OBJECTIVE: Cerebral palsy (CP) is a group of neurological disorders with profound implications for children\'s development. The identification of perinatal risk factors for CP may lead to improved preventive and therapeutic strategies. This study aimed to identify the early predictors of CP using machine learning (ML).
METHODS: This is a retrospective case-control study, using data from the two population-based databases, the Slovenian National Perinatal Information System and the Slovenian Registry of Cerebral Palsy. Multiple ML algorithms were evaluated to identify the best model for predicting CP.
METHODS: This is a population-based study of CP and control subjects born into one of Slovenia\'s 14 maternity wards.
METHODS: A total of 382 CP cases, born between 2002 and 2017, were identified. Controls were selected at a control-to-case ratio of 3:1, with matched gestational age and birth multiplicity. CP cases with congenital anomalies (n=44) were excluded from the analysis. A total of 338 CP cases and 1014 controls were included in the study.
METHODS: 135 variables relating to perinatal and maternal factors.
METHODS: Receiver operating characteristic (ROC), sensitivity and specificity.
RESULTS: The stochastic gradient boosting ML model (271 cases and 812 controls) demonstrated the highest mean ROC value of 0.81 (mean sensitivity=0.46 and mean specificity=0.95). Using this model with the validation dataset (67 cases and 202 controls) resulted in an area under the ROC curve of 0.77 (mean sensitivity=0.27 and mean specificity=0.94).
CONCLUSIONS: Our final ML model using early perinatal factors could not reliably predict CP in our cohort. Future studies should evaluate models with additional factors, such as genetic and neuroimaging data.

The goal of this paper is to build an automatic way to interpret conclusions from brain molecular imaging reports performed for investigation of cognitive disturbances (FDG, Amyloid and Tau PET) by comparing several traditional machine learning (ML) techniques-based text classification methods. Two purposes are defined: to identify positive or negative results in all three modalities, and to extract diagnostic impressions for Alzheimer\'s Disease (AD), Fronto-Temporal Dementia (FTD), Lewy Bodies Dementia (LBD) based on metabolism of perfusion patterns. A dataset was created by manual parallel annotation of 1668 conclusions of reports from the Nuclear Medicine and Molecular Imaging Division of Geneva University Hospitals. The 6 Machine Learning (ML) algorithms (Support Vector Machine (Linear and Radial Basis function), Naive Bayes, Logistic Regression, Random Forrest, and K-Nearest Neighbors) were trained and evaluated with a 5-fold cross-validation scheme to assess their performance and generalizability. The best classifier was SVM showing the following accuracies: FDG (0.97), Tau (0.94), Amyloid (0.98), Oriented Diagnostic (0.87 for a diagnosis among AD, FTD, LBD, undetermined, other), paving the way for a paradigm shift in the field of data handling in nuclear medicine research.

BACKGROUND: Attention-Deficit/Hyperactivity Disorder (ADHD) is a multifaceted neurodevelopmental psychiatric condition that typically emerges during childhood but often persists into adulthood, significantly impacting individuals\' functioning, relationships, productivity, and overall quality of life. However, the current diagnostic process exhibits limitations that can significantly affect its overall effectiveness. Notably, its face-to-face and time-consuming nature, coupled with the reliance on subjective recall of historical information and clinician subjectivity, stand out as key challenges. To address these limitations, objective measures such as neuropsychological evaluations, imaging techniques and physiological monitoring of the Autonomic Nervous System functioning, have been explored.
METHODS: The main aim of this study was to investigate whether physiological data (i.e., Electrodermal Activity, Heart Rate Variability, and Skin Temperature) can serve as meaningful indicators of ADHD, evaluating its utility in distinguishing adult ADHD patients. This observational, case-control study included a total of 76 adult participants (32 ADHD patients and 44 healthy controls) who underwent a series of Stroop tests, while their physiological data was passively collected using a multi-sensor wearable device. Univariate feature analysis was employed to identify the tests that triggered significant signal responses, while the Informative k-Nearest Neighbors (KNN) algorithm was used to filter out less informative data points. Finally, a machine-learning decision pipeline incorporating various classification algorithms, including Logistic Regression, KNN, Random Forests, and Support Vector Machines (SVM), was utilized for ADHD patient detection.
RESULTS: Results indicate that the SVM-based model yielded the optimal performance, achieving 81.6% accuracy, maintaining a balance between the experimental and control groups, with sensitivity and specificity of 81.4% and 81.9%, respectively. Additionally, integration of data from all physiological signals yielded the best results, suggesting that each modality captures unique aspects of ADHD.
CONCLUSIONS: This study underscores the potential of physiological signals as valuable diagnostic indicators of adult ADHD. For the first time, to the best of our knowledge, our findings demonstrate that multimodal physiological data collected via wearable devices can complement traditional diagnostic approaches. Further research is warranted to explore the clinical applications and long-term implications of utilizing physiological markers in ADHD diagnosis and management.

