COVID-19 Artificial Intelligence Diagnosis Using Only Cough Recordings

Design of an Efficient CNN-based Cough Detection System on Lightweight FPGA

Precisely and automatically detecting the cough sound is of vital clinical importance. Nevertheless, due to privacy protection considerations, transmitting the raw audio data to the cloud is not permitted, and therefore there is a great demand for an efficient, accurate, and low-cost solution at the edge device. To address this challenge, we propose a semi-custom software-hardware co-design methodology to help build the cough detection system. Specifically, we first design a scalable and compact convolutional neural network (CNN) structure that generates many network instances. Second, we develop a dedicated hardware accelerator to perform the inference computation efficiently, and then we find the optimal network instance by applying network design space exploration. Finally, we compile the optimal network and let it run on the hardware accelerator. The experimental results demonstrate that our model achieves 88.8% classification accuracy, 91.2% sensitivity, 86.5% specificity, and 86.5% precision, while the computation complexity is only 1.09M multiply-accumulation (MAC). Additionally, when implemented on a lightweight field programmable gate array (FPGA), the complete cough detection system only occupies 7.9K lookup tables (LUTs), 12.9K flip-flops (FFs), and 41 digital signal processing (DSP) slices, providing 8.3 GOP/s actual inference throughput and total power dissipation of 0.93 W. This framework meets the needs of partial application and can be easily extended or integrated into other healthcare applications.

Application of deep learning for bronchial asthma diagnostics using respiratory sound recordings

Methods of computer-assisted diagnostics that utilize deep learning techniques on recordings of respiratory sounds have been developed to diagnose bronchial asthma. In the course of the study an anonymous database containing audio files of respiratory sound recordings of patients suffering from different respiratory diseases and healthy volunteers has been accumulated and used to train the software and control its operation. The database consists of 1,238 records of respiratory sounds of patients and 133 records of volunteers. The age of tested persons was from 18 months to 47 years. The sound recordings were captured during calm breathing at four points: in the oral cavity, above the trachea, at the chest, the second intercostal space on the right side, and at the point on the back. The developed software provides binary classifications (diagnostics) of the type: "sick/healthy" and "asthmatic patient/non-asthmatic patient and healthy". For small test samples of 50 (control group) to 50 records (comparison group), the diagnostic sensitivity metric of the first classifier was 88%, its specificity metric -86% and accuracy metric -87%. The metrics for the classifier "asthmatic patient/non-asthmatic patient and healthy" were 92%, 82%, and 87%, respectively. The last model applied to analyze 941 records in asthmatic patients indicated the correct asthma diagnosis in 93% of cases. The proposed method is distinguished by the fact that the trained model enables diagnostics of bronchial asthma (including differential diagnostics) with high accuracy irrespective of the patient gender and age, stage of the disease, as well as the point of sound recording. The proposed method can be used as an additional screening method for preclinical bronchial asthma diagnostics and serve as a basis for developing methods of computer assisted patient condition monitoring including remote monitoring and real-time estimation of treatment effectiveness.

Machine learning to analyse omic-data for COVID-19 diagnosis and prognosis

BACKGROUND

With the global spread of COVID-19, the world has seen many patients, including many severe cases. The rapid development of machine learning (ML) has made significant disease diagnosis and prediction achievements. Current studies have confirmed that omics data at the host level can reflect the development process and prognosis of the disease. Since early diagnosis and effective treatment of severe COVID-19 patients remains challenging, this research aims to use omics data in different ML models for COVID-19 diagnosis and prognosis. We used several ML models on omics data of a large number of individuals to first predict whether patients are COVID-19 positive or negative, followed by the severity of the disease.

RESULTS

On the COVID-19 diagnosis task, we got the best AUC of 0.99 with our multilayer perceptron model and the highest F1-score of 0.95 with our logistic regression (LR) model. For the severity prediction task, we achieved the highest accuracy of 0.76 with an LR model. Beyond classification and predictive modeling, our study founds ML models performed better on integrated multi-omics data, rather than single omics. By comparing top features from different omics dataset, we also found the robustness of our model, with a wider range of applicability in diverse dataset related to COVID-19. Additionally, we have found that omics-based models performed better than image or physiological feature-based models, proving the importance of the omics-based dataset for future model development.

CONCLUSIONS

This study diagnoses COVID-19 positive cases and predicts accurate severity levels. It lowers the dependence on clinical data and professional judgment, by leveraging the utilization of state-of-the-art models. our model showed wider applicability across different omics dataset, which is highly transferable in other respiratory or similar diseases. Hospital and public health care mechanisms can optimize the distribution of medical resources and improve the robustness of the medical system.

Multi-Modal Point-of-Care Diagnostics for COVID-19 Based on Acoustics and Symptoms

BACKGROUND

The COVID-19 pandemic has highlighted the need to invent alternative respiratory health diagnosis methodologies which provide improvement with respect to time, cost, physical distancing and detection performance. In this context, identifying acoustic bio-markers of respiratory diseases has received renewed interest.

OBJECTIVE

In this paper, we aim to design COVID-19 diagnostics based on analyzing the acoustics and symptoms data. Towards this, the data is composed of cough, breathing, and speech signals, and health symptoms record, collected using a web-application over a period of twenty months.

METHODS

We investigate the use of time-frequency features for acoustic signals and binary features for encoding different health symptoms. We experiment with use of classifiers like logistic regression, support vector machines and long-short term memory (LSTM) network models on the acoustic data, while decision tree models are proposed for the symptoms data.

RESULTS

We show that a multi-modal integration of inference from different acoustic signal categories and symptoms achieves an area-under-curve (AUC) of 96.3%, a statistically significant improvement when compared against any individual modality ([Formula: see text]). Experimentation with different feature representations suggests that the mel-spectrogram acoustic features performs relatively better across the three kinds of acoustic signals. Further, a score analysis with data recorded from newer SARS-CoV-2 variants highlights the generalization ability of the proposed diagnostic approach for COVID-19 detection.

CONCLUSION

The proposed method shows a promising direction for COVID-19 detection using a multi-modal dataset, while generalizing to new COVID variants.

Automatic diagnosis of COVID-19 with MCA-inspired TQWT-based classification of chest X-ray images

In this era of Coronavirus disease 2019 (COVID-19), an accurate method of diagnosis with less diagnosis time and cost can effectively help in controlling the disease spread with the new variants taking birth from time to time. In order to achieve this, a two-dimensional (2D) tunable Q-wavelet transform (TQWT) based on a memristive crossbar array (MCA) is introduced in this work for the decomposition of chest X-ray images of two different datasets. TQWT has resulted in promising values of peak signal-to-noise ratio (PSNR) and structural similarity index measure (SSIM) at the optimum values of its parameters namely quality factor (Q) of 4, and oversampling rate (r) of 3 and at a decomposition level (J) of 2. The MCA-based model is used to process decomposed images for further classification with efficient storage. These images have been further used for the classification of COVID-19 and non-COVID-19 images using ResNet50 and AlexNet convolutional neural network (CNN) models. The average accuracy values achieved for the processed chest X-ray images classification in the small and large datasets are 98.82% and 94.64%, respectively which are higher than the reported conventional methods based on different models of deep learning techniques. The average accuracy of detection of COVID-19 via the proposed method of image classification has also been achieved with less complexity, energy, power, and area consumption along with lower cost estimation as compared to CMOS-based technology.

