NRV: An open framework for in silico evaluation of peripheral nerve electrical stimulation strategies.

Electrical stimulation of peripheral nerves has been used in various pathological contexts for rehabilitation purposes or to alleviate the symptoms of neuropathologies, thus improving the overall quality of life of patients. However, the development of novel therapeutic strategies is still a challenging issue requiring extensive in vivo experimental campaigns and technical development. To facilitate the design of new stimulation strategies, we provide a fully open source and self-contained software framework for the in silico evaluation of peripheral nerve electrical stimulation. Our modeling approach, developed in the popular and well-established Python language, uses an object-oriented paradigm to map the physiological and electrical context. The framework is designed to facilitate multi-scale analysis, from single fiber stimulation to whole multifascicular nerves. It also allows the simulation of complex strategies such as multiple electrode combinations and waveforms ranging from conventional biphasic pulses to more complex modulated kHz stimuli. In addition, we provide automated support for stimulation strategy optimization and handle the computational backend transparently to the user. Our framework has been extensively tested and validated with several existing results in the literature.

Expanding vaccination competencies to community pharmacists: modelling the organizational and economic impacts of new human papilloma virus (HPV) vaccine pathways in France.

BACKGROUND: The vaccine coverage rate (VCR) for human papillomavirus (HPV) in France is one of the lowest in Europe, well below the target of 80% announced in the French Cancer Plan 2021-2030. The extension of vaccination competencies (prescription and administration) to new health care providers, such as community pharmacists (CPs), was a decisive step by the French Health Authority (HAS) in 2022 to simplify access to vaccination and improve the VCR. This research assessed the economic and organizational impacts (OIs) of the extension of vaccination competencies in France. METHODS: A model was developed in Excel® to compare the current HPV vaccination pathway focused on general practitioners (GPs) to a mix of pathways (new and current) that extends pharmacists' competencies (prescription and/or injection). The simulated population corresponded to girls and boys targeted by the French recommendations. The model was run from 2023 to 2030. HAS guidelines were used to identify OIs related to these new pathways. Model inputs were collected from national data sources and an acceptability study. The results focused on three OIs (HPV vaccination ability [defined as the number of adolescents who could be vaccinated in each pathway], the VCR projection, and flows of activity between health care professionals]). The economic impact was evaluated from the National Health Insurance (NHI) perspective in 2022. RESULTS: With a mix of vaccination pathways, including an increasing role of pharmacists, the target of an 80% VCR could be reached in 2030 (versus 2032 with the current pathway) with lower investment than the current situation, resulting in cost savings for the NHI of €212 million. Expanding vaccination competencies will provide pharmacists with additional revenue (an average of €755,000/month for all vaccinating pharmacies) and will free up medical time for GPs (average of 603,000 consultations/year for all GPs). CONCLUSIONS: Expanding vaccination competencies to pharmacists has a positive impact on the entire ecosystem. From a public health perspective, the national VCR target can be achieved and better access to care can be provided, freeing up medical time. From an economic perspective, this approach can provide savings for the NHI and additional revenue for pharmacists.

User Evaluation of a Shared Robot Control System Combining BCI and Eye Tracking in a Portable Augmented Reality User Interface.

This study evaluates an innovative control approach to assistive robotics by integrating brain-computer interface (BCI) technology and eye tracking into a shared control system for a mobile augmented reality user interface. Aimed at enhancing the autonomy of individuals with physical disabilities, particularly those with impaired motor function due to conditions such as stroke, the system utilizes BCI to interpret user intentions from electroencephalography signals and eye tracking to identify the object of focus, thus refining control commands. This integration seeks to create a more intuitive and responsive assistive robot control strategy. The real-world usability was evaluated, demonstrating significant potential to improve autonomy for individuals with severe motor impairments. The control system was compared with an eye-tracking-based alternative to identify areas needing improvement. Although BCI achieved an acceptable success rate of 0.83 in the final phase, eye tracking was more effective with a perfect success rate and consistently lower completion times (p<0.001). The user experience responses favored eye tracking in 11 out of 26 questions, with no significant differences in the remaining questions, and subjective fatigue was higher with BCI use (p=0.04). While BCI performance lagged behind eye tracking, the user evaluation supports the validity of our control strategy, showing that it could be deployed in real-world conditions and suggesting a pathway for further advancements.

