Nowadays, very large amounts of data are generating at a fast rate from a wide variety of rich data sources. Valuable information and knowledge embedded in these big data can be discovered by data science, data mining and machine learning techniques. Biomedical records are examples of the big data. With the technological advancements, more healthcare practice has gradually been supported by electronic processes and communication. This enables health informatics, in which computer science meets the healthcare sector to address healthcare and medical problems. As a concrete example, there have been more than 635 millions cumulative cases of coronavirus disease 2019 (COVID-19) worldwide over the past 3 years since COVID-19 has declared as a pandemic. Hence, effective strategies, solutions, tools and methods—such as artificial intelligence (AI) and/or big data approaches—to tackle the COVID-19 pandemic and possible future pandemics are in demand. In this paper, we present models to analyze big COVID-19 pandemic data and make predictions via N-shot learning. Specifically, our binary model predicts whether patients are COVID-19 or not. If so, the model predicts whether they require hospitalization or not, whereas our multi-class model predicts severity and thus the corresponding levels of hospitalization required by the patients. Our models uses N-shot learning with autoencoders. Evaluation results on real-life pandemic data demonstrate the practicality of our models towards effective allocation of resources (e.g., hospital facilities, staff). These showcase the benefits of AI and/or big data approaches in tackling the pandemic.

Health informatics is an interdisciplinary area where computer science and related disciplines meet to address problems and support healthcare and medicine. In particular, computer has played an important role in medicine. Many existing computer-based systems (e.g., machine learning models) for healthcare applications produce binary prediction (e.g., whether a patient catches a disease or not). However, there are situations in which a non-binary prediction (e.g., what is hospitalization status of a patient) is needed. As a concrete example, over the past two years, people around the world have been affected by the coronavirus disease 2019 (COVID-19) pandemic. There have been works on binary prediction to determine whether a patient is COVID-19 positive or not. With availability of alternative methods (e.g., rapid test), such a binary prediction has become less important. Moreover, with the evolution of the disease (e.g., recent development of COVID-19 Omicron variant), multi-label prediction of the hospitalization status has become more important when compared with binary prediction on the confirmation of cases. Hence, in this paper, we present a multi-label prediction system for computer-based medical applications. Our system makes use of autoencoders (consisting of encoders and decoders) and few-shot learning to predict the hospitalization status (e.g., ICU, semi-ICU, regular wards, or no hospitalization). The prediction is important for allocation of medical resources (e.g., hospital facilities and medical staff), which in turn affect patient lives. Experimental results on real-life open datasets show that, when training with only a few data, our multilabel prediction system gave a high F1-score when predicting hospitalization status of COVID-19 cases.

Bus riders desire precision and accuracy when using the transit system. While the transit system is responsible for maintaining and delivering public transportation services for the city residents, they rely on idealized assumptions regarding real-world bus driving conditions. The published bus schedule seems to assume that the buses move at a uniform speed at all times, which leads to bus arrival times that are imprecise and inaccurate. Busses can arrive early, late, or on time. Given that bus stops cannot have a dynamic schedule, it is logical to create a schedule accounting for the changes in traffic patterns. Hence, in this paper, we present a transportation analytics solution. It captures imprecision via fuzzy logic. It takes in account lane closures (for construction sites) and traffic count when predicting bus on-time performance via regression. Evaluation on real-life data covering close to 6,000 bus stops in the Canadian city of Winnipeg demonstrates the practicality of our fuzzy logic- and regression-based transportation analytics solution in predicting whether buses arrive the bus stops early, on time, or late in various time periods of the day. This helps in building a smart city.

In the current era of big data, very large amounts of data are generating at a rapid rate from a wide variety of rich data sources. Embedded in these big data are valuable information and knowledge that can be discovered by data science, data mining and machine learning techniques. Electronic health (e-health) records are examples of the big data. With the technological advancements, more healthcare practice has gradually been supported by electronic processes and communication. This enables health informatics, in which computer science meets the healthcare sector to address healthcare and medical problems. As a concrete example, there have been more than 610 millions cumulative cases of coronavirus disease 2019 (COVID-19) worldwide over the past 2.5 years since COVID-19 has declared as a pandemic. As some of these cases require hospitalization. it is important to estimate the demand in hospitalization. Moreover, different levels of hospitalization may require different types of resources (e.g., hospital beds, medical staff). For example, patients admitted into the intensive care unit (ICU) may require assisted ventilation. Hence, in this paper, we present models to make predictions based on e-health records. Specifically, our binary model predicts whether a patient require hospitalization, whereas our multi-class model predicts what level of hospitalization (e.g., regular ward, semi-ICU, ICU) is required by the patient. Our models uses few-shot learning (and may use multi-task learning) with autoencoders (comprising encoders and decoders) and a predictor. Evaluation results on real-life e-health records show the practicality of our models in predicting hospital statuses of COVID-19 cases and the benefits of these models towards effective allocation of resources (e.g., hospital facilities, staff).

Bioinformatics and health informatics-in conjection with data science, data mining and machine learning-have been applied in numerous real-life applications including disease and healthcare analytics, such as predictive analytics of coronavirus disease 2019 (COVID-19). Many of these existing works usually require large volumes of data train the classification and prediction models. However, these data (e.g., computed tomography (CT) scan images, viral/molecular test results) that can be expensive to produce and/or not easily accessible. For instance, partially due to privacy concerns and other factors, the volume of available disease data can be limited. Hence, in this paper, we present a predictive analytics system to support health analytics. Specifically, the system make good use of autoencoder and few-shot learning to train the prediction model with only a few samples of more accessible and less expensive types of data (e.g., serology/antibody test results from blood samples), which helps to support prediction on classification of potential patients (e.g., potential COVID-19 patients). Moreover, the system also provides users (e.g., healthcare providers) with predictions on hospitalization status and clinical outcomes of COVID-19 patients. This provides healthcare administrators and staff with a good estimate on the demand for healthcare support. With this system, users could then focus and provide timely treatment to the true patients, thus preventing them for spreading the disease in the community. The system is helpful, especially for rural areas, when sophisticated equipment (e.g., CT scanners) may be unavailable. Evaluation results on a real-life datasets demonstrate the effectiveness of our digital health system in health analytics, especially in classifying patients and their medical needs.

Summary form only given, as follows. Health analytics, which make good uses of techniques like data mining and machine learning, can be applied to numerous real-life applications and services. For example, it can be applied to the identification and predictive analytics of coronavirus disease 2019 (COVID-19). However, many existing health analytic works require large volumes of data train the classification and prediction models. Note that these data (e.g., computed tomography (CT) scan images, viral/molecular test results) that can be expensive to produce and/or not easily accessible. For instance, partially due to privacy concerns and other factors, the volume of available disease data can be limited. Hence, in this paper, we present a system for health analytics. Specifically, the system make good use of autoencoder, few-shot learning and multitask learning to train the prediction model with only a few samples of more accessible and less expensive types of data (e.g., serology/antibody test results from blood samples), which helps to support prediction on classification of potential patients (e.g., potential COVID-19 patients). Moreover, the system also provides users (e.g., healthcare providers) with interpretable explanation of the prediction results, which increases their trust in the system. With this system, users could then focus and provide timely treatment to the true patients, thus preventing them for spreading the disease in the community. The system is helpful, especially for rural areas, when sophisticated equipment (e.g., CT scanners) may be unavailable. Evaluation results on a real-life datasets demonstrate the effectiveness of our system in health analytics, especially in classifying and explaining crucial information about COVID-19 patients.