Fundamental frequency related parameters in Brazilians with COVID-19

This study compares fundamental frequency (f_o) and fundamental frequency standard deviation (f_oSD) of COVID-19 patients with the same parameters in the speech of subjects without COVID-19, and verifies whether there is an effect of age and sex in the patient group. Both groups, subjects with and without COVID-19, are formed by Brazilian Portuguese speakers. Speech samples were obtained from 100 patients with mild to severe symptoms of COVID-19, and 100 healthy subjects. A single 31-syllable Portuguese sentence was used as the elicitation material for all subjects. The recordings were divided into four age groups. The acoustic measures were semi-automatically extracted and analyzed by a series of analyses of variance. Patients with COVID-19 present vocal differences in f_o-related parameters when compared to healthy subjects, that is, patient voices presented higher f_o and f_oSD with respect to control voices. In addition, for patient voices, there was an age and sex effect on f_o SD values. Vocal parameters of women and elderly subjects showed more marked differences in f_o-related parameters, indicating that patient voices are higher-pitched and have a higher variation of f_o SD. Consequently, f_o-related parameters may be tested as vocal biomarkers in the screening of respiratory insufficiency by voice analysis, in patients with severe symptoms of COVID-19.

D-Cov19Net: A DNN based COVID-19 detection system using lung sound

The limitations of proper detectors for COVID-19 for the proliferating number of patients provoked us to build an auto-diagnosis system to detect COVID-19 infection using only one parameter. Our designed model is based on Deep Convolution Neural Network and considers lung/respiratory sound as the deterministic input for our approach. 'D-Cov19Net' has been trained with 23,592 recordings, begetting an AUC of 0.972 and sensitivity of 0.983 after 100 epochs. The model can be of immense utility in biomedical technology due to its significant accuracy, simplicity, user convenience, feasibility, and faster detection while maintaining social distancing.

Cough Audio Analysis for COVID-19 Diagnosis

Humanity has suffered catastrophically due to the COVID-19 pandemic. One of the most reliable diagnoses of COVID-19 is RT-PCR (reverse-transcription polymer chain reaction) testing. This method, however, has its limitations. It is time consuming and requires scalability. This research work carries out a preliminary prognosis of COVID-19, which is scalable and less time consuming. The research carried out a competitive analysis of four machine-learning models namely, Multilayer Perceptron, Convolutional Neural Networks, Recurrent Neural Networks with Long Short-Term Memory, and VGG-19 with Support Vector Machines. Out of these models, Multilayer Perceptron outperformed with higher specificity of 94.5% and accuracy of 96.8%. The results show that Multilayer Perceptron was able to distinguish between positive and negative COVID-19 coughs by a robust feature embedding technique.

Coronavirus diagnosis using cough sounds: Artificial intelligence approaches

Introduction

The Coronavirus disease 2019 (COVID-19) pandemic has caused irreparable damage to the world. In order to prevent the spread of pathogenicity, it is necessary to identify infected people for quarantine and treatment. The use of artificial intelligence and data mining approaches can lead to prevention and reduction of treatment costs. The purpose of this study is to create data mining models in order to diagnose people with the disease of COVID-19 through the sound of coughing.

Method

In this research, Supervised Learning classification algorithms have been used, which include Support Vector Machine (SVM), random forest, and Artificial Neural Networks, that based on the standard "Fully Connected" neural network, Convolutional Neural Networks (CNN) and Long Short-Term Memory (LSTM) recurrent neural networks have been established. The data used in this research was from the online site sorfeh.com/sendcough/en, which has data collected during the spread of COVID-19.

Result

With the data we have collected (about 40,000 people) in different networks, we have reached acceptable accuracies.

Conclusion

These findings show the reliability of this method for using and developing a tool as a screening and early diagnosis of people with COVID-19. This method can also be used with simple artificial intelligence networks so that acceptable results can be expected. Based on the findings, the average accuracy was 83% and the best model was 95%.

Detecting Lombard Speech Using Deep Learning Approach

Robust Lombard speech-in-noise detecting is challenging. This study proposes a strategy to detect Lombard speech using a machine learning approach for applications such as public address systems that work in near real time. The paper starts with the background concerning the Lombard effect. Then, assumptions of the work performed for Lombard speech detection are outlined. The framework proposed combines convolutional neural networks (CNNs) and various two-dimensional (2D) speech signal representations. To reduce the computational cost and not resign from the 2D representation-based approach, a strategy for threshold-based averaging of the Lombard effect detection results is introduced. The pseudocode of the averaging process is also included. A series of experiments are performed to determine the most effective network structure and the 2D speech signal representation. Investigations are carried out on German and Polish recordings containing Lombard speech. All 2D signal speech representations are tested with and without augmentation. Augmentation means using the alpha channel to store additional data: gender of the speaker, F0 frequency, and first two MFCCs. The experimental results show that Lombard and neutral speech recordings can clearly be discerned, which is done with high detection accuracy. It is also demonstrated that the proposed speech detection process is capable of working in near real-time. These are the key contributions of this work.

Development of CNN-LSTM combinational architecture for COVID-19 detection

The world has been under extreme pressure due to the spread of the coronavirus. The urgency to eradicate the virus has caused distress amongst civilians and medical agencies to an equal extent. Due to anomalies observed in the results from reverse transcription-polymerase chain reaction (RTPCR) tests, more reliable options like computed tomography (CT) scan-based tests are being researched upon. In this paper, a novel combinational architecture is built upon the principles of Convolution Neural Networks (CNN) and Long Short Term Memory (LSTM) Networks to detect COVID-19 virus. This method uses chest X-ray images as inputs to combinational architecture for the classification of samples. The CNN part of the network will be used to extract features that help in the classification, and the LSTM part will be used for classification based on the extracted features. A total of 8 convolutional layers and 4 pooling layers are used for CNN and 4 LSTM layers of 64 and 128 cells respectively. Instead of the sigmoid function, a rectified linear unit function is used as an activation function. This provides non-linearity to the CNN and better accuracies in comparison. The proposed model employs a padding layer to prevent the loss of information. Accuracy, loss, F1 score, and Matthew's Correlation Coefficient (MCC) are calculated to analyse the effectiveness of the proposed architecture. The proposed model is validated using a relatively larger dataset of 7292 images. The combinational architecture provides a more informative and truthful result in the evaluation of classification as it caters to both the size of positive elements and negative elements in the dataset. The proposed CNN-LSTM model gives an accuracy of 98.91% and an MCC value of 97.84% respectively. The model is also compared with models employing transfer learning methods for similar applications.