UNASSIGNED: During the past decade, the frequency of extrapulmonary forms of tuberculosis (TB) has increased. These forms are often miss-diagnosed. This statement of the TB epidemiological profile modification, conduct us to reflect about the utility of the Tuberculin Skin Test (TST) in active TB detection. This study aimed to evaluate the diagnostic accuracy performance of the TST for active tuberculosis detection.
UNASSIGNED: This was a case-control, multicenter study conducted in 11 anti-TB centers in Tunisia (June-November2014). The cases were adults aged between 18 and 55 years with newly diagnosed and confirmed tuberculosis. Controls were free from tuberculosis. A data collection sheet was filled out and a TST was performed for each participant.Diagnostic accuracy measures of TST were estimated using Receiver Operating Curve (ROC) curve and Area Under Curve (AUC) to estimate sensitivity and specificity of a determined cut-off point.
UNASSIGNED: Overall, 1050 patients were enrolled, composed of 336 cases and 714 controls. The mean age was 38.3±11.8 years for cases and 33.6±11 years for controls.The mean diameter of the TST induration was significantly higher among cases than controls (13.7mm vs.6.2mm; p=10 -6). AUC was 0.789 [95% CI: 0.758-0.819; p=0.01], corresponding to a moderate discriminating performance for this test. The most discriminative cut-off value of the TST, which was associated with the best sensitivity (73.7%) and specificity (76.6%) couple was   ≥ 11 mm with a Youden index of 0.503. Positive and Negative predictive values were 3.11% and 99.52%, respectively.
UNASSIGNED: TST could be a useful tool used for active tuberculosis detection, with a moderate global performance and accepted sensitivity and specificity at the cut-off point of 11 mm. However, it cannot be considered as a gold standard test due to its multiple disadvantages.

BACKGROUND: The study aimed to evaluate the diagnostic efficacy of dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) and diffusion-weighted imaging (DWI) parameters in distinguishing sinonasal lymphoma from sinonasal carcinoma.
METHODS: Forty-two participants with histologically confirmed sinonasal lymphomas and fifty-two cases of sinonasal carcinoma underwent imaging with a 3.0T MRI scanner. DCE-MRI and DWI were conducted, and various parameters including type of time-intensity curve(TIC), time to peak, peak enhancement, peak contrast enhancement, washout rate, apparent diffusion coefficient (ADC), and relative ADC were measured. Binary logistic regression and receiver operating characteristic (ROC) curve analysis were employed to assess the diagnostic capability of individual and combined indices for differentiating nasal sinus lymphoma from nasal sinus carcinoma.
RESULTS: Sinonasal lymphoma predominantly exhibited type II TIC(n = 20), whereas sinonasal carcinoma predominantly exhibited type III TIC(n = 23). Significant differences were observed in all parameters except washout ratio (p < 0.05), and ADC value emerged as the most reliable diagnostic tool in single parameter. Combined DCE-MRI parameters demonstrated superior diagnostic efficacy compared to individual parameters, with the highest efficiency (area under curve = 0.945) achieved when combining all parameters of DCE-MRI and DWI.
CONCLUSIONS: Multiparametric evaluation involving contrast-enhanced dynamic MRI and DWI holds considerable diagnostic value in distinguishing sinonasal lymphoma from sinonasal carcinoma.

