ABSTRACT
BACKGROUND: Machine learning techniques are starting to be used in various health care data sets to identify frail persons who may benefit from interventions. However, evidence about the performance of machine learning techniques compared to conventional regression is mixed. It is also unclear what methodological and database factors are associated with performance. OBJECTIVE: This study aimed to compare the mortality prediction accuracy of various machine learning classifiers for identifying frail older adults in different scenarios. METHODS: We used deidentified data collected from older adults (65 years of age and older) assessed with interRAI-Home Care instrument in New Zealand between January 1, 2012, and December 31, 2016. A total of 138 interRAI assessment items were used to predict 6-month and 12-month mortality, using 3 machine learning classifiers (random forest [RF], extreme gradient boosting [XGBoost], and multilayer perceptron [MLP]) and regularized logistic regression. We conducted a simulation study comparing the performance of machine learning models with logistic regression and interRAI Home Care Frailty Scale and examined the effects of sample sizes, the number of features, and train-test split ratios. RESULTS: A total of 95,042 older adults (median age 82.66 years, IQR 77.92-88.76; n=37,462, 39.42% male) receiving home care were analyzed. The average area under the curve (AUC) and sensitivities of 6-month mortality prediction showed that machine learning classifiers did not outperform regularized logistic regressions. In terms of AUC, regularized logistic regression had better performance than XGBoost, MLP, and RF when the number of features was ≤80 and the sample size ≤16,000; MLP outperformed regularized logistic regression in terms of sensitivities when the number of features was ≥40 and the sample size ≥4000. Conversely, RF and XGBoost demonstrated higher specificities than regularized logistic regression in all scenarios. CONCLUSIONS: The study revealed that machine learning models exhibited significant variation in prediction performance when evaluated using different metrics. Regularized logistic regression was an effective model for identifying frail older adults receiving home care, as indicated by the AUC, particularly when the number of features and sample sizes were not excessively large. Conversely, MLP displayed superior sensitivity, while RF exhibited superior specificity when the number of features and sample sizes were large.
ABSTRACT
COVID-19 continues to threaten the world. Relaxing local travel behaviours on preventing the spread of COVID-19, may increase the infection risk in subsequent waves of SARS-CoV-2 transmission. In this study, we analysed changes in the travel behaviour of different population groups (adult, child, student, elderly) during four pandemic waves in Hong Kong before January 2021, by 4-billion second-by-second smartcard records of subway. A significant continuous relaxation in human travel behaviour was observed during the four waves of SARS-CoV-2 transmission. Residents sharply reduced their local travel by 51.9%, 50.1%, 27.6%, and 20.5% from the first to fourth pandemic waves, respectively. The population flow in residential areas, workplaces, schools, shopping areas, amusement areas and border areas, decreased on average by 30.3%, 33.5%, 41.9%, 58.1%, 85.4% and 99.6%, respectively, during the pandemic weeks. We also found that many other cities around the world experienced a similar relaxation trend in local travel behaviour, by comparing traffic congestion data during the pandemic with data from the same period in 2019. The quantitative pandemic fatigue in local travel behaviour could help governments partially predicting personal protective behaviours, and thus to suggest more accurate interventions during subsequent waves, especially for highly infectious virus variants such as Omicron.
ABSTRACT
Introduction: Non-emergency patient transportation (NEPT) services are particularly important nowadays due to the aging population and contagious disease outbreaks (e.g., Covid-19 and SARS). In this work, we study a NEPT problem with a case study of patient transportation services in Hong Kong. The purpose of this work is to study the discomfort and inconvenience measures (e.g., waiting time and extra ride time) associated with the transportation of non-emergency patients while optimizing the operational costs and utilization of NEPT ambulances. Methods: A mixed-integer linear programming (MILP) formulation is developed to model the NEPT problem. This MILP model contributes to the existing literature by not only including the patient inconvenience measures in the objective function but also illustrating a better trade-off among different performance measures through its specially customized formulation and real-life characteristics. CPLEX is used to find the optimal solutions for the test instances. To overcome the computational complexity of the problem, a clustering-based iterative heuristic framework is designed to solve problems of practical sizes. The proposed framework distinctively exploits the problem-specific structure of the considered NEPT problem in a novel way to enhance and improve the clustering mechanism by repeatedly updating cluster centers. Results: The computational experiments on 19 realistic problem instances show the effective execution of the solution method and demonstrate the applicability of our approach. Our heuristic framework observes an optimality gap of less than 5% for all those instances where CPLEX delivered the result. The weighted objective function of the proposed model supports the analysis of different performance measures by setting different preferences for these measures. An extensive sensitivity analysis performed to observe the behavior of the MILP model shows that when operating costs are given a weightage of 0.05 in the objective function, the penalty value for user inconvenience measures is the lowest; when the weightage value for operating costs varies between 0.8 and 1.0, the penalty value for the same measures is the highest. Conclusions: This research can assist decision-makers in improving service quality by balancing operational costs and patient discomfort during transportation.
ABSTRACT
[This corrects the article DOI: 10.1002/adtp.202100055.].