Reliability of crowdsourced data and patient-reported outcome measures in cough-based COVID-19 screening

Mass community testing is a critical means for monitoring the spread of the COVID-19 pandemic. Polymerase chain reaction (PCR) is the gold standard for detecting the causative coronavirus 2 (SARS-CoV-2) but the test is invasive, test centers may not be readily available, and the wait for laboratory results can take several days. Various machine learning based alternatives to PCR screening for SARS-CoV-2 have been proposed, including cough sound analysis. Cough classification models appear to be a robust means to predict infective status, but collecting reliable PCR confirmed data for their development is challenging and recent work using unverified crowdsourced data is seen as a viable alternative. In this study, we report experiments that assess cough classification models trained (i) using data from PCR-confirmed COVID subjects and (ii) using data of individuals self-reporting their infective status. We compare performance using PCR-confirmed data. Models trained on PCR-confirmed data perform better than those trained on patient-reported data. Models using PCR-confirmed data also exploit more stable predictive features and converge faster. Crowd-sourced cough data is less reliable than PCR-confirmed data for developing predictive models for COVID-19, and raises concerns about the utility of patient reported outcome data in developing other clinical predictive models when better gold-standard data are available.

Considerations and Challenges for Real-World Deployment of an Acoustic-Based COVID-19 Screening System

Coronavirus disease 2019 (COVID-19) has led to countless deaths and widespread global disruptions. Acoustic-based artificial intelligence (AI) tools could provide a simple, scalable, and prompt method to screen for COVID-19 using easily acquirable physiological sounds. These systems have been demonstrated previously and have shown promise but lack robust analysis of their deployment in real-world settings when faced with diverse recording equipment, noise environments, and test subjects. The primary aim of this work is to begin to understand the impacts of these real-world deployment challenges on the system performance. Using Mel-Frequency Cepstral Coefficients (MFCC) and RelAtive SpecTrAl-Perceptual Linear Prediction (RASTA-PLP) features extracted from cough, speech, and breathing sounds in a crowdsourced dataset, we present a baseline classification system that obtains an average receiver operating characteristic area under the curve (AUC-ROC) of 0.77 when discriminating between COVID-19 and non-COVID subjects. The classifier performance is then evaluated on four additional datasets, resulting in performance variations between 0.64 and 0.87 AUC-ROC, depending on the sound type. By analyzing subsets of the available recordings, it is noted that the system performance degrades with certain recording devices, noise contamination, and with symptom status. Furthermore, performance degrades when a uniform classification threshold from the training data is subsequently used across all datasets. However, the system performance is robust to confounding factors, such as gender, age group, and the presence of other respiratory conditions. Finally, when analyzing multiple speech recordings from the same subjects, the system achieves promising performance with an AUC-ROC of 0.78, though the classification does appear to be impacted by natural speech variations. Overall, the proposed system, and by extension other acoustic-based diagnostic aids in the literature, could provide comparable accuracy to rapid antigen testing but significant deployment challenges need to be understood and addressed prior to clinical use.

Recommendations for Successful Implementation of the Use of Vocal Biomarkers for Remote Monitoring of COVID-19 and Long COVID in Clinical Practice and Research

The COVID-19 pandemic accelerated the use of remote patient monitoring in clinical practice or research for safety and emergency reasons, justifying the need for innovative digital health solutions to monitor key parameters or symptoms related to COVID-19 or Long COVID. The use of voice-based technologies, and in particular vocal biomarkers, is a promising approach, voice being a rich, easy-to-collect medium with numerous potential applications for health care, from diagnosis to monitoring. In this viewpoint, we provide an overview of the potential benefits and limitations of using voice to monitor COVID-19, Long COVID, and related symptoms. We then describe an optimal pipeline to bring a vocal biomarker candidate from research to clinical practice and discuss recommendations to achieve such a clinical implementation successfully.

Deep learning based cough detection camera using enhanced features

Coughing is a typical symptom of COVID-19. To detect and localize coughing sounds remotely, a convolutional neural network (CNN) based deep learning model was developed in this work and integrated with a sound camera for the visualization of the cough sounds. The cough detection model is a binary classifier of which the input is a two second acoustic feature and the output is one of two inferences (Cough or Others). Data augmentation was performed on the collected audio files to alleviate class imbalance and reflect various background noises in practical environments. For effective featuring of the cough sound, conventional features such as spectrograms, mel-scaled spectrograms, and mel-frequency cepstral coefficients (MFCC) were reinforced by utilizing their velocity (V) and acceleration (A) maps in this work. VGGNet, GoogLeNet, and ResNet were simplified to binary classifiers, and were named V-net, G-net, and R-net, respectively. To find the best combination of features and networks, training was performed for a total of 39 cases and the performance was confirmed using the test F1 score. Finally, a test F1 score of 91.9% (test accuracy of 97.2%) was achieved from G-net with the MFCC-V-A feature (named Spectroflow), an acoustic feature effective for use in cough detection. The trained cough detection model was integrated with a sound camera (i.e., one that visualizes sound sources using a beamforming microphone array). In a pilot test, the cough detection camera detected coughing sounds with an F1 score of 90.0% (accuracy of 96.0%), and the cough location in the camera image was tracked in real time.

A high-throughput fully automatic biosensing platform for efficient COVID-19 detection

We propose a label-free biosensor based on a porous silicon resonant microcavity and localized surface plasmon resonance. The biosensor detects SARS-CoV-2 antigen based on engineered trimeric angiotensin converting enzyme-2 binding protein, which is conserved across different variants. Robotic arms run the detection process including sample loading, incubation, sensor surface rinsing, and optical measurements using a portable spectrometer. Both the biosensor and the optical measurement system are readily scalable to accommodate testing a wide range of sample numbers. The limit of detection is 100 TCID_50/ml. The detection time is 5 min, and the throughput of one single robotic site is up to 384 specimens in 30 min. The measurement interface requires little training, has standard operation, and therefore is suitable for widespread use in rapid and onsite COVID-19 screening or surveillance.

Comparative Analysis of Deep Learning Models Used in Impact Analysis of Coronavirus Chest X-ray Imaging

The impact analysis of deep learning models for COVID-19-infected X-ray images is an extremely challenging task. Every model has unique capabilities that can provide suitable solutions for some given problem. The prescribed work analyzes various deep learning models that are used for capturing the chest X-ray images. Their performance-defining factors, such as accuracy, f1-score, training and the validation loss, are tested with the support of the training dataset. These deep learning models are multi-layered architectures. These parameters fluctuate based on the behavior of these layers, learning rate, training efficiency, or over-fitting of models. This may in turn introduce sudden changes in the values of training accuracy, testing accuracy, loss or validation loss, f1-score, etc. Some models produce linear responses with respect to the training and testing data, such as Xception, but most of the models provide a variation of these parameters either in the accuracy or the loss functions. The prescribed work performs detailed experimental analysis of deep learning image neural network models and compares them with the above said parameters with detailed analysis of these parameters with their responses regarding accuracy and loss functions. This work also analyses the suitability of these model based on the various parameters, such as the accuracy and loss functions to various applications. This prescribed work also lists out various challenges on the implementation and experimentation of these models. Solutions are provided for enhancing the performance of these deep learning models. The deep learning models that are used in the prescribed work are Resnet, VGG16, Resnet with VGG, Inception V3, Xception with transfer learning, and CNN. The model is trained with more than 1500 images of the chest-X-ray data and tested with around 132 samples of the X-ray image dataset. The prescribed work analyzes the accuracy, f1-score, recall, and precision of these models and analyzes these parameters. It also measures parameters such as training accuracy, testing accuracy, loss, and validation loss. Each epoch of every model is recorded to measure the changes in these parameters during the experimental analysis. The prescribed work provides insight for future research through various challenges and research findings with future directions.