Demodex mite proliferation is frequently involved in the pathogenesis of rosacea. The gold standard for Demodex identification is microscopic examination on a standardized skin surface biopsy. However, this method of sampling can be distressing and painful, especially when performed on hairy sites. In this case-control study, we compared the sensitivity of PCR and microscopic examination in diagnosing a Demodex infestation. Moreover, we investigated the possible correlations between the presence of Demodex mites and clinical characteristics. In total, 20 patients affected by papulopustular rosacea and 10 controls were included. At both microscopic examination and PCR, patients with rosacea presented a greater prevalence of positive samples than controls at the scalp and at the face. Microscopy had sensitivity of 50% at the face and of 46.7% at the scalp. PCR had sensitivity of 93.75% at the face and of 86.7% at the scalp. The positivity of PCR was associated to a higher frequency of facial papules and pustules. Patients with positivity at the face had a more frequent positivity at the scalp. The scalp could represent a reservoir for the Demodex mites, and should be investigated by sensitive and painless methods. PCR performed on painlessly collected samples should be further investigated.

BACKGROUND: Preeclampsia is a life-threatening complication of pregnancy that occurs in approximately 7% of all pregnancies. In India, the incidence of preeclampsia is 8%-10% and the prevalence is 5.4%, whereas the prevalence of hypertensive disorders of pregnancy is 7.8%.
OBJECTIVE: This study was aimed at evaluating the diagnostic accuracy of serum glycosylated fibronectin (S. GlyFn) in the prediction of preeclampsia.
METHODS: A nested case-control study was carried out for 16 months in the department of obstetrics and gynecology. A total of 240 women were recruited and followed after written consent and ethical clearance. Six were lost to follow-up, 15 had second-trimester abortions (excluded from the study), and 32 women developed hypertensive disorders of pregnancy (cases), out of which 1 woman developed antepartum eclampsia, 10 women developed preeclampsia with severe features, and 21 women developed preeclampsia without severe features. One hundred and eighty-seven women remained normotensive throughout the pregnancy until 6 weeks postpartum. After randomization, out of these samples, 54 were analyzed and considered controls. Levels of S. GlyFn were estimated using an ELISA kit using the ELISA technique.
RESULTS: The mean S. GlyFn level was significantly higher at the time of enrollment among those women who later developed preeclampsia (127.59 ± 27.68 ng/m) as compared to controls (107.79-53.51 ng/mL). GlyFn at a cutoff value of 126.70 ng/mL significantly (P = 0.034) discriminates cases of preeclampsia with severe features from healthy controls with a sensitivity of 90.00%, a specificity of 63.00%, a 31.03% positive predictive value, and 97.14% negative predictive value.
CONCLUSIONS: S. GlyFn, at a cutoff value of 126.70 ng/mL, had good sensitivity to discriminate PE from normotensive and was also a good prognostic marker.
Résumé Contexte:La prééclampsie est une complication potentiellement mortelle de la grossesse qui survient dans environ 7 % de toutes les grossesses. En Inde, l’incidence de la prééclampsie est de 8 % à 10 % et la prévalence est de 5,4 %, alors que la prévalence des troubles hypertensifs de la grossesse est 7,8 %. But et objectifs : Cette étude visait à évaluer la précision diagnostique de la fibronectine sérique glycosylée (S. GlyFn) chez la prédiction de la prééclampsie.Méthodes:Une étude cas-témoin nichée a été menée pendant 16 mois dans le service d’obstétrique et gynécologie. Au total, 240 femmes ont été recrutées et suivies après consentement écrit et autorisation éthique. Six ont été perdus de vue, 15 avaient avortements au deuxième trimestre (exclus de l’étude), et 32 femmes ont développé des troubles hypertensifs de la grossesse (cas), dont 1 femme a développé une éclampsie antepartum, 10 femmes ont développé une prééclampsie avec des caractéristiques sévères et 21 femmes ont développé une prééclampsie sans traits sévères. Cent quatre-vingt sept femmes sont restées normotendues tout au long de la grossesse jusqu’à 6 semaines après l’accouchement. Après randomisation, sur ces échantillons, 54 ont été analysés et considérés comme témoins. Les niveaux de S. GlyFn ont été estimés à l’aide d’un kit ELISA en utilisant la technique ELISA.Résultats:Le niveau moyen de S. GlyFn était significativement plus élevé au moment de l’inscription chez les femmes qui ont développé plus tard une prééclampsie (127,59 ± 27,68 ng/m) par rapport aux témoins (107,79–53,51 ng/mL). GlyFn à une valeur seuil de 126,70 ng/mL de manière significative (P = 0,034) discrimine les cas de prééclampsie avec des caractéristiques sévères des témoins sains avec une sensibilité de 90,00 %, un spécificité de 63,00 %, une valeur prédictive positive de 31,03 % et une valeur prédictive négative de 97,14 %.Conclusion:S. GlyFn, à une valeur seuil de 126,70 ng/mL, avait une bonne sensibilité pour distinguer l’EP du normotendu et était également un bon marqueur pronostique.

