Management of imported malaria cases and healthcare institutions in central China, 2012-2017: application of decision tree analysis

Risk assessment of imported malaria in China: a machine learning perspective

BACKGROUND

Following China's official designation as malaria-free country by WHO, the imported malaria has emerged as a significant determinant impacting the malaria reestablishment within China. The objective of this study is to explore the application prospects of machine learning algorithms in imported malaria risk assessment of China.

METHODS

The data of imported malaria cases in China from 2011 to 2019 was provided by China CDC; historical epidemic data of malaria endemic country was obtained from World Malaria Report, and the other data used in this study are open access data. All the data processing and model construction based on R, and map visualization used ArcGIS software.

RESULTS

A total of 27,088 malaria cases imported into China from 85 countries between 2011 and 2019. After data preprocessing and classification, clean dataset has 765 rows (85 * 9) and 11 cols. Six machine learning models was constructed based on the training set, and Random Forest model demonstrated the best performance in model evaluation. According to RF, the highest feature importance were the number of malaria deaths and Indigenous malaria cases. The RF model demonstrated high accuracy in forecasting risk for the year 2019, achieving commendable accuracy rate of 95.3%. This result aligns well with the observed outcomes, indicating the model's reliability in predicting risk levels.

CONCLUSIONS

Machine learning algorithms have reliable application prospects in risk assessment of imported malaria in China. This study provides a new methodological reference for the risk assessment and control strategies adjusting of imported malaria in China.

Factors affecting delays in seeking treatment among malaria patients during the pre-certification phase in China

BACKGROUND

Delays in malaria treatment can not only lead to severe and even life-threatening complications, but also foster transmission, putting more people at risk of infection. This study aimed to investigate the factors influencing treatment delays among malaria patients and their health-seeking behaviour.

METHODS

The medical records of 494 patients diagnosed with malaria from 6 different malaria-endemic provinces in China were analysed. A bivariate and multivariable regression model was used to investigate the association between delays in seeking treatment and various factors. A Sankey diagram was used to visualize the trajectories of malaria patients seeking medical care. Total treatment delays were categorized as patient delays and doctor delays.

RESULTS

The incidence of total delays in seeking malaria treatment was 81.6%, of which 28.4% were delayed by patients alone and 34.8% by doctors alone. The median time from the onset of symptoms to the initial healthcare consultation was 1 day. The median time from the initial healthcare consultation to the conclusive diagnosis was 2 day. After being subjected to multiple logistic regression analysis, living in central China was less likely to experience patient delays (OR = 0.43, 95% CI 0.24-0.78). The factors significantly associated with the lower likelihood of doctor delays included: age between 30 to 49 (OR = 0.43, 95% CI 0.23-0.81), being single/divorce/separated (OR = 0.48, 95% CI 0.24-0.95), first visiting a county-level health institution (OR = 0.25, 95% CI 0.14-0.45), first visiting a prefectural health institution (OR = 0.06, 95% CI 0.03-0.12) and first visiting a provincial health institution (OR = 0.05, 95%CI 0.02-0.12). Conversely, individuals with mixed infections (OR = 2.04, 95% CI 1.02-4.08) and those experiencing periodic symptoms (OR = 1.71, 95% CI 1.00-2.92) might face increased doctor delays. Furthermore, higher financial burden and complications were found to be associated with patient delays. Doctor delays, in addition to incurring these two consequences, were associated with longer hospital stays.

CONCLUSION

There was a substantial delay in access to health care for malaria patients before China was certified malaria free. Region, marital status, periodic symptoms and the level of health institutions were factors contributing to delays in treatment-seeking among malaria patients.

Care-seeking delay of imported malaria to China: implications for improving post-travel healthcare for migrant workers

BACKGROUND

Imported malaria cases continue to pose major challenges in China as well as in other countries having achieved elimination. Our study aims to identify the factors influencing the timing of care-seeking after symptom onset among migrant workers with imported malaria, in order to develop innovative interventions to improve access and provision of post-travel healthcare for returning migrants.

METHODS

We analysed the timing and types of healthcare service utilization after symptom onset among patients with imported malaria between 2012 and 2019 in Jiangsu Province, China. Moreover, decision tree models were used to explore the factors influencing the care-seeking timing after symptom onset among patients with imported malaria.

RESULTS

A total of 2255 cases of imported malaria were identified from 1 June 2012 through 31 December 2019. Patients with malaria imported into China were mainly male migrant labourers returning from sub-Saharan Africa (96.8%). A substantial number of patients with imported malaria sought healthcare >3 days after symptom onset, which clearly represented delayed healthcare-seeking behaviour. According to the decision tree analysis, initial healthcare seeking from healthcare facilities at higher administrative levels, infection with Plasmodium vivax and absence of malaria infection history were significantly associated with delayed healthcare seeking in patients with imported malaria.