A forced cough sound based pulmonary function assessment method by using machine learning

Pulmonary function testing (PFT) has important clinical value for the early detection of lung diseases, assessment of the disease severity, causes identification of dyspnea, and monitoring of critical patients. However, traditional PFT can only be carried out in a hospital environment, and it is challenging to meet the needs for daily and frequent evaluation of chronic respiratory diseases. In this study, we propose a novel method for accurately assessing pulmonary function by analyzing recorded forced cough sounds by mobile device without time and location restrictions. In the experiment, 309 clips of cough sound segments were separated from 133 patients who underwent PFT by using Audacity software. There are 247 clips of training samples and 62 clips of testing samples. Totally 52 features were extracted from the dataset, and principal component analysis (PCA) was used for feature reduction. Combined with biological attributes, the normalized features were regressed by using machine learning models with pulmonary function parameters (i.e., FEV1, FVC, FEV1/FVC, FEV1%, and FVC%). And a 5-fold cross-validation was applied to evaluate the performance of the regression models. As described in the experimental result, the result of coefficient of determination (R2) indicates that the support vector regression (SVR) model performed best in assessing FVC (0.84), FEV1% (0.61), and FVC% (0.62) among these models. The gradient boosting regression (GBR) model performs best in evaluating FEV1 (0.86) and FEV1/FVC (0.54). The result confirmed that the proposed method was capable of accurately assessing pulmonary function with forced cough sound. Besides, the cough sound sampling by a smartphone made it possible to conduct sampling and assess pulmonary function frequently in the home environment.

A voice-based biomarker for monitoring symptom resolution in adults with COVID-19: Findings from the prospective Predi-COVID cohort study

People with COVID-19 can experience impairing symptoms that require enhanced surveillance. Our objective was to train an artificial intelligence-based model to predict the presence of COVID-19 symptoms and derive a digital vocal biomarker for easily and quantitatively monitoring symptom resolution. We used data from 272 participants in the prospective Predi-COVID cohort study recruited between May 2020 and May 2021. A total of 6473 voice features were derived from recordings of participants reading a standardized pre-specified text. Models were trained separately for Android devices and iOS devices. A binary outcome (symptomatic versus asymptomatic) was considered, based on a list of 14 frequent COVID-19 related symptoms. A total of 1775 audio recordings were analyzed (6.5 recordings per participant on average), including 1049 corresponding to symptomatic cases and 726 to asymptomatic ones. The best performances were obtained from Support Vector Machine models for both audio formats. We observed an elevated predictive capacity for both Android (AUC = 0.92, balanced accuracy = 0.83) and iOS (AUC = 0.85, balanced accuracy = 0.77) as well as low Brier scores (0.11 and 0.16 respectively for Android and iOS when assessing calibration. The vocal biomarker derived from the predictive models accurately discriminated asymptomatic from symptomatic individuals with COVID-19 (t-test P-values<0.001). In this prospective cohort study, we have demonstrated that using a simple, reproducible task of reading a standardized pre-specified text of 25 seconds enabled us to derive a vocal biomarker for monitoring the resolution of COVID-19 related symptoms with high accuracy and calibration.

Particle Swarm Optimization-Based Extreme Learning Machine for COVID-19 Detection

COVID-19 (coronavirus disease 2019) is an ongoing global pandemic caused by severe acute respiratory syndrome coronavirus 2. Recently, it has been demonstrated that the voice data of the respiratory system (i.e., speech, sneezing, coughing, and breathing) can be processed via machine learning (ML) algorithms to detect respiratory system diseases, including COVID-19. Consequently, many researchers have applied various ML algorithms to detect COVID-19 by using voice data from the respiratory system. However, most of the recent COVID-19 detection systems have worked on a limited dataset. In other words, the systems utilize cough and breath voices only and ignore the voices of the other respiratory system, such as speech and vowels. In addition, another issue that should be considered in COVID-19 detection systems is the classification accuracy of the algorithm. The particle swarm optimization-extreme learning machine (PSO-ELM) is an ML algorithm that can be considered an accurate and fast algorithm in the process of classification. Therefore, this study proposes a COVID-19 detection system by utilizing the PSO-ELM as a classifier and mel frequency cepstral coefficients (MFCCs) for feature extraction. In this study, respiratory system voice samples were taken from the Corona Hack Respiratory Sound Dataset (CHRSD). The proposed system involves thirteen different scenarios: breath deep, breath shallow, all breath, cough heavy, cough shallow, all cough, count fast, count normal, all count, vowel a, vowel e, vowel o, and all vowels. The experimental results demonstrated that the PSO-ELM was capable of attaining the highest accuracy, reaching 95.83%, 91.67%, 89.13%, 96.43%, 92.86%, 88.89%, 96.15%, 96.43%, 88.46%, 96.15%, 96.15%, 95.83%, and 82.89% for breath deep, breath shallow, all breath, cough heavy, cough shallow, all cough, count fast, count normal, all count, vowel a, vowel e, vowel o, and all vowel scenarios, respectively. The PSO-ELM is an efficient technique for the detection of COVID-19 utilizing voice data from the respiratory system.

Ensemble multimodal deep learning for early diagnosis and accurate classification of COVID-19

Over the past few years, the awful COVID-19 pandemic effect has become a lethal sickness. The processing of the gathered samples requires extra time due to the use of medical diagnostic equipment, methodologies, and clinical testing procedures for the early diagnosis of infected individuals. An innovative multimodal paradigm for the early diagnosis and precise categorization of COVID-19 is put up as a solution to this issue. To extract distinguishing features from the prepared chest X-ray picture and cough (audio) database, chest X-ray-based and cough-based model are used here. Other public chest X-ray image datasets, and the Coswara cough (audio) dataset containing 92 COVID-19 positive, and 1079 healthy subjects (people) using the deep Uniform-Net, and Convolutional Neural Network (CNN). The weighted sum-rule fusion method and ensemble deep learning algorithms are utilized to further combine the extracted features. For the early diagnosis of patients, the framework offers an accuracy of 98.67%.

