Predicting the evolution of clinical skin aging in a multi-ethnic population: Developing causal Bayesian networks using dermatological expertise.

INTRODUCTION: Software to predict the impact of aging on physical appearance is increasingly popular. But it does not consider the complex interplay of factors that contribute to skin aging. OBJECTIVES: To predict the +15-year progression of clinical signs of skin aging by developing Causal Bayesian Belief Networks (CBBNs) using expert knowledge from dermatologists. MATERIAL AND METHODS: Structures and conditional probability distributions were elicited worldwide from dermatologists with experience of at least 15 years in aesthetics. CBBN models were built for all phototypes and for ages ranging from 18 to 65 years, focusing on wrinkles, pigmentary heterogeneity and facial ptosis. Models were also evaluated by a group of independent dermatologists ensuring the quality of prediction of the cumulative effects of extrinsic and intrinsic skin aging factors, especially the distribution of scores for clinical signs 15 years after the initial assessment. RESULTS: For easiness, only models on African skins are presented in this paper. The forehead wrinkle evolution model has been detailed. Specific atlas and extrinsic factors of facial aging were used for this skin type. But the prediction method has been validated for all phototypes, and for all clinical signs of facial aging. CONCLUSION: This method proposes a skin aging model that predicts the aging process for each clinical sign, considering endogenous and exogenous factors. It simulates aging curves according to lifestyle. It can be used as a preventive tool and could be coupled with a generative AI algorithm to visualize aging and, potentially, other skin conditions, using appropriate images.

Features of Mild-to-Moderate COVID-19 Patients With Dysphonia.

INTRODUCTION: To explore the prevalence of dysphonia in European patients with mild-to-moderate COVID-19 and the clinical features of dysphonic patients. METHODS: The clinical and epidemiological data of 702 patients with mild-to-moderate COVID-19 were collected from 19 European Hospitals. The following data were extracted: age, sex, ethnicity, tobacco consumption, comorbidities, general, and otolaryngological symptoms. Dysphonia and otolaryngological symptoms were self-assessed through a 4-point scale. The prevalence of dysphonia, as part of the COVID-19 symptoms, was assessed. The outcomes were compared between dysphonic and nondysphonic patients. The association between dysphonia severity and outcomes was studied through Bayesian analysis. RESULTS: A total of 188 patients were dysphonic, accounting for 26.8% of cases. Females developed more frequently dysphonia than males (P = 0.022). The proportion of smokers was significantly higher in the dysphonic group (P = 0.042). The prevalence of the following symptoms was higher in dysphonic patients compared with nondysphonic patients: cough, chest pain, sticky sputum, arthralgia, diarrhea, headache, fatigue, nausea, and vomiting. The severity of dyspnea, dysphagia, ear pain, face pain, throat pain, and nasal obstruction was higher in dysphonic group compared with nondysphonic group. There were significant associations between the severity of dysphonia, dysphagia, and cough. CONCLUSION: Dysphonia may be encountered in a quarter of patients with mild-to-moderate COVID-19 and should be considered as a symptom list of the infection. Dysphonic COVID-19 patients are more symptomatic than nondysphonic individuals. Future studies are needed to investigate the relevance of dysphonia in the COVID-19 clinical presentation.

Bayesian predictive model to assess BRCA2 mutational status according to clinical history: Early onset, metastatic phenotype or family history of breast/ovary cancer.

BACKGROUND: Mutations of the BRCA2 gene are the most frequent alterations found in germline DNA from men with prostate cancer (PrCa), but clinical parameters that could better orientate for BRCA2 mutation screening need to be established. METHODS: Germline DNA from 325 PrCa patients (median age at diagnosis: 57 years old) was screened for BRCA2 mutation. The mutation frequency was compared between three subgroups: patients with an age at diagnosis at 55 years old and under (Group I); a personal or family history of breast, uterine or ovarian cancer (Group II); or a metastatic disease (Group III). Frequency of BRCA2 mutations was established for each combination of phenotypes, and compared between patients meeting or not the criteria for each subgroup using Fisher's exact test. Mutual information, direct effect, elasticity and contribution to the mutational status of each phenotype, taking into account overlap between subgroups, were also estimated using Bayesian algorithms. RESULTS: The proportion of BRCA2 mutation was 5.9% in Group I, 10.9% in Group II and 6.9% in Group III. The frequency of BRCA2 mutation was significantly higher among patients of Group II (p = .006), and reached 15.6% among patients of this group who presented a metastatic disease. Mutual information, direct effect, elasticity and contribution to the mutational status were the highest for phenotype II. Fifteen (71.4%) of the 21 BRCA2 mutation carriers had an aggressive form of the disease. Four (19%) of them died from PrCa after a median follow-up duration of 64.5 months. CONCLUSIONS: Our results showed that a higher frequency of BRCA2 mutation carriers is observed, not only among PrCa patients with young onset or a metastatic disease, but also with a personal or a familial history of breast cancer.

Predictive Accuracy of COVID-19 World Health Organization (WHO) Severity Classification and Comparison with a Bayesian-Method-Based Severity Score (EPI-SCORE).