CONCLUSION

The delay in seeking of medical care among migrant workers with imported malaria should be considered and addressed by specific interventions. In addition to increasing awareness about these issues among health care professionals, improved access to healthcare facilities at higher administrative levels as well as improved diagnostic capacity of healthcare facilities at lower administrative levels should be developed. Moreover, education programs targeting populations at risk of malaria importation and delayed healthcare seeking should be improved to facilitate early healthcare seeking and service use.

Factors associated with prolonged hospital stay of imported malaria cases in Chengdu, China: a retrospective study

BACKGROUND

Although China has entered the post-malaria-elimination era, imported cases remain a public health concern in China.

METHODS

We retrospectively analyzed data from cases of imported malaria from January 2017 to December 2020 in Chengdu Public Health Clinical Center. We assessed potential clinical, epidemiological, geographical, and seasonal effects on duration of hospital stay. Cox proportional hazards model was used to identify predictive factors for prolonged hospital stay. Multivariate logistic regression was used to assess the potential risk factors associated with severe cases.

RESULTS

The highest number of imported cases of malaria were from the Democratic Republic of the Congo (23%, 34/150) and most patients (74%, 26/34) were infected by Plasmodium falciparum. The Edwards test indicated no significant seasonality in imported cases of malaria (χ² = 2.51, p = 0.28). Bacterial infection (adjusted hazard ratio [aHR] for discharge = 0.58, p = 0.01) and thrombocytopenia (aHR = 0.66, p = 0.02) were risk factors for prolonged hospital stay. The C-reactive protein (OR = 1.02, p = 0.01) and procalcitonin (OR = 1.03, p = 0.01) were risk factors for severe cases.

CONCLUSIONS

Bacterial infection and thrombocytopenia are risk factors for prolonged hospital stay among imported malaria cases. The C-reactive protein and procalcitonin level were risk factors for severe cases.

Risk factors for the accuracy of the initial diagnosis of malaria cases in China: a decision-tree modelling approach

Background

Early accurate diagnosis and risk assessment for malaria are crucial for improving patients’ terminal prognosis and preventing them from progressing to a severe or critical stage. This study aims to describe the accuracy of the initial diagnosis of malaria cases with different characteristics and the factors that affect the accuracy in the context of the agenda for a world free of malaria.

Methods

A retrospective study was conducted on 494 patients admitted to hospitals with a diagnosis of malaria from January 2014 through December 2016. Descriptive statistics were calculated, and decision tree analysis was performed to predict the probability of patients who may be misdiagnosed.

Results

Of the 494 patients included in this study, the proportions of patients seeking care in county-level, prefecture-level and provincial-level hospitals were 27.5% (n = 136), 26.3% (n = 130) and 8.3% (n = 41), respectively; the proportions of patients seeking care in clinic, township health centre and Centres for Disease Control and Prevention were 25.9% (n = 128), 4.1% (n = 20), and 7.9% (n = 39), respectively. Nearly 60% of malaria patients were misdiagnosed on their first visit, and 18.8% had complications. The median time from onset to the first visit was 2 days (IQR: 0-3 days), and the median time from the first visit to diagnosis was 3 days (IQR: 0–4 days). The decision tree classification of malaria patients being misdiagnosed consisted of six categorical variables: healthcare facilities for the initial diagnosis, time interval between onset and initial diagnosis, region, residence type, insurance status, and age.

Conclusions

Insufficient diagnostic capacity of healthcare facilities with lower administrative levels for the first visit was the most important risk factor in misdiagnosing patients. To reduce diagnostic errors, clinicians, government decision-makers and communities should consider strengthening the primary care facilities, the time interval between onset and initial diagnosis, residence type, and health insurance status.

Sports Enterprise Marketing and Financial Risk Management Based on Decision Tree and Data Mining

With the development of modern economy, traditional sports industry enterprises have also been further developed in the financial business. How to ensure information security and financial risk management is the problem faced by sports companies. Risk assessment is the use of mathematical models to calculate the risk factors established in the previous step to predict possible risks. In response to the above problems, we developed a sports enterprise marketing and financial risk management model based on decision trees and data mining. First, we have established a relevant evaluation index system and data samples through in-depth understanding of the actual marketing and financial problems of sports companies. Second, we use the decision tree algorithm to mine and explore related data samples and conduct risk assessment through related indicators. By using the model to calculate the probability of occurrence of the risk, analyze the degree of damage. Finally, the algorithm of this paper is analyzed and discussed through simulation experiments.