Implementation of a Bio-Inspired Neural Architecture for Autonomous Vehicles on a Multi-FPGA Platform.

Autonomous vehicles require efficient self-localisation mechanisms and cameras are the most common sensors due to their low cost and rich input. However, the computational intensity of visual localisation varies depending on the environment and requires real-time processing and energy-efficient decision-making. FPGAs provide a solution for prototyping and estimating such energy savings. We propose a distributed solution for implementing a large bio-inspired visual localisation model. The workflow includes (1) an image processing IP that provides pixel information for each visual landmark detected in each captured image, (2) an implementation of N-LOC, a bio-inspired neural architecture, on an FPGA board and (3) a distributed version of N-LOC with evaluation on a single FPGA and a design for use on a multi-FPGA platform. Comparisons with a pure software solution demonstrate that our hardware-based IP implementation yields up to 9× lower latency and 7× higher throughput (frames/second) while maintaining energy efficiency. Our system has a power footprint as low as 2.741 W for the whole system, which is up to 5.5-6× less than what Nvidia Jetson TX2 consumes on average. Our proposed solution offers a promising approach for implementing energy-efficient visual localisation models on FPGA platforms.

Using Novel Multi-Frequency Analysis Methods to Retrieve Material and Temperature Information in Tactile Sensing Areas.

This article presents a novel artificial skin technology based on the Electric Impedance Tomography (EIT) that employs multi-frequency currents for detecting the material and the temperature of objects in contact with piezoresistive sheets. To date, few artificial skins in the literature are capable of detecting an object's material, e.g., wood, skin, leather, or plastic. EIT-based artificial skins have been employed mostly to detect the position of the contact but not its characteristics. Thanks to multi-frequency currents, our EIT-based artificial skin is capable of characterising the spectral profile of objects in contact and identifying an object's material at ambient temperature. Moreover, our model is capable of detecting several levels of temperature (from -10 up to 60 °C) and can also maintain a certain accuracy for material identification. In addition to the known capabilities of EIT-based artificial skins concerning detecting pressure and location of objects, as well as being low cost, these two novel modalities demonstrate the potential of EIT-based artificial skins to achieve global tactile sensing.

Pneumococcal susceptibility to antibiotics in carriage: a 17 year time series analysis of the adaptive evolution of non-vaccine emerging serotypes to a new selective pressure environment.

BACKGROUND: Pneumococcal conjugate vaccine (PCV) implementations led to major changes in serotype distribution and antibiotic resistance in carriage, accompanied by changes in antibiotic consumption. OBJECTIVES: To assess the dynamic patterns of antimicrobial non-susceptibility across non-PCV13 serotypes following PCV implementations. METHODS: We conducted a quasi-experimental interrupted time series analysis based on a 17 year French nationwide prospective cohort. From 2001 to 2018, 121 paediatricians obtained nasopharyngeal swabs from children with acute otitis media who were aged 6 months to 2 years. The main outcome was the rate of penicillin-non-susceptible pneumococci (PNSP), analysed by segmented regression. RESULTS: We enrolled 10 204 children. After PCV13 implementation, the PNSP rate decreased (-0.5% per month; 95% CI -0.9 to -0.1), then, after 2014, the rate slightly increased (+0.7% per month; 95% CI +0.2 to +1.2). Global antibiotic use within the previous 3 months decreased over the study period (-22.2%; 95% CI -33.0 to -11.3), but aminopenicillin use remained high. Among the main non-PCV13 serotypes, four dynamic patterns of penicillin susceptibility evolution were observed, including unexpected patterns of serotypes emerging while remaining or even becoming penicillin susceptible. In contrast to PNSP strains, for these latter patterns, the rate of co-colonization with Haemophilus influenzae increased concomitant with their emergence. CONCLUSIONS: In a context of continuing high antibiotic selective pressure, a progressive increase in PNSP rate was observed after 2014. However, we highlighted an unexpected variability in dynamic patterns of penicillin susceptibility among emerging non-PCV13 serotypes. Antibiotic resistance may not be the only adaptive mechanism to antimicrobial selective pressure, and co-colonization with H. influenzae may be involved.

