0.032) compared with those who spontaneously achieved a pregnancy. Moreover, it appeared that the same haplotype increased the chances of obtaining a pregnancy for patients who underwent an IVF procedure (aOR: 2.57, 95% CI: 0.85-6.75, p = 0.023). (4) Conclusions: Determination of KIR haplotype could be beneficial for patients with RPL or RIF in order to offer an individualized management.

Hematologic Risk Factors for the Development of Retinopathy of Prematurity-A Retrospective Study.

(1) Background: Retinopathy of prematurity (ROP) can cause severe visual impairment or even blindness. We aimed to assess the hematological risk factors that are associated with different stages of ROP in a cohort of preterm newborns, and to compare the clinical characteristics and therapeutic interventions between groups. (2) Methods: This retrospective study included 149 preterm newborns from a tertiary maternity hospital in Romania between January 2018 and December 2018, who were segregated into: Group 1 (with ROP, n = 59 patients), and Group 2 (without ROP, n = 90 patients). The patients that were affected by ROP were subsequently divided into the following subgroups: Subgroup 1 (Stage 1, n = 21), Subgroup 2 (Stage 2, n = 35), and Subgroup 3 (Stage 3, n = 25). The associations were analyzed using multivariate logistic regression and sensitivity analysis. (3) Results: Platelet mass indexes (PMI) that were determined in the first, seventh, and tenth days of life were significantly associated with Stage 1 ROP. PMI determined in the first day of life was also significantly associated with Stage 2 ROP. The sensitivity and specificity of these parameters were modest, ranging from 44 to 57%, and 59 to 63%. (4) Conclusions: PMI has a modest ability to predict the development of ROP.

Machine Learning Approaches for the Prediction of Hepatitis B and C Seropositivity.

(1) Background: The identification of patients at risk for hepatitis B and C viral infection is a challenge for the clinicians and public health specialists. The aim of this study was to evaluate and compare the predictive performances of four machine learning-based models for the prediction of HBV and HCV status. (2) Methods: This prospective cohort screening study evaluated adults from the North-Eastern and South-Eastern regions of Romania between January 2022 and November 2022 who underwent viral hepatitis screening in their family physician's offices. The patients' clinical characteristics were extracted from a structured survey and were included in four machine learning-based models: support vector machine (SVM), random forest (RF), naïve Bayes (NB), and K nearest neighbors (KNN), and their predictive performance was assessed. (3) Results: All evaluated models performed better when used to predict HCV status. The highest predictive performance was achieved by KNN algorithm (accuracy: 98.1%), followed by SVM and RF with equal accuracies (97.6%) and NB (95.7%). The predictive performance of these models was modest for HBV status, with accuracies ranging from 78.2% to 97.6%. (4) Conclusions: The machine learning-based models could be useful tools for HCV infection prediction and for the risk stratification process of adult patients who undergo a viral hepatitis screening program.

Prediction of HELLP Syndrome Severity Using Machine Learning Algorithms-Results from a Retrospective Study.

(1) Background: HELLP (hemolysis, elevated liver enzymes, and low platelets) syndrome is a rare and life-threatening complication of preeclampsia. The aim of this study was to evaluate and compare the predictive performances of four machine learning-based models for the prediction of HELLP syndrome, and its subtypes according to the Mississippi classification; (2) Methods: This retrospective case-control study evaluated pregnancies that occurred in women who attended a tertiary maternity hospital in Romania between January 2007 and December 2021. The patients' clinical and paraclinical characteristics were included in four machine learning-based models: decision tree (DT), naïve Bayes (NB), k-nearest neighbors (KNN), and random forest (RF), and their predictive performance were assessed; (3) Results: Our results showed that HELLP syndrome was best predicted by RF (accuracy: 89.4%) and NB (accuracy: 86.9%) models, while DT (accuracy: 91%) and KNN (accuracy: 87.1%) models had the highest performance when used to predict class 1 HELLP syndrome. The predictive performance of these models was modest for class 2 and 3 of HELLP syndrome, with accuracies ranging from 65.2% and 83.8%; (4) Conclusions: The machine learning-based models could be useful tools for predicting HELLP syndrome, and its most severe form-class 1.