An automated COVID-19 triage pipeline using artificial intelligence based on chest radiographs and clinical data

While COVID-19 diagnosis and prognosis artificial intelligence models exist, very few can be implemented for practical use given their high risk of bias. We aimed to develop a diagnosis model that addresses notable shortcomings of prior studies, integrating it into a fully automated triage pipeline that examines chest radiographs for the presence, severity, and progression of COVID-19 pneumonia. Scans were collected using the DICOM Image Analysis and Archive, a system that communicates with a hospital’s image repository. The authors collected over 6,500 non-public chest X-rays comprising diverse COVID-19 severities, along with radiology reports and RT-PCR data. The authors provisioned one internally held-out and two external test sets to assess model generalizability and compare performance to traditional radiologist interpretation. The pipeline was evaluated on a prospective cohort of 80 radiographs, reporting a 95% diagnostic accuracy. The study mitigates bias in AI model development and demonstrates the value of an end-to-end COVID-19 triage platform.

Regression and Artificial Intelligence Models to Predict the Surface Roughness in Additive Manufacturing

In additive manufacturing (AM), it is necessary to study the surface roughness, which affected the building parameters such as layer thickness and building orientation. Some AM machines have minimum layer thickness that doesn't satisfy the desired roughness. Also, it produces a fine surface that isn't required. This increases the building time and cost without any benefits. To overcome these problems and achieve a certain surface roughness, a prediction model is proposed in this chapter. Regression models were used to predict the surface roughness through the building orientation. ANN was used to predict the surface roughness through the building orientation and the layer thickness together. ANN was constructed based on experimental work that study the effect of layer thickness and building orientation on the surface roughness. Some data were used in the training process and others were used in the verification process. The results show that the layer thickness parameter has an effect more than the building orientation parameter on the surface roughness.

A Cutting-Edge Survey of Tribological Behavior Evaluation Using Artificial and Computational Intelligence Models

Any metal surface’s usefulness is essential in various applications such as machining and welding and aerospace and aerodynamic applications. There is a great deal of wear in metals, used widely in machines and appliances. The gradual loss of the upper metal layers in all metal parts is inevitable over the machine or component’s lifetime. Artificial intelligence implementations and computational models are being studied to evaluate different metals’ tribological behavior, as technological progress has been made in this field. Different neural networks were used for different metals. They are classified in this paper, together with a description of their benefits and inconveniences and an overview and use of the different types of wear. Artificial intelligence is a relatively new term that uses mechanical engineering. There is still no scientific progress to examine various metal wear cases and compare AI and computational models’ accuracy in wear behavior.

Attention Autoencoder for Generative Latent Representational Learning in Anomaly Detection

Today, accurate and automated abnormality diagnosis and identification have become of paramount importance as they are involved in many critical and life-saving scenarios. To accomplish such frontiers, we propose three artificial intelligence models through the application of deep learning algorithms to analyze and detect anomalies in human heartbeat signals. The three proposed models include an attention autoencoder that maps input data to a lower-dimensional latent representation with maximum feature retention, and a reconstruction decoder with minimum remodeling loss. The autoencoder has an embedded attention module at the bottleneck to learn the salient activations of the encoded distribution. Additionally, a variational autoencoder (VAE) and a long short-term memory (LSTM) network is designed to learn the Gaussian distribution of the generative reconstruction and time-series sequential data analysis. The three proposed models displayed outstanding ability to detect anomalies on the evaluated five thousand electrocardiogram (ECG5000) signals with 99% accuracy and 99.3% precision score in detecting healthy heartbeats from patients with severe congestive heart failure.

Early Diagnosis of Liver Metastases from Colorectal Cancer through CT Radiomics and Formal Methods: A Pilot Study

Background: Liver metastases are a leading cause of cancer-associated deaths in patients affected by colorectal cancer (CRC). The multidisciplinary strategy to treat CRC is more effective when the radiological diagnosis is accurate and early. Despite the evolving technologies in radiological accuracy, the radiological diagnosis of Colorectal Cancer Liver Metastases (CRCLM) is still a key point. The aim of our study was to define a new patient representation different by Artificial Intelligence models, using Formal Methods (FMs), to help clinicians to predict the presence of liver metastasis when still undetectable using the standard protocols. Methods: We retrospectively reviewed from 2013 to 2020 the CT scan of nine patients affected by CRC who would develop liver lesions within 4 months and 8 years. Seven patients developed liver metastases after primary staging before any liver surgery, and two patients were enrolled after R0 liver resection. Twenty-one patients were enrolled as the case control group (CCG). Regions of Interest (ROIs) were identified through manual segmentation on the medical images including only liver parenchyma and eventual benign lesions, avoiding major vessels and biliary ducts. Our predictive model was built based on formally verified radiomic features. Results: The precision of our methods is 100%, scheduling patients as positive only if they will be affected by CRCLM, showing a 93.3% overall accuracy. Recall was 77.8%. Conclusion: FMs can provide an effective early detection of CRCLM before clinical diagnosis only through non-invasive radiomic features even in very heterogeneous and small clinical samples.

DIAGNOSIS OF COVID-19 BASED ON ARTIFICIAL INTELLIGENCE MODELS AND PHYSIOLOGICAL SENSORS: REVIEW

Covid-19 invaded the world very quickly and caused the loss of many lives; maximum emergency was activated all over the world due to its rapid spread. Consequently, it became a huge burden on emergency and intensive care units due to the large number of infected individuals and the inability of the medical staff to deal with patients according to the degree of severity. Covid-19 can be diagnosed based on the artificial intelligence (AI) model. Based on AI, the CT images of the patient’s chest can be analyzed to identify the patient case whether it is normal or he/she has Covid-19. The possibility of employing physiological sensors such as heart rate, temperature, respiratory rate, and SpO2 sensors in diagnosing Covid-19 was investigated. In this paper, several articles which used intelligent techniques and vital signs for diagnosing Covid-19 have been reviewed, classified, and compared. The combination of AI and physiological sensors reading, called AI-PSR, can help the clinician in making the decisions and predicting the occurrence of respiratory failure in Covid-19 patients. The physiological parameters of the Covid-19 patients can be transmitted wirelessly based on a specific wireless technology such as Wi-Fi and Bluetooth to the clinician to avoid direct contact between the patient and the clinician or nursing staff. The outcome of the AI-PSR model leads to the probability of recording and linking data with what will happen later, to avoid respiratory failure, and to help the patient with one of the mechanical ventilation devices.

Identifying Perverse Incentives in Buyer Profiling on Online Trading Platforms

With advance machine learning and artificial intelligence models, the capability of online trading platforms to profile consumers to identify and understand their needs has substantially increased. In this study, we use an analytical model to study whether these platforms have an incentive to profile their customers as accurately as possible. We find that “payments-for-transactions” platforms (i.e., platforms that charge for transactions that occur on the platform) indeed have such incentives to accurately profile the customers. However, surprisingly, “payments-for-discoveries” platform (i.e., platforms that charge customers for discoveries) have a perverse incentive to deviate from accurate consumer profiling. Our study provides insights into underlying mechanisms that drive this perverse incentive and discuss circumstances that lead to such a perverse incentive.