A Secure Occupational Therapy Framework for Monitoring Cancer Patients' Quality of Life.

Once diagnosed with cancer, a patient goes through a series of diagnosis and tests, which are referred to as "after cancer treatment". Due to the nature of the treatment and side effects, maintaining quality of life (QoL) in the home environment is a challenging task. Sometimes, a cancer patient's situation changes abruptly as the functionality of certain organs deteriorates, which affects their QoL. One way of knowing the physiological functional status of a cancer patient is to design an occupational therapy. In this paper, we propose a blockchain and off-chain-based framework, which will allow multiple medical and ambient intelligent Internet of Things sensors to capture the QoL information from one's home environment and securely share it with their community of interest. Using our proposed framework, both transactional records and multimedia big data can be shared with an oncologist or palliative care unit for real-time decision support. We have also developed blockchain-based data analytics, which will allow a clinician to visualize the immutable history of the patient's data available from an in-home secure monitoring system for a better understanding of a patient's current or historical states. Finally, we will present our current implementation status, which provides significant encouragement for further development.

Cell Count Analysis from Nonbronchoscopic Bronchoalveolar Lavage in Preterm Infants.

OBJECTIVES: To establish the reference values, diagnostic accuracy, and effect of various factors on cell count in intubated preterm neonates subjected to nonbronchoscopic bronchoalveolar lavage. STUDY DESIGN: This prospective, cross-sectional, blinded study included preterm neonates ventilated for any reason who underwent nonbronchoscopic bronchoalveolar lavage if they had not previously received postnatal antibiotics or steroids. Lavage was performed before surfactant replacement, if any. A gentle ventilation policy was applied. Pneumonia was diagnosed using clinical criteria, without considering cell count. Investigators performing cell counts were blinded to the clinical data. RESULTS: There were 276 neonates enrolled; 36 had congenital or ventilator-associated pneumonia. In the 240 noninfected babies, median neutrophil count increased significantly after the first 2 days of ventilation (day 1, 2 cells per field [IQR, 0.0-9.5 cells per field]; day 2, 2 cells per field [IQR, 0-15 cells per field]; day 3, 20 cells per field [IQR, 2-99 cells per field]; day 4, 15 cells per field [IQR, 2-96 cells per field]; P < .0001). No significant difference was seen over time in infected babies. Multivariate analysis indicated pneumonia (standardized ß = 0.134; P = .033) and the time spent under mechanical ventilation before nonbronchoscopic bronchoalveolar lavage as factors significantly influencing neutrophil count (standardized ß = 0.143; P = .027). Neutrophil count was correlated with the duration of ventilation (rho = 0.28; P <.001). Neutrophil counts were higher in infected (24 cells/field [IQR, 5-78] cells/field) than in noninfected babies (4 cells/field [IQR, 1-24 cells/field]; P <.001) and had an moderate reliability for pneumonia within the first 2 days of ventilation (area under the curve, 0.745; (95% CI, 0.672-0.810; P = .002). CONCLUSIONS: We provide reference values for airway neutrophil counts in ventilated preterm neonates. Bronchoalveolar lavage neutrophils significantly increase after 2 days of ventilation. Neutrophil count has moderate accuracy to diagnose pneumonia, but only within the first 2 days of ventilation.