Predicting Absenteeism and Temporary Disability Using Machine Learning: a Systematic Review and Analysis

The main objective of this paper is to present a systematic analysis and review of the state of the art regarding the prediction of absenteeism and temporary incapacity using machine learning techniques. Moreover, the main contribution of this research is to reveal the most successful prediction models available in the literature. A systematic review of research papers published from 2010 to the present, related to the prediction of temporary disability and absenteeism in available in different research databases, is presented in this paper. The review focuses primarily on scientific databases such as Google Scholar, Science Direct, IEEE Xplore, Web of Science, and ResearchGate. A total of 58 articles were obtained from which, after removing duplicates and applying the search criteria, 18 have been included in the review. In total, 44% of the articles were published in 2019, representing a significant growth in scientific work regarding these indicators. This study also evidenced the interest of several countries. In addition, 56% of the articles were found to base their study on regression methods, 33% in classification, and 11% in grouping. After this systematic review, the efficiency and usefulness of artificial neural networks in predicting absenteeism and temporary incapacity are demonstrated. The studies regarding absenteeism and temporary disability at work are mainly conducted in Brazil and India, which are responsible for 44% of the analyzed papers followed by Saudi Arabia, and Australia which represented 22%. ANNs are the most used method in both classification and regression models representing 83% and 80% of the analyzed works, respectively. Only 10% of the literature use SVM, which is the less used method in regression models. Moreover, Naïve Bayes is the less used method in classification models representing 17%.

Malaria Risk Map Using Spatial Multi-Criteria Decision Analysis along Yunnan Border During the Pre-elimination Period

In moving toward malaria elimination, finer scale malaria risk maps are required to identify hotspots for implementing surveillance–response activities, allocating resources, and preparing health facilities based on the needs and necessities at each specific area. This study aimed to demonstrate the use of multi-criteria decision analysis (MCDA) in conjunction with geographic information systems (GISs) to create a spatial model and risk maps by integrating satellite remote-sensing and malaria surveillance data from 18 counties of Yunnan Province along the China–Myanmar border. The MCDA composite and annual models and risk maps were created from the consensus among the experts who have been working and know situations in the study areas. The experts identified and provided relative factor weights for nine socioeconomic and disease ecology factors as a weighted linear combination model of the following: ([Forest coverage × 0.041] + [Cropland × 0.086] + [Water body × 0.175] + [Elevation × 0.297] + [Human population density × 0.043] + [Imported case × 0.258] + [Distance to road × 0.030] + [Distance to health facility × 0.033] + [Urbanization × 0.036]). The expert-based model had a good prediction capacity with a high area under curve. The study has demonstrated the novel integrated use of spatial MCDA which combines multiple environmental factors in estimating disease risk by using decision rules derived from existing knowledge or hypothesized understanding of the risk factors via diverse quantitative and qualitative criteria using both data-driven and qualitative indicators from the experts. The model and fine MCDA risk map developed in this study could assist in focusing the elimination efforts in the specifically identified locations with high risks.

Distribution of malaria patients seeking care in different types of health facilities during the implementation of National Malaria Elimination Programme

BACKGROUND

China launched the National Malaria Elimination Programme (NMEP) in 2010 and set the goal that all health facilities should be able to diagnose malaria. Additionally, hospitals at all levels could treat malaria by 2015. To provide a reference for the control of imported malaria, a study was conducted on the distribution of malaria patients seeking care in different types of health facilities.

METHODS

There were two data sources. One was obtained through the Infectious Diseases Information Reporting Management System (IDIRMS), which only contained the name of health facilities and the number of cases. The other was obtained through multistage stratified cluster sampling. Descriptive statistical analysis was used to investigate the distribution of malaria patients attending different types of health facilities (hospitals, township hospitals, and Centers for Disease Control and Prevention), hospital tiers (county-level, prefecture-level, and provincial-level), and hospital levels (primary, secondary, and tertiary). Chi-square test was also used to compare the proportions of patients seeking care outside their current residence region between different types of hospitals. Point maps were drawn to visualize the spatial distribution of hospitals reporting malaria cases, and flow maps were created to show the spatial flow of malaria patients by using the ArcGIS software.

RESULTS

The proportions of malaria patients who sought care in hospitals, township hospitals, and Centers for Disease Control and Prevention were 81.7%, 14.7%, and 3.6%, respectively. For those who sought care in hospitals, the percentages of patients who sought care in provincial-level, prefecture-level and county-level hospitals were 17.4%, 60.5% and 22.1%, correspondingly; the proportions of patients who sought care in tertiary hospitals, secondary hospitals, and primary hospitals were 59.8%, 39.9%, and 0.3%, respectively. Moreover, the proportions of patients seeking care in hospitals within county and prefectural administrative areas were 18.2%, 63.4%, respectively.

CONCLUSION

During the implementation of NMEP, malaria patients tended to seek care in tertiary hospitals and prefecture-level hospitals, and more than half of patients could be treated in hospitals in prefecture-level areas. In the current phase, it is necessary to establish referral system from county-level hospitals to higher-level hospitals for malaria treatment.