OBJECTIVE: To determine how fetuin-A contributes to diagnosing and assessing MASLD severity.
METHODS: Fifty MASLD patients and fifty healthy control participants were involved in this retrospective case-control research. Abdominal ultrasonography, fibroscan with controlled attenuated parameter scan (CAP scan), laboratory investigation (including fetuin-A assessment), clinical examination, and history-taking were performed on every case.
RESULTS: Fetuin-A level was considerably higher in the Cases group (1154.85 ± 629.89) than in the Control group (505.29 ± 150.4) (p < 0.001). Fetuin-A had significant validity in the prediction of MASLD at a cut-off > 702.5 with 82% sensitivity, 90% specificity, and 86% overall accuracy.
CONCLUSIONS: One possible marker for MASLD diagnosis could be fetuin-A. Furthermore, a substantial association between such marker and the severity of the disease as it revealed a significant correlation with ultrasound grading and fibroscan with controlled attenuated parameters. Trial registration 1- Pan African Clinical Trial Registry. Unique Identifying number/registration ID: PACTR202309644280965. URL: https://pactr.samrc.ac.za/TrialDisplay.aspx?TrialID=26860 . Registration Approval date: 21/09/2023. 2- ClinicalTrials.gov. Unique Identifying number /registration ID: NCT06097039. URL: https://clinicaltrials.gov/study/NCT06097039?cond=NCT06097039&rank=1 . Registration Approval date: 25/10/2023.

UNASSIGNED: While real-time reverse transcription PCR (RT-PCR) is the recommended laboratory method to diagnose severe acute respiratory syndrome Coronavirus 2 (SARS-CoV-2) infection, its use in resource limited settings can be difficult to maintain due to high testing demand and shortage of reagents. The aim of this study was to evaluate the performances of Realy Tech™ and Standard Q™ in comparison to RT-PCR in a relatively low COVID-19 prevalence setting, Mali.
UNASSIGNED: We conducted a cross-sectional study between January and April 2021 in Bamako and Kati regions to evaluate both rapid tests during a large SARS-CoV-2 prevalence study in Mali.
UNASSIGNED: Of the 390 samples tested, the sensitivity and specificity of Realy Tech™ and Standard Q™ were 57.1% (95%CI: 44.1-69.2), 95.8% (95%CI: 93.1-97.5); 61.9% (95%CI: 46.8-75.0), and 94.1% (95%CI: 89.5-96.8) respectively. Using RT-PCR, the global prevalence of SARS-CoV-2 was 14.4% (56/390). In both rapid antigen tests, the performance was better when used in suspected patients compared to positive patients under treatment. Moreover, higher viral loads equivalent to Ct < 25 were associated with better detection rates.
UNASSIGNED: While waiting for more complete data, these preliminary studies suggest that Realy Tech™ and Standard Q™ should not be used alone for COVID-19 diagnosis in Mali.

BACKGROUND: Early screening and detection of lung cancer is essential for the diagnosis and prognosis of the disease. In this paper, we investigated the feasibility of serum Raman spectroscopy for rapid lung cancer screening.
METHODS: Raman spectra were collected from 45 patients with lung cancer, 45 with benign lung lesions, and 45 healthy volunteers. And then the support vector machine (SVM) algorithm was applied to build a diagnostic model for lung cancer. Furthermore, 15 independent individuals were sampled for external validation, including 5 lung cancer patients, 5 benign lung lesion patients, and 5 healthy controls.
RESULTS: The diagnostic sensitivity, specificity, and accuracy were 91.67%, 92.22%, 90.56% (lung cancer vs. healthy control), 92.22%,95.56%,93.33% (benign lung lesion vs. healthy) and 80.00%, 83.33%, 80.83% (lung cancer vs. benign lung lesion), repectively. In the independent validation cohort, our model showed that all the samples were classified correctly.
CONCLUSIONS: Therefore, this study demonstrates that the serum Raman spectroscopy analysis technique combined with the SVM algorithm has great potential for the noninvasive detection of lung cancer.