Outcomes of Preterm Neonates Transferred Between Tertiary Perinatal Centers.

OBJECTIVE: To verify if preterm neonates transferred between tertiary referral centers have worse outcomes than matched untransferred infants. DESIGN: Cohort study with a historically matched control group. SETTING: Two tertiary-level neonatal ICUs. PATIENTS: Seventy-five neonates per group. INTERVENTIONS: Transfer between tertiary-level neonatal ICUs carried out by a fully equipped transportation team. MEASUREMENTS AND MAIN RESULTS: We measured in-hospital mortality, frequency of intraventricular hemorrhage greater than 2nd grade, periventricular leukomalacia, necrotizing enterocolitis greater than or equal to grade 2, bronchopulmonary dysplasia, composite outcomes (in-hospital mortality/bronchopulmonary dysplasia, in-hospital mortality/intraventricular hemorrhage > 2nd grade, and bronchopulmonary dysplasia/periventricular leukomalacia/intraventricular hemorrhage > 2nd grade), length of neonatal ICU stay, weight at discharge, and time spent on ventilatory support. Seventy-five similar (except for antenatal steroids administration) neonates were enrolled in each cohort. Cohorts did not differ in mortality, bronchopulmonary dysplasia, intraventricular hemorrhage greater than 2nd grade, periventricular leukomalacia, necrotizing enterocolitis greater than or equal to grade 2, any composite outcomes, neonatal ICU stay, weight at discharge, and duration of respiratory support. Results were unchanged adjusting for antenatal steroids. CONCLUSIONS: Neonatal transfer between tertiary-level centers does not impact on clinical outcomes, if performed under optimal conditions.

NRV: An open framework for in silico evaluation of peripheral nerve electrical stimulation strategies.

Electrical stimulation of peripheral nerves has been used in various pathological contexts for rehabilitation purposes or to alleviate the symptoms of neuropathologies, thus improving the overall quality of life of patients. However, the development of novel therapeutic strategies is still a challenging issue requiring extensive in vivo experimental campaigns and technical development. To facilitate the design of new stimulation strategies, we provide a fully open source and self-contained software framework for the in silico evaluation of peripheral nerve electrical stimulation. Our modeling approach, developed in the popular and well-established Python language, uses an object-oriented paradigm to map the physiological and electrical context. The framework is designed to facilitate multi-scale analysis, from single fiber stimulation to whole multifascicular nerves. It also allows the simulation of complex strategies such as multiple electrode combinations and waveforms ranging from conventional biphasic pulses to more complex modulated kHz stimuli. In addition, we provide automated support for stimulation strategy optimization and handle the computational backend transparently to the user. Our framework has been extensively tested and validated with several existing results in the literature.

A shared robot control system combining augmented reality and motor imagery brain-computer interfaces with eye tracking.

Objective: Brain-computer interface (BCI) control systems monitor neural activity to detect the user's intentions, enabling device control through mental imagery. Despite their potential, decoding neural activity in real-world conditions poses significant challenges, making BCIs currently impractical compared to traditional interaction methods. This study introduces a novel motor imagery (MI) BCI control strategy for operating a physically assistive robotic arm, addressing the difficulties of MI decoding from electroencephalogram (EEG) signals, which are inherently non-stationary and vary across individuals. Approach: A proof-of-concept BCI control system was developed using commercially available hardware, integrating MI with eye tracking in an augmented reality (AR) user interface to facilitate a shared control approach. This system proposes actions based on the user's gaze, enabling selection through imagined movements. A user study was conducted to evaluate the system's usability, focusing on its effectiveness and efficiency. Main results:Participants performed tasks that simulated everyday activities with the robotic arm, demonstrating the shared control system's feasibility and practicality in real-world scenarios. Despite low online decoding performance (mean accuracy: 0.52 9, F1: 0.29, Cohen's Kappa: 0.12), participants achieved a mean success rate of 0.83 in the final phase of the user study when given 15 minutes to complete the evaluation tasks. The success rate dropped below 0.5 when a 5-minute cutoff time was selected. Significance: These results indicate that integrating AR and eye tracking can significantly enhance the usability of BCI systems, despite the complexities of MI-EEG decoding. While efficiency is still low, the effectiveness of our approach was verified. This suggests that BCI systems have the potential to become a viable interaction modality for everyday applications in the future.

