Using association rule mining to identify risk factors for early childhood caries

Machine learning algorithms' application to predict childhood vaccination among children aged 12-23 months in Ethiopia: Evidence 2016 Ethiopian Demographic and Health Survey dataset

INTRODUCTION

Childhood vaccination is a cost-effective public health intervention to reduce child mortality and morbidity. But, vaccination coverage remains low, and previous similar studies have not focused on machine learning algorithms to predict childhood vaccination. Therefore, knowledge extraction, association rule formulation, and discovering insights from hidden patterns in vaccination data are limited. Therefore, this study aimed to predict childhood vaccination among children aged 12-23 months using the best machine learning algorithm.

METHODS

A cross-sectional study design with a two-stage sampling technique was used. A total of 1617 samples of living children aged 12-23 months were used from the 2016 Ethiopian Demographic and Health Survey dataset. The data was pre-processed, and 70% and 30% of the observations were used for training, and evaluating the model, respectively. Eight machine learning algorithms were included for consideration of model building and comparison. All the included algorithms were evaluated using confusion matrix elements. The synthetic minority oversampling technique was used for imbalanced data management. Informational gain value was used to select important attributes to predict childhood vaccination. The If/ then logical association was used to generate rules based on relationships among attributes, and Weka version 3.8.6 software was used to perform all the prediction analyses.

RESULTS

PART was the first best machine learning algorithm to predict childhood vaccination with 95.53% accuracy. J48, multilayer perceptron, and random forest models were the consecutively best machine learning algorithms to predict childhood vaccination with 89.24%, 87.20%, and 82.37% accuracy, respectively. ANC visits, institutional delivery, health facility visits, higher education, and being rich were the top five attributes to predict childhood vaccination. A total of seven rules were generated that could jointly determine the magnitude of childhood vaccination. Of these, if wealth status = 3 (Rich), adequate ANC visits = 1 (yes), and residency = 2 (Urban), then the probability of childhood vaccination would be 86.73%.

CONCLUSIONS

The PART, J48, multilayer perceptron, and random forest algorithms were important algorithms for predicting childhood vaccination. The findings would provide insight into childhood vaccination and serve as a framework for further studies. Strengthening mothers' ANC visits, institutional delivery, improving maternal education, and creating income opportunities for mothers could be important interventions to enhance childhood vaccination.

Prediction of contraceptive discontinuation among reproductive-age women in Ethiopia using Ethiopian Demographic and Health Survey 2016 Dataset: A Machine Learning Approach

BACKGROUND

Globally, 38% of contraceptive users discontinue the use of a method within the first twelve months. In Ethiopia, about 35% of contraceptive users also discontinue within twelve months. Discontinuation reduces contraceptive coverage, family planning program effectiveness and contributes to undesired fertility. Hence understanding potential predictors of contraceptive discontinuation is crucial to reducing its undesired outcomes. Predicting the risk of discontinuing contraceptives is also used as an early-warning system to notify family planning programs. Thus, this study could enable to predict and determine the predictors for contraceptive discontinuation in Ethiopia.

METHODOLOGY

Secondary data analysis was done on the 2016 Ethiopian Demographic and Health Survey. Eight machine learning algorithms were employed on a total sample of 5885 women and evaluated using performance metrics to predict and identify important predictors of discontinuation through python software. Feature importance method was used to select top predictors of contraceptive discontinuation. Finally, association rule mining was applied to discover the relationship between contraceptive discontinuation and its top predictors by using R statistical software.

RESULT

Random forest was the best predictive model with 68% accuracy which identified the top predictors of contraceptive discontinuation. Association rule mining identified women's age, women's education level, family size, husband's desire for children, husband's education level, and women's fertility preference as predictors most frequently associated with contraceptive discontinuation.

CONCLUSION

Results have shown that machine learning algorithms can accurately predict the discontinuation status of contraceptives, making them potentially valuable as decision-support tools for the relevant stakeholders. Through association rule mining analysis of a large dataset, our findings also revealed previously unknown patterns and relationships between contraceptive discontinuation and numerous predictors.

Understanding Differences in Behaviour Patterns of Healthcare Service Elements Among Regions Applying Data Mining

Maternal and child healthcare (MCH) has always been regarded as one of the important issues globally. The aim of this article is to find out all frequently occurring healthcare service elements along with their availability conditions and their interactions with other health system (HS) elements, when coverage of priority MCH intervention was either poor or moderate or good in any region. Association rule mining technique has been used to understand the probability of occurrences of different healthcare service elements among regions. Along with the proposed analytical framework, an interactive decision support system (DSS) has also been developed on a web platform, which would help healthcare policymakers to integrate the analytical framework easily in their processes of decision-making. The system has been developed by using Shiny package on R software. Data for all variables are collected for 584 Indian districts from the third phase of district-level household and facility survey. From results, it is observed that community healthcare services, sub-centre (SC)-level healthcare services and PHC-level healthcare services of a region are very much interlinked with each other, and their relationships define the healthcare condition of that region.