A comprehensive review of COVID-19 detection techniques: From laboratory systems to wearable devices

Screening of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) among symptomatic and asymptomatic patients offers unique opportunities for curtailing the transmission of novel coronavirus disease 2019, commonly known as COVID-19. Molecular diagnostic techniques, namely reverse transcription loop-mediated isothermal amplification (RT-LAMP), reverse transcription-polymerase chain reaction (RT-PCR), and immunoassays, have been frequently used to identify COVID-19 infection. Although these techniques are robust and accurate, mass testing of potentially infected individuals has shown difficulty due to the resources, manpower, and costs it entails. Moreover, as these techniques are typically used to test symptomatic patients, healthcare systems have failed to screen asymptomatic patients, whereas the spread of COVID-19 by these asymptomatic individuals has turned into a crucial problem. Besides, respiratory infections or cardiovascular conditions generally demonstrate changes in physiological parameters, namely body temperature, blood pressure, and breathing rate, which signifies the onset of diseases. Such vitals monitoring systems have shown promising results employing artificial intelligence (AI). Therefore, the potential use of wearable devices for monitoring asymptomatic COVID-19 individuals has recently been explored. This work summarizes the efforts that have been made in the domains from laboratory-based testing to asymptomatic patient monitoring via wearable systems.

A novel deep fusion strategy for COVID-19 prediction using multimodality approach

Over the last two years, the novel coronavirus has become a significant threat to the health of the public, and numerous approaches are developed to determine the symptoms of COVID-19. To deal with the complex symptoms of COVID-19, a Deep Learning-assisted Multi-modal Data Analysis (DMDA) approach is introduced to determine COVID-19 symptoms by utilizing acoustic and image-based data. Furthermore, the classified events are forwarded to the proposed Dynamic Fusion Strategy (DFS) for confirming the health status of the individual. Initially, the performance of the proposed solution is evaluated on both acoustic and image-based samples and the proposed solution attains the maximum accuracy of 96.88% and 98.76%, respectively. Similarly, the DFS has achieved an overall symptom determination accuracy of 98.72% which is highly acceptable for decision-making. Moreover, the proposed solution shows high reliability with an accuracy of 95.64% even in absence of any one of the data modalities during testing.

Use of Breath Analysis for Diagnosing COVID-19: Opportunities, Challenges, and Considerations for Future Pandemic Responses

Due to the coronavirus disease 2019 (COVID-19) pandemic, there is currently a need for accurate, rapid, and easy-to-administer diagnostic tools to help communities manage local outbreaks and assess the spread of disease. The use of artificial intelligence within the domain of breath analysis techniques has shown to have potential in diagnosing a variety of diseases, such as cancer and lung disease, by analyzing volatile organic compounds (VOCs) in exhaled breath. This combined with their rapid, easy-to-use, and noninvasive nature makes them a good candidate for use in diagnosing COVID-19 in large scale public health operations. However, there remains issues with their implementation when it comes to the infrastructure currently available to support their use on a broad scale. This includes issues of standardization, and whether or not a characteristic VOC pattern can be identified for COVID-19. Despite these difficulties, breathalyzers offer potential to assist in pandemic responses and their use should be investigated.

Chest X ray and cough sample based deep learning framework for accurate diagnosis of COVID-19

All witnessed the terrible effects of the COVID-19 pandemic on the health and work lives of the population across the world. It is hard to diagnose all infected people in real time since the conventional medical diagnosis of COVID-19 patients takes a couple of days for accurate diagnosis results. In this paper, a novel learning framework is proposed for the early diagnosis of COVID-19 patients using hybrid deep fusion learning models. The proposed framework performs early classification of patients based on collected samples of chest X-ray images and Coswara cough (sound) samples of possibly infected people. The captured cough samples are pre-processed using speech signal processing techniques and Mel frequency cepstral coefficient features are extracted using deep convolutional neural networks. Finally, the proposed system fuses extracted features to provide 98.70% and 82.7% based on Chest-X ray images and cough (audio) samples for early diagnosis using the weighted sum-rule fusion method.

Evaluation of Respiratory Sounds Using Image-Based Approaches for Health Measurement Applications

Goal: The evaluation of respiratory events using audio sensing in an at-home setting can be indicative of worsening health conditions. This paper investigates the use of image-based transfer learning applied to five audio visualizations to evaluate three classification tasks (C1: wet vs. dry vs. whooping cough vs. restricted breathing; C2: wet vs. dry cough; C3: cough vs. restricted breathing). Methods: The five visualizations (linear spectrogram, logarithmic spectrogram, Mel-spectrogram, wavelet scalograms, and aggregate images) are applied to a pre-trained AlexNet image classifier for all tasks. Results: The aggregate image-based classifier achieved the highest overall performance across all tasks with C1, C2, and C3 having testing accuracies of 0.88, 0.88, and 0.91 respectively. However, the Mel-spectrogram method had the highest testing accuracy (0.94) for C2. Conclusions: The classification of respiratory events using aggregate image inputs to transfer learning approaches may help healthcare professionals by providing information that would otherwise be unavailable to them.

Smartphone in medicine — from a reference book to a diagnostic system. Overview of the current state of the issue

The paper provides a brief overview of the modern possibilities of using a smartphone as a diagnostic device of a wide profile. In some cases, additional specialized attachments are required. In others, the diagnostic algorithm uses only standard cameras, a microphone and various built-in smartphone sensors. The development of the smartphone integration into the healthcare system is modern, relevant and very promising, given the widespread use of smartphones among the global population.

Challenges and Opportunities of Deep Learning for Cough-Based COVID-19 Diagnosis: A Scoping Review

In the past two years, medical researchers and data scientists worldwide have focused their efforts on containing the pandemic of coronavirus disease 2019 (COVID-19). Deep learning models have been proven to be capable of efficient medical diagnosis and prognosis in cancer, common lung diseases, and COVID-19. On the other hand, artificial neural networks have demonstrated their potential in pattern recognition and classification in various domains, including healthcare. This literature review aims to report the state of research on developing neural network models to diagnose COVID-19 from cough sounds to create a cost-efficient and accessible testing tool in the fight against the pandemic. A total of 35 papers were included in this review following a screening of the 161 outputs of the literature search. We extracted information from articles on data resources, model structures, and evaluation metrics and then explored the scope of experimental studies and methodologies and analyzed their outcomes and limitations. We found that cough is a biomarker, and its associated information can determine an individual's health status. Convolutional neural networks were predominantly used, suggesting they are particularly suitable for feature extraction and classification. The reported accuracy values ranged from 73.1% to 98.5%. Moreover, the dataset sizes ranged from 16 to over 30,000 cough audio samples. Although deep learning is a promising prospect in identifying COVID-19, we identified a gap in the literature on research conducted over large and diversified data sets.