Evaluating the real-world usability of BCI control systems with augmented reality: a user study protocol.

Brain-computer interfaces (BCI) enable users to control devices through their brain activity. Motor imagery (MI), the neural activity resulting from an individual imagining performing a movement, is a common control paradigm. This study introduces a user-centric evaluation protocol for assessing the performance and user experience of an MI-based BCI control system utilizing augmented reality. Augmented reality is employed to enhance user interaction by displaying environment-aware actions, and guiding users on the necessary imagined movements for specific device commands. One of the major gaps in existing research is the lack of comprehensive evaluation methodologies, particularly in real-world conditions. To address this gap, our protocol combines quantitative and qualitative assessments across three phases. In the initial phase, the BCI prototype's technical robustness is validated. Subsequently, the second phase involves a performance assessment of the control system. The third phase introduces a comparative analysis between the prototype and an alternative approach, incorporating detailed user experience evaluations through questionnaires and comparisons with non-BCI control methods. Participants engage in various tasks, such as object sorting, picking and placing, and playing a board game using the BCI control system. The evaluation procedure is designed for versatility, intending applicability beyond the specific use case presented. Its adaptability enables easy customization to meet the specific user requirements of the investigated BCI control application. This user-centric evaluation protocol offers a comprehensive framework for iterative improvements to the BCI prototype, ensuring technical validation, performance assessment, and user experience evaluation in a systematic and user-focused manner.

Use of Rapid Antigen Triple Test Nasal Swabs (COVID-VIRO ALL-IN TRIPLEX: Severe Acute Respiratory Syndrome Coronavirus 2, Respiratory Syncytial Virus, and Influenza) in Children With Respiratory Symptoms: A Real-life Prospective Study.

Background: In autumn 2022, the epidemics due to severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), respiratory syncytial virus (RSV), and influenza overlapped, and these diseases can present with the same symptomatology. The use of a triple antigen test (SARS-CoV-2 + influenza A/B + RSV) seems crucial for accurate viral diagnosis in the context of implementing long-acting monoclonal antibody vaccination against RSV in the upcoming RSV season. Methods: We assessed the usefulness of the triple test in real life in this prospective study performed from October 2022 to May 2023 and involving 116 pediatricians (2 emergency department pediatricians and 114 ambulatory pediatricians). Children <15 years old with flu-like illness (with fever), bronchiolitis (dyspnea ± wheezing), otitis, and croup were enrolled and sampled with a nasal triple test. Results: For 8329 children with flu-like illness (65.3%), bronchiolitis (17.9%), otitis (8.8%), and croup (6.3%), the use of the triple test led to a viral diagnosis in 47.9% of cases. The highest RSV positivity occurred in children with bronchiolitis (32.9%). The highest influenza A and B positivity (24.6% and 19.6%) occurred in children with flu-like illness. A succession of 3 epidemics (RSV and influenza A and B) occurred over time with several overlap periods. Conclusions: The triple test allowed for a viral diagnosis in half of our cases. The upcoming introduction of RSV prevention will emphasize the need for active surveillance with viral results both in ambulatory settings and hospitals. Clinical Trials Registration. NCT0441231.

An annotated wing interferential pattern dataset of dipteran insects of medical interest for deep learning.