Age, sex, residence, and region-specific differences in prevalence and patterns of multimorbidity among older Chinese: evidence from Chinese Longitudinal Healthy Longevity Survey

BACKGROUND

Multimorbidity among older adults, which is associated with added functional decline and higher health care utilization and mortality, has become increasingly common with the dramatic acceleration of ageing in China. The purpose of this study was to reveal age, sex, residence, and region- specific prevalence and patterns of multimorbidity among older adults in China.

METHODS

This study is based on the 2018 Chinese Longitudinal Health Longevity Survey (CLHLS), the most recent edition of this national survey, and involved analysis of 15,275 participants aged 65 years and older. Multimorbidity was defined as an individual who has two or more chronic diseases or conditions and was divided into two types for analysis: ≥2 (MM2+) and ≥ 3 (MM3+). Fourteen chronic diseases or conditions surveyed were used to assess patterns of multimorbidity through association rule mining.

RESULTS

Among the 15,275 participants, the largest proportion (39.9%) was 90 years old and over, while the distribution of sex and residence is roughly the same. Overall, the prevalence of multimorbidity was 44.1% for MM2+ and 22.9% for MM3+. The most frequently occurring patterns were two or three combinations between hypertension, cardiovascular diseases and affective disorders. Cardiovascular diseases combined with diabetes or dyslipidemia showed the most predominant association in different age groups. Moreover, the prevalence of the hypertension +diabetes pattern decreased with age. The strongest associations were found for the clustering of hypertension + cardiovascular diseases + respiratory diseases in males, however, among females it was the cardiovascular diseases + diabetes cluster. Cardiovascular diseases + rheumatoid arthritis + visual impairment was observed in urban areas and hypertension + cardiovascular diseases + affective disorders in rural areas. The most distinctive association rule in Northern China was {cardiovascular diseases, hypertension, visual impairment} = > {diabetes}. Respiratory disease was more prevalent in combination with other systemic disorders in Western China, and affective disorders in Southern China.

CONCLUSIONS

The prevalence of multimorbidity among older Chinese was substantial, and patterns of multimorbidity varied by age, sex, residence, and region. Future efforts are needed to identify possible prevention strategies and guidelines that consider differences in demographic characteristics of multimorbid patients to promote health in older adults.

Salivary cystatin S levels in children with early childhood caries in comparison with caries-free children; statistical analysis and machine learning

Background

Early childhood caries is the most common infectious disease in childhood, with a high prevalence in developing countries. The assessment of the variables that influence early childhood caries as well as its pathophysiology leads to improved control of this disease. Cystatin S, as one of the salivary proteins, has an essential role in pellicle formation, tooth re-mineralization, and protection. The present study aims to assess salivary cystatin S levels and demographic data in early childhood caries in comparison with caries-free ones using statistical analysis and machine learning methods.

Methods

A cross-sectional, case–control study was undertaken on 20 cases of early childhood caries and 20 caries-free children as a control. Unstimulated whole saliva samples were collected by suction. Cystatin S concentrations in samples were determined using human cystatin S ELISA kit. The checklist was collected from participants about demographic characteristics, oral health status, and dietary habits by interviewing parents. Regression and receiver operating characteristic (ROC) curve analysis were done to evaluate the potential role of cystatin S salivary level and demographic using statistical analysis and machine learning.

Results

The mean value of salivary cystatin S concentration in the early childhood caries group was 191.55 ± 81.90 (ng/ml) and in the caries-free group was 370.06 ± 128.87 (ng/ml). T-test analysis showed a statistically significant difference between early childhood caries and caries-free groups in salivary cystatin S levels (p = 0.032). Investigation of the area under the curve (AUC) and accuracy of the ROC curve revealed that the logistic regression model based on salivary cystatin S levels and birth weight had the most and acceptable potential for discriminating of early childhood caries from caries-free controls. Furthermore, using salivary cystatin S levels enhanced the capability of machine learning methods to differentiate early childhood caries from caries-free controls.

Conclusion

Salivary cystatin S levels in caries-free children were higher than the children with early childhood caries. Results of the present study suggest that considering clinical examination, demographic and socioeconomic factors, along with the salivary cystatin S levels, could be usefull for early diagnosis ofearly childhood caries in high-risk children; furthermore, cystatin S is a protective factor against dental caries.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12903-021-02016-x.

Discovering symptom patterns of COVID-19 patients using association rule mining

BACKGROUND

The COVID-19 pandemic is a significant public health crisis that is hitting hard on people's health, well-being, and freedom of movement, and affecting the global