A comparative analysis of deep neural network architectures for the dynamic diagnosis of COVID-19 based on acoustic cough features

The study aims to assess the detection performance of a rapid primary screening technique for COVID-19 that is purely based on the cough sound extracted from 2200 clinically validated samples using laboratory molecular testing (1100 COVID-19 negative and 1100 COVID-19 positive). Results and severity of samples based on quantitative RT-PCR (qRT-PCR), cycle threshold, and patient lymphocyte numbers were clinically labeled. Our suggested general methods consist of a tensor based on audio characteristics and deep-artificial neural network classification with deep cough convolutional layers, based on the dilated temporal convolution neural network (DTCN). DTCN has approximately 76% accuracy, 73.12% in TCN, and 72.11% in CNN-LSTM which have been trained at a learning rate of 0.2%, respectively. In our scenario, CNN-LSTM can no longer be employed for COVID-19 predictions, as they would generally offer questionable forecasts. In the previous stage, we discussed the exactness of the total cases of TCN, dilated TCN, and CNN-LSTM models which were truly predicted. Our proposed technique to identify COVID-19 can be considered as a robust and in-demand technique to rapidly detect the infection. We believe it can considerably hinder the COVID-19 pandemic worldwide.

COVID-19: respiratory disease diagnosis with regularized deep convolutional neural network using human respiratory sounds

Human respiratory sound auscultation (HRSA) parameters have been the real choice for detecting human respiratory diseases in the last few years. It is a challenging task to extract the respiratory sound features from the breath, voice, and cough sounds. The existing methods failed to extract the sound features to diagnose respiratory diseases. We proposed and evaluated a new regularized deep convolutional neural network (RDCNN) architecture to accept COVID-19 sound data and essential sound features. The proposed architecture is trained with the COVID-19 sound data sets and gives a better learning curve than any other state-of-the-art model. We examine the performance of RDCNN with Max-Pooling (Model-1) and without Max-Pooling (Model-2) functions. In this work, we observed that RDCNN model performance with three sound feature extraction methods [Soft-Mel frequency channel, Log-Mel frequency spectrum, and Modified Mel-frequency Cepstral Coefficient (MMFCC) spectrum] for COVID-19 sound data sets (KDD-data, ComParE2021-CCS-CSS-Data, and NeurlPs2021-data). To amplify the models' performance, we applied the augmentation technique along with regularization. We have also carried out this work to estimate the mutation of SARS-CoV-2 in the five waves using prognostic models (fractal-based). The proposed model achieves state-of-the-art performance on the COVID-19 sound data set to identify COVID-19 disease symptoms. The model's learnable parameter gradients have vanished in the intermediate layers while optimizing the prediction error which is addressed with our proposed RDCNN model. Our experiments suggested that 3 × 3 kernel size for regularized deep CNN (without max-pooling) shows 2-3% better classification accuracy compared to RDCNN with max-pooling. The experimental results suggest that this new approach may achieve the finest results on respiratory diseases.

Mobile Sensing in the COVID-19 Era: A Review

Background

During the COVID-19 pandemic, mobile sensing and data analytics techniques have demonstrated their capabilities in monitoring the trajectories of the pandemic, by collecting behavioral, physiological, and mobility data on individual, neighborhood, city, and national scales. Notably, mobile sensing has become a promising way to detect individuals' infectious status, track the change in long-term health, trace the epidemics in communities, and monitor the evolution of viruses and subspecies.

Methods

We followed the PRISMA practice and reviewed 60 eligible papers on mobile sensing for monitoring COVID-19. We proposed a taxonomy system to summarize literature by the time duration and population scale under mobile sensing studies.

Results

We found that existing literature can be naturally grouped in four clusters, including remote detection, long-term tracking, contact tracing, and epidemiological study. We summarized each group and analyzed representative works with regard to the system design, health outcomes, and limitations on techniques and societal factors. We further discussed the implications and future directions of mobile sensing in communicable diseases from the perspectives of technology and applications.

Conclusion

Mobile sensing techniques are effective, efficient, and flexible to surveil COVID-19 in scales of time and populations. In the post-COVID era, technical and societal issues in mobile sensing are expected to be addressed to improve healthcare and social outcomes.

Non-Contact Supervision of COVID-19 Breathing Behaviour With FMCW Radar and Stacked Ensemble Learning Model in Real-Time

A respiratory disorder that attacks COVID-19 patients requires intensive supervision of medical practitioners during the isolation period. A non-contact monitoring device will be a suitable solution for reducing the spread risk of the virus while monitoring the COVID-19 patient. This study uses Frequency-Modulated Continuous Wave (FMCW) radar and Machine Learning (ML) to obtain respiratory information and analyze respiratory signals, respectively. Multiple subjects in a room can be detected simultaneously by calculating the Angle of Arrival (AoA) of the received signal and utilizing the Multiple Input Multiple Output (MIMO) of FMCW radar. Fast Fourier Transform (FFT) and some signal processing are implemented to obtain a breathing waveform. ML helps the system to analyze the respiratory signals automatically. This paper also compares the performance of several ML algorithms such as Multinomial Logistic Regression (MLR), Decision Tree (DT), Random Forest (RF), Support Vector Machine (SVM), eXtreme Gradient Boosting (XGB), Light Gradient Boosting Machine (LGBM), CatBoosting (CB) Classifier, Multilayer Perceptron (MLP), and three proposed stacked ensemble models, namely Stacked Ensemble Classifier (SEC), Boosting Tree-based Stacked Classifier (BTSC), and Neural Stacked Ensemble Model (NSEM) to obtain the best ML model. The results show that the NSEM algorithm achieves the best performance with 97.1% accuracy. In the real-time implementation, the system could simultaneously detect several objects with different breathing characteristics and classify the respiratory signals into five different classes.

Automatic Non-Invasive Cough Detection based on Accelerometer and Audio Signals

We present an automatic non-invasive way of detecting cough events based on both accelerometer and audio signals. The acceleration signals are captured by a smartphone firmly attached to the patient’s bed, using its integrated accelerometer. The audio signals are captured simultaneously by the same smartphone using an external microphone. We have compiled a manually-annotated dataset containing such simultaneously-captured acceleration and audio signals for approximately 6000 cough and 68000 non-cough events from 14 adult male patients. Logistic regression (LR), support vector machine (SVM) and multilayer perceptron (MLP) classifiers provide a baseline and are compared with three deep architectures, convolutional neural network (CNN), long short-term memory (LSTM) network, and residual-based architecture (Resnet50) using a leave-one-out cross-validation scheme. We find that it is possible to use either acceleration or audio signals to distinguish between coughing and other activities including sneezing, throat-clearing, and movement on the bed with high accuracy. However, in all cases, the deep neural networks outperform the shallow classifiers by a clear margin and the Resnet50 offers the best performance, achieving an area under the ROC curve (AUC) exceeding 0.98 and 0.99 for acceleration and audio signals respectively. While audio-based classification consistently offers better performance than acceleration-based classification, we observe that the difference is very small for the best systems. Since the acceleration signal requires less processing power, and since the need to record audio is sidestepped and thus privacy is inherently secured, and since the recording device is attached to the bed and not worn, an accelerometer-based highly accurate non-invasive cough detector may represent a more convenient and readily accepted method in long-term cough monitoring.