Several Diptera species are known to transmit pathogens of medical and veterinary interest. However, identifying these species using conventional methods can be time-consuming, labor-intensive, or expensive. A computer vision-based system that uses Wing interferential patterns (WIPs) to identify these insects could solve this problem. This study introduces a dataset for training and evaluating a recognition system for dipteran insects of medical and veterinary importance using WIPs. The dataset includes pictures of Culicidae, Calliphoridae, Muscidae, Tabanidae, Ceratopogonidae, and Psychodidae. The dataset is complemented by previously published datasets of Glossinidae and some Culicidae members. The new dataset contains 2,399 pictures of 18 genera, with each genus documented by a variable number of species and annotated as a class. The dataset covers species variation, with some genera having up to 300 samples.

Immunogenicity and safety of the quadrivalent meningococcal serogroups A, C, W-135 and Y tetanus toxoid conjugate vaccine (MenACWY-TT) in 2-10-year-old children: results of an open, randomised, controlled study.

UNLABELLED: In Europe, the introduction of monovalent meningococcal serogroup C (MenC) conjugate vaccines has resulted in a significant decline in MenC invasive disease. However, given the potential for strain evolution and increasing travel to areas of high endemicity, protection against additional serogroups is needed. In this study, the immunogenicity, measured by a serum bactericidal activity assay using rabbit complement (rSBA), and the safety of a quadrivalent meningococcal serogroups A, C, W-135 and Y tetanus toxoid conjugate vaccine (MenACWY-TT) were compared to that of a licensed monovalent MenC conjugate vaccine (MenC-CRM197) in children 2-10 years of age. Children were randomised (3:1) to receive a single dose of either MenACWY-TT or MenC-CRM197. Non-inferiority of the immunogenicity of MenACWY-TT versus MenC-CRM197 in terms of rSBA-MenC vaccine response was demonstrated. Exploratory analyses suggested that rSBA-MenC geometric mean titres adjusted for pre-vaccination titres were lower in children vaccinated with MenACWY-TT compared to MenC-CRM197. Nevertheless, at 1 month post-vaccination, ≥99.3 % of the children who received MenACWY-TT had rSBA titres ≥1:128 for each of the four vaccine serogroups, which is the more conservative correlate of protection. The reactogenicity and safety profile of MenACWY-TT was clinically acceptable and no serious adverse events considered related to vaccination were reported throughout the study. CONCLUSION: When administered to European school-age children, MenACWY-TT has a clinically acceptable safety profile and, when compared with MenC-CRM197, the potential to broaden protection against meningococcal disease caused by serogroups A, W-135 and Y while maintaining protection against MenC. This study has been registered at www.clinicaltrials.gov NCT00674583.

BIMMS: A versatile and portable system for biological tissue and electrode-tissue interface electrical characterization.

The presented design is a low-cost, compact, and open-source USB-controlled platform for biological tissue and electrode-tissue interface electrical measurements, capable of potentiostatic and galvanostatic electrical impedance spectroscopy up to 10 MHz and cyclic voltammetry with voltage compliance of +-8 V and up to 2.4 mA while ensuring tissue-safety conditions. The data acquisition and generation are based on an Analog Discovery 2 platform (Digilent, USA). We provide accuracy analysis and comparisons with a commercially available calibrated impedance analyzer. Impedance measurements are demonstrated on implanted electrodes for neural stimulation and on an isolated ex-vivo calf brain as an example use case of the presented design.

Neonatal bacterial infections: Diagnosis, bacterial epidemiology and antibiotic treatment.