Assess the predictive accuracy of the WHO COVID-19 severity classification on COVID-19 hospitalized patients. The secondary aim was to compare its predictive power with a new prediction model, named COVID-19 EPI-SCORE, based on a Bayesian network analysis. Methods: We retrospectively analyzed a population of 295 COVID-19 RT-PCR positive patients hospitalized at Epicura Hospital Center, Belgium, admitted between March 1st and April 30th, 2020. Results: Our cohort's median age was 73 (62-83) years, and the female proportion was 43%. All patients were classified following WHO severity classification at admission. In total, 125 (42.4%) were classified as Moderate, 69 (23.4%) as Severe, and 101 (34.2%) as Critical. Death proportions through these three classes were 11.2%, 33.3%, and 67.3%, respectively, and the proportions of critically ill patients (dead or needed Invasive Mechanical Ventilation) were 11.2%, 34.8%, and 83.2%, respectively. A Bayesian network analysis was used to create a model to analyze predictive accuracy of the WHO severity classification and to create the EPI-SCORE. The six variables that have been automatically selected by our machine learning algorithm were the WHO severity classification, acute kidney injury, age, Lactate Dehydrogenase Levels (LDH), lymphocytes and activated prothrombin time (aPTT). Receiver Operation Characteristic (ROC) curve indexes hereby obtained were 83.8% and 91% for the models based on WHO classification only and our EPI-SCORE, respectively. Conclusions: Our study shows that the WHO severity classification is reliable in predicting a severe outcome among COVID-19 patients. The addition to this classification of a few clinical and laboratory variables as per our COVID-19 EPI-SCORE has demonstrated to significantly increase its accuracy.

Clinical and epidemiological characteristics of 1420 European patients with mild-to-moderate coronavirus disease 2019.

BACKGROUND: The clinical presentation of European patients with mild-to-moderate COVID-19 infection is still unknown. OBJECTIVE: To study the clinical presentation of COVID-19 in Europe. METHODS: Patients with positive diagnosis of COVID-19 were recruited from 18 European hospitals. Epidemiological and clinical data were obtained through a standardized questionnaire. Bayesian analysis was used for analysing the relationship between outcomes. RESULTS: A total of 1,420 patients completed the study (962 females, 30.7% of healthcare workers). The mean age of patients was 39.17 ± 12.09 years. The most common symptoms were headache (70.3%), loss of smell (70.2%), nasal obstruction (67.8%), cough (63.2%), asthenia (63.3%), myalgia (62.5%), rhinorrhea (60.1%), gustatory dysfunction (54.2%) and sore throat (52.9%). Fever was reported by 45.4%. The mean duration of COVID-19 symptoms of mild-to-moderate cured patients was 11.5 ± 5.7 days. The prevalence of symptoms significantly varied according to age and sex. Young patients more frequently had ear, nose and throat complaints, whereas elderly individuals often presented fever, fatigue and loss of appetite. Loss of smell, headache, nasal obstruction and fatigue were more prevalent in female patients. The loss of smell was a key symptom of mild-to-moderate COVID-19 patients and was not associated with nasal obstruction and rhinorrhea. Loss of smell persisted at least 7 days after the disease in 37.5% of cured patients. CONCLUSION: The clinical presentation of mild-to-moderate COVID-19 substantially varies according to the age and the sex characteristics of patients. Olfactory dysfunction seems to be an important underestimated symptom of mild-to-moderate COVID-19 that needs to be recognized as such by the WHO.

Anosmia Is a Key Symptom of COVID-19 Infection and Should Be Used as a Diagnostic Tool.

Based on observations described in our letter, we can draw the following conclusions: (1) anosmia must imperatively be added to the list of specific symptoms of COVID-19 infection, (2) anosmia can serve as a free and specific diagnostic tool for developing countries currently affected by the pandemic, (3) the mechanisms of COVID-19 anosmia seem not to directly involve nasal obstruction but rather seem to be related to damage the olfactory neuroepithelium.

Effect of genetic variability within 8q24 on aggressiveness patterns at diagnosis and familial status of prostate cancer.

PURPOSE: Recently, two independent loci located at 8q24 that contribute to prostate cancer risk in men of European origin were identified. EXPERIMENTAL DESIGN: Using Bayesian probability network and logistic regression model, we searched for associations between 34 single-nucleotide polymorphisms (SNP) located at 8q24 and the aggressiveness patterns of prostate adenocarcinoma or familial history of cancers in 823 White Caucasian French men. RESULTS: Probability network according to the Markov chain algorithm separated the SNPs into two main groups: The first one was linked to the locus marked by rs6983267 and the second one was linked to the locus marked by rs1447295. When the patients were stratified according to tumor stage and prostate-specific antigen value, the association between the variant genotypes from six SNPs located in the second network and prostate cancer risk was strongest or confined to the patients from the more aggressive classes. However, the association between prostate cancer risk and the CC genotype of rs7841264, which marked the recombination hotspot at 8q24, was confined to patients with the highest Gleason score (odds ratio, 2.15; 95% confidence interval, 1.27-3.64; P=0.004). Interestingly, the G allele of rs6983267 was associated with familial prostate cancer risk. CONCLUSIONS: Our data further support that variability at 8q24 is associated with a high risk of aggressive prostate cancer at diagnosis and is linked with familial history of prostate cancer. These results corroborate that 8q24 SNPs must be evaluated in terms of prostate cancer aggressiveness markers to optimize early diagnosis procedures and management of the disease.