End-to-end design of wearable sensors

Wearable devices provide an alternative pathway to clinical diagnostics by exploiting various physical, chemical and biological sensors to mine physiological (biophysical and/or biochemical) information in real time (preferably, continuously) and in a non-invasive or minimally invasive manner. These sensors can be worn in the form of glasses, jewellery, face masks, wristwatches, fitness bands, tattoo-like devices, bandages or other patches, and textiles. Wearables such as smartwatches have already proved their capability for the early detection and monitoring of the progression and treatment of various diseases, such as COVID-19 and Parkinson disease, through biophysical signals. Next-generation wearable sensors that enable the multimodal and/or multiplexed measurement of physical parameters and biochemical markers in real time and continuously could be a transformative technology for diagnostics, allowing for high-resolution and time-resolved historical recording of the health status of an individual. In this Review, we examine the building blocks of such wearable sensors, including the substrate materials, sensing mechanisms, power modules and decision-making units, by reflecting on the recent developments in the materials, engineering and data science of these components. Finally, we synthesize current trends in the field to provide predictions for the future trajectory of wearable sensors.

Cybersecurity

Cybersecurity policies aim to ensure that digital technologies are safe and resilient. It is impossible to guarantee that technology is fully cyber-incident proof. However, it is possible and desirable to increase technologies’ resilience to incidents and malicious attacks to minimize the risk of using technology. For this reason, cybersecurity is an essential ingredient of any public strategies geared to fostering the digital economy: lowering risk implies lowering the economy’s expected costs and increasing the likelihood of adoption through greater trust. Cyber-risk can entail enormous costs for the economy, businesses, and ordinary users alike. However, markets do not autonomously converge to the optimal level of investment in cybersecurity from a social point of view, and public policy is needed to create the right incentives and steer all actors to contribute to the safety of the cyberspace.

Digital Government

Digitizing the public sector has become imperative for every country in the world. A digitized public administration is leaner, faster, and more efficient. It can better identify and anticipate its constituency’s issues; it is transparent and accountable. That is all the more necessary to enable governments to perform increasingly challenging tasks, such as dealing with shrinking public budgets, meeting citizens’ raising expectations, and relating with a highly dynamic surrounding economic environment. Transformation is, however, far from easy. Technological adoption, the modernization of infrastructure, and the upskilling of the public workforce are just the first steps. A digital public sector requires a radical cultural change for public employees and citizens alike. It begs for significant investment and efforts to establish a mutually beneficial communication flow between public administrations and citizens, business, and society at large. Of particular relevance is the use of data in the public sector. Data is a powerful enabler of innovation. But to unleash its full potential, it needs the proper governance framework.

Technology and Employment

Technology can improve workers’ productivity, but it can also make them redundant: if machines and algorithms can perform the same job faster and at a lower cost, why would anybody employ human workers? As it turns out, the previous industrial revolutions did not reduce the need for humans in labour markets. Instead, they induced a transformation of the jobs that workers were required to perform, creating new opportunities and tasks that only humans could pursue. It may be reasonable to expect that this time, with the Fourth Industrial Revolution brought about by technological progress, is not going to be any different. New jobs will be created, and technological adoption will not produce structural unemployment. However, even if this is the case, the transition is nevertheless costly and necessarily painful for a significant part of the working population. Thus, public policies are needed to protect workers temporarily displaced or in atypical employment contracts with wide and flexible social safety nets. Lifelong learning may be the best way to ensure a smooth transition to labour markets 4.0.

Technology and the Covid-19 Pandemic

The Covid-19 pandemic had a brutal impact on the life of human beings around the globe. As of March 2020, SARS-CoV-2, a virus provoking severe acute respiratory syndrome, had spread from China to the rest of the world. Billions of people experienced severe limitations to their fundamental rights to move, work, and engage in physical contact with other human beings. Technology supported the global effort to respond to the health emergency and provided a lifeline for economies. Digital services allowed families to be in contact through videoconference applications or social networks. E-commerce fuelled home-delivery services to locked-down households. Technology made telework possible when offices were not accessible. But technology played a double role. It exacerbated the opportunity gap between those who could use it for studying or working and those who could not, facilitating the spread of misleading information on the virus, and shifting economic value to dominant digital companies, aggravating those concentration tendencies that have been increasingly observed in online markets. While the pandemic has undoubtedly pushed the economy to become more digitized, the outstanding question is how much of that level of digitization will be retained by business and users alike after the pandemic is over.

Artificial Intelligence

Artificial intelligence (AI) holds the keys to unlocking a future of unconceivable prosperity for humankind: it may dramatically boost the performance of economies and provide unprecedented opportunities for citizens, companies, and the public sector. It may also advance our ability to address humanity’s challenges, such as providing effective tools for disaster control, a weapon against climate change, or a cure for diseases like cancer. But AI also conceals the potential for a future at the other end of the spectrum. A future where citizens of dystopian societies undergo permanent monitoring for the way they behave or could behave. Where discriminatory treatment is a norm and fundamental rights are systematically ignored. A society where the gap between the haves and have-nots becomes unbridgeable. The role of public policy in the AI space is thus extremely important. Public policy can create the conditions for humanity to get the most out of AI while steering it away from the dystopian future, popularly depicted in science fiction books or films, by designing appropriate ethical and legal frameworks to protect society’s core values.

The Sharing Economy

Nothing better represents the meaning of digital disruption than the “sharing economy”. Online sharing platforms allow owners of under-used assets (for example, a car, a house, or even a specific knowledge or expertise) to compete with established businesses, offering services of comparable, if not enhanced, quality and exploit their assets in a profitable way. Users can access services often supplied by non-professional “peers” at advantageous conditions compared to those offered by professionals. The resulting impact on markets and legacy businesses can be wide and significant, though not always positive: it may concern the environment, labour markets, and society at large, with important implications for policy-making. This chapter provides an overview of the sharing economy and analyses its main features.

Connectivity

Fast and reliable connectivity is the first indispensable input for a digitized economy and society. However, telecom markets are highly complex. Their structural features, such as the need for high sunk investment to deploy infrastructure and the relationship between networks’ size and services’ quality, make it unlikely that they would work efficiently without public intervention. Thus, public policy is needed, particularly to pursue two overarching goals: (1) to incentivize investment to achieve high speed, reliability, responsiveness, and security of data traffic; and (2) to incentivize access under reasonable terms for everybody everywhere. Concretely, the success of the EU long-term telecom strategic plan should be measured against two indicators: the deployment of wired optical fibre networks and wireless 5G networks, especially where services are less profitable (in rural areas, for example); and the degree of cross-border connectivity. A variety of public policy tools are available to pursue those plans: “push” policies to directly support the deployment of new networks; “pull” policies to attract investment stimulating demand of digital services; spectrum management policies; and regulation and competition policy to stimulate and preserve a dynamic, pro-competitive telecom environment.

The Data Economy

Data is an essential input to the digital economy. As we have seen in the case of connectivity, a digital economy and society cannot prosper without a flourishing data economy behind it. However, the data value chain poses difficult challenges to policymakers, giving rise to complex and novel issues. Several important economic structural features associated with data and lack of transparency or competition often lead data markets to malfunction. Public policy can intervene, fostering competition and realigning the incentives of market players with those of society to achieve higher welfare levels. The European Union’s institutions have been very active in the area, setting global standards for privacy protection with the 2018 General Data Protection Regulation (GDPR) and designing actions to support the development and uptake of data analytics in Europe.

Digital Economic Policy. 2022. [DOI: 10.1093/oso/9780198831471.001.0001] [Citation(s) in RCA: 0] [Impact Index Per Article: 0]

The emergence of new technologies and business models such as data analytics, online platforms, and artificial intelligence has shaken the economy and society at their foundations. Recently, it has become apparent that public authorities must take a pro-active role to define the rules of the newly emerged markets before potential issues and concerns cement. How rules are currently written determines who will exert a stronger influence on the economy and society in the coming years. This is a key reason why digital policymakers are currently exposed to tremendous pressure by stakeholders. This book takes a journey through all the main areas in the digital economy that beg for policy action. Readers may learn about the general features of a digital economy and the EU long-term strategic plans to govern it. They may learn about telecom markets, the data economy, the digitization of the public sector, cybersecurity, the platform economy, liability for online content, e-commerce, the sharing economy, the impact of technology on labour markets, digital inequality, disinformation, and artificial intelligence. This book primarily aims to provide students with the background knowledge and analytical tools necessary to understand, analyse, and assess the impact of EU digital policies on the European economy and society. The approach is both theoretical and applied. The main goal is to prepare students to give informed and economically sound advice to an EU policymaker for digital affairs.

E-Commerce

E-commerce is a general term encompassing any trade activity facilitated by the use of a digital interface. The vast majority of e-commerce transactions involve business customers. However, consumers are increasingly relying on e-commerce to fulfil their shopping needs. E-commerce brings significant advantages to the economy: it boosts companies’ productivity, reduces costs, and increases convenience. But its growth is hampered by several obstacles, such as regulatory frictions, access to digital infrastructure and skills, logistical costs, lack of trust and compliance costs, and uncertainty due to outdated taxation frameworks. These issues can, in particular, limit the expansion of e-commerce cross-border and prevent the completion of a functioning EU Digital Single Market. Policy measures of different nature are thus needed to foster regulatory harmonization, increase trust and security, and eliminate potential distortions of competition.

Online Content and Platform Liability

In their early days, online platforms were considered neutral intermediaries with no direct editorial responsibility. That is the approach enshrined in the 2000 e-Commerce EU Directive, whereby information society services are not considered liable for the illegal content they unknowingly host. That principle may be not entirely suitable to address today’s challenges. In particular, platforms have been subject to increasing public pressure to take on a proactive role to limit the ever-growing spread of harmful content online: from incitement to hatred, from violence to child pornography. A change in platforms’ liability approach seems all the more sensible since platforms have, over time, outgrown their mere intermediary role and acquired the sophisticated technological means necessary to monitor their users’ behaviour. Yet entrusting platforms with a proactive screening role for the content they host entails a significant risk: hampering users’ freedom of expression. Ultimately, it has the potential to undermine the functioning of the Internet as we know it today. Reconciling the two sides of the dilemma is the fundamental goal of policy action.

An Introduction to Online Platforms

The emergence of online platforms has radically changed how goods and services are produced, supplied, and consumed. Online platforms became the primary vehicle of information flow between market players and now play a pivotal role in the economy and society. The magnitude of benefits brought by platforms cannot be overstated. Day-to-day benefits and gains range from easier communication thanks to social media and new types of online services, to the convenience and reduced transaction costs related to online purchases and home delivery, to the ubiquitous access to information offered by Internet search engines. But at the same time, as a small number of tech companies grow in dominance in the globally integrated business environment, non-negligible downsides have emerged: platforms have a great potential to cause harm. Given the complexity and the novelty of their business dynamics, market failures are particularly tricky to identify and address. It is the job of policymakers to verify whether the current regulatory framework is still adequate to ensure the correct functioning of markets and, if not, to propose efficient solutions. Updating competition policy and regulatory tools may be amongst those.

Digital Inequality

Technological development is often presented as a powerful way to enhance the human condition, particularly for the most vulnerable segments of the population. Digital technologies can improve the efficiency of general interest services, most notably in the health care and educational sectors. They generate opportunities and reduce costs for consumers, workers, and small entrepreneurs. New technologies provide for incredibly effective communication channels, enhancing political participation and amplifying the voice of those who are the margin of society. On the contrary, history shows that the most recent technological development cemented and even exacerbated off-line inequalities, contributing to polarizing societies and widening the gap between the haves and the have-nots. A key driver of this extremely worrying phenomenon is the digital divide, defined as individuals’ different exposure to the opportunities offered by technology, both in terms of access and ability to use it and profit from it. Policymakers must deploy policy solutions that would promote wider access to technology within the population and a more symmetric distribution of the benefits that stem from it. Policy should drive technological development to correct off-line inequality rather than exacerbate it.

A Digital Economy

Throughout history, economies and societies have always been deeply affected by technology. Radical technological innovations, such as steam-power, electricity or electronics, prompted the first, second, and third industrial revolutions. Now, countries worldwide are experiencing a fourth, equally disruptive, industrial revolution, thanks to the Internet and powerful emerging technologies such as artificial intelligence. As society becomes more and more reliant on digital applications, action by public policy is required to correct markets where they fail to deliver optimal outcomes, namely: creating significant value and ensuring that everyone can enjoy it. The job is not easy, and digital policy needs to address complex challenges: it needs to balance dynamism and stability, to address regulatory fragmentation in a highly fluid, fast-changing, environment; to solve novel economic puzzles and to answer profound philosophical dilemmas. Nations around the world are deploying digital policy strategies in an attempt to secure an overarching consistent public approach to emerging issues.

Disinformation in the Digital Age

Disinformation is an ancient phenomenon that digitization boosted. It is impossible to say whether the average quality of information is higher or lower online than what it was before, when news could only circulate through print, radio, or TV. Today, however, the game has changed: it is far easier to generate and spread information to reach wide audiences in the Internet age. And the predominant online business model, highly dependent on web traffic and advertisement, undoubtedly generates high incentives to maximize audience, possibly by eliciting emotional engagement in users and arousing them to share false stories on social media. Markets seem unable to curb disinformation by themselves. Thus, public policy is needed to reduce the spread of false information online and defuse its potentially harmful effects. Measures include fact-checking and enabling access to high-quality media, forcing platforms to become more transparent and forthcoming, for example, allowing researchers to access their data. Furthermore, promising actions include empowering users with educational tools to overcome their “behavioural biases” and increase their wariness towards what they read or view online.