Severe bacterial infections have a higher incidence in the neonatal period than at any other pediatric age. Incidence is even higher in premature babies than in term newborns, and severity is increased in the absence of early diagnosis and treatment. By contrast, clinical signs are nonspecific and sometimes trivial, and biomarkers perform poorly during the first 24 hours of infection. For decades, this has led to having too many children treated for extended periods with broad-spectrum antibiotics. Today, the challenge is to prescribe antibiotics in a targeted way, by identifying truly infected newborns. Over the last ten years, major paradigm shifts have occurred and should be taken into account, as a result of growing awareness of the ecological impact of early antibiotic therapy, notably antibiotic resistance, by choosing the narrowest spectrum antibiotic and stopping antibiotic therapy as soon as the diagnosis of infection has been reasonably ruled out. Among the biological tests, the most important are blood cultures. At least one blood culture, taken under aseptic conditions, of sufficient volume (1 to 2 mL), and using pediatric bottles must be taken as soon as the decision to treat has been made, before starting any antibiotic therapy. The bacteria responsible for early-onset bacterial neonatal infections (EBNI) have not changed significantly over recent years and remain dominated by Group B Streptococcus and Escherichia coli, which are the main targets of treatment. GBS is largely predominant in full-term infants, but the proportion of infections due to E. coli increases with prematurity.

Radar-based human activity recognition with adaptive thresholding towards resource constrained platforms.

Radar systems are increasingly being employed in healthcare applications for human activity recognition due to their advantages in terms of privacy, contactless sensing, and insensitivity to lighting conditions. The proposed classification algorithms are however often complex, focusing on a single domain of radar, and requiring significant computational resources that prevent their deployment in embedded platforms which often have limited memory and computational resources. To address this issue, we present an adaptive magnitude thresholding approach for highlighting the region of interest in the multi-domain micro-Doppler signatures. The region of interest is beneficial to extract salient features, meanwhile it ensures the simplicity of calculations with less computational cost. The results for the proposed approach show an accuracy of up to 93.1% for six activities, outperforming state-of-the-art deep learning methods on the same dataset with an over tenfold reduction in both training time and memory footprint, and a twofold reduction in inference time compared to a series of deep learning implementations. These results can help bridge the gap toward embedded platform deployment.

Species identification of phlebotomine sandflies using deep learning and wing interferential pattern (WIP).

Sandflies (Diptera; Psychodidae) are medical and veterinary vectors that transmit diverse parasitic, viral, and bacterial pathogens. Their identification has always been challenging, particularly at the specific and sub-specific levels, because it relies on examining minute and mostly internal structures. Here, to circumvent such limitations, we have evaluated the accuracy and reliability of Wing Interferential Patterns (WIPs) generated on the surface of sandfly wings in conjunction with deep learning (DL) procedures to assign specimens at various taxonomic levels. Our dataset proves that the method can accurately identify sandflies over other dipteran insects at the family, genus, subgenus, and species level with an accuracy higher than 77.0%, regardless of the taxonomic level challenged. This approach does not require inspection of internal organs to address identification, does not rely on identification keys, and can be implemented under field or near-field conditions, showing promise for sandfly pro-active and passive entomological surveys in an era of scarcity in medical entomologists.

Wing Interferential Patterns (WIPs) and machine learning for the classification of some Aedes species of medical interest.

Hematophagous insects belonging to the Aedes genus are proven vectors of viral and filarial pathogens of medical interest. Aedes albopictus is an increasingly important vector because of its rapid worldwide expansion. In the context of global climate change and the emergence of zoonotic infectious diseases, identification tools with field application are required to strengthen efforts in the entomological survey of arthropods with medical interest. Large scales and proactive entomological surveys of Aedes mosquitoes need skilled technicians and/or costly technical equipment, further puzzled by the vast amount of named species. In this study, we developed an automatic classification system of Aedes species by taking advantage of the species-specific marker displayed by Wing Interferential Patterns. A database holding 494 photomicrographs of 24 Aedes spp. from which those documented with more than ten pictures have undergone a deep learning methodology to train a convolutional neural network and test its accuracy to classify samples at the genus, subgenus, and species taxonomic levels. We recorded an accuracy of 95% at the genus level and > 85% for two (Ochlerotatus and Stegomyia) out of three subgenera tested. Lastly, eight were accurately classified among the 10 Aedes sp. that have undergone a training process with an overall accuracy of > 70%. Altogether, these results demonstrate the potential of this methodology for Aedes species identification and will represent a tool for the future implementation of large-scale entomological surveys.