ABSTRACT
BACKGROUND: The occupancy of healthcare resources by the COVID-19 outbreak had led to the unmet health needs of non-COVID-19 diseases. We aimed to explore whether the social media information could help surveil and understand the characteristics of unmet non-COVID-19 health needs during the COVID-19 outbreak in Wuhan city. METHODS: This was an observational study based on social media data. The study period was set during the 3 months of the COVID-19 outbreak. Non-COVID-19 urgent and emergent health needs in Wuhan city were derived from Sina Weibo-one of China's largest social media platforms. Lag Spearman correlation was used to investigate the epidemiological relationship between the COVID-19 outbreak and non-COVID-19 health needs. Patient's primary diseases and needed care were annotated and categorized according to the International Classification of Diseases 11th Revision. The delay time in seeking help was calculated and compared. RESULTS: After screening 114,795 Weibo posts, a total of 229 patients with non-COVID-19 health needs were included in our study. There were significant correlations between the daily number of COVID-19 cases at a 10-day lag, deaths at a 5-day lag, and non-COVID-19 Weibo. The actual number of non-COVID-19 patients with urgent and emergent health needs was estimated to be about 6,966. Patients with non-COVID-19 health needs were skewed to those aged 50 to 70 years. The non-COVID-19 diseases were diverse, with 46.3% as non-neoplastic diseases and 53.7% as neoplasms. The most needed cares were palliative cancer care (22.7%), chemotherapy (18.8%), and critical care (17.0%). The median delay in seeking help was 3 days [interquartile range (IQR), 1 to 15 days] for acute care, and 18.5 days (IQR, 6 to 30 days) for cancer care. CONCLUSIONS: Our preliminary findings in Wuhan city indicated that the social media data might provide a viable option to surveil and understand the unmet health needs during an outbreak. Those heterogeneous health needs derived from the social media data might inspire a more resilient healthcare system to address the unmet needs promptly.
ABSTRACT
Identifying effective drug treatments for COVID-19 is essential to reduce morbidity and mortality. Although a number of existing drugs have been proposed as potential COVID-19 treatments, effective data platforms and algorithms to prioritize drug candidates for evaluation and application of knowledge graph for drug repurposing have not been adequately explored. A COVID-19 knowledge graph by integrating 14 public bioinformatic databases containing information on drugs, genes, proteins, viruses, diseases, symptoms and their linkages is developed. An algorithm is developed to extract hidden linkages connecting drugs and COVID-19 from the knowledge graph, to generate and rank proposed drug candidates for repurposing as treatments for COVID-19 by integrating three scores for each drug: motif scores, knowledge graph PageRank scores, and knowledge graph embedding scores. The knowledge graph contains over 48 000 nodes and 13 37 000 edges, including 13 563 molecules in the DrugBank database. From the 5624 molecules identified by the motif-discovery algorithms, ranking results show that 112 drug molecules had the top 2% scores, of which 50 existing drugs with other indications approved by health administrations reported. The proposed drug candidates serve to generate hypotheses for future evaluation in clinical trials and observational studies.
ABSTRACT
COVID-19 threatens the world. Social distancing is a significant factor in determining the spread of this disease, and social distancing is strongly affected by the local travel behaviour of people in large cities. In this study, we analysed the changes in the local travel behaviour of various population groups in Hong Kong, between 1 January and 31 March 2020, by using second-by-second smartcard data obtained from the Mass Transit Railway Corporation (MTRC) system. Due to the pandemic, local travel volume decreased by 43%, 49% and 59% during weekdays, Saturdays and Sundays, respectively. The local travel volumes of adults, children, students and senior citizens decreased by 42%, 86%, 73% and 48%, respectively. The local travel behaviour changes for adults and seniors between non-pandemic and pandemic times were greater than those between weekdays and weekends. The opposite was true for children and students. During the pandemic, the daily commute flow decreased by 42%. Local trips to shopping areas, amusement areas and borders decreased by 42%, 81% and 99%, respectively. The effective reproduction number (R t ) of COVID-19 had the strongest association with daily population use of the MTR 7-8 days earlier.
ABSTRACT
BACKGROUND: Coronavirus disease 2019 (COVID-19) continues to threaten human life worldwide. We explored how human behaviors have been influenced by the COVID-19 pandemic in Hong Kong, and how the transmission of other respiratory diseases (eg, influenza) has been influenced by human behavior. METHODS: We focused on the spread of COVID-19 and influenza infections based on the reported COVID-19 cases and influenza surveillance data and investigated the changes in human behavior due to COVID-19 based on mass transit railway data and the data from a telephone survey. We did the simulation based on a susceptible-exposed-infected-recovered (SEIR) model to assess the risk reduction of influenza transmission caused by the changes in human behavior. RESULTS: During the COVID-19 pandemic, the number of passengers fell by 52.0% compared with the same period in 2019. Residents spent 32.2% more time at home. Each person, on average, came into close contact with 17.6 and 7.1 people per day during the normal and pandemic periods, respectively. Students, workers, and older people reduced their daily number of close contacts by 83.0%, 48.1%, and 40.3%, respectively. The close contact rates in residences, workplaces, places of study, restaurants, shopping centers, markets, and public transport decreased by 8.3%, 30.8%, 66.0%, 38.5%, 48.6%, 41.0%, and 36.1%, respectively. Based on the simulation, these changes in human behavior reduced the effective reproduction number of influenza by 63.1%. CONCLUSIONS: Human behaviors were significantly influenced by the COVID-19 pandemic in Hong Kong. Close contact control contributed more than 47% to the reduction in infection risk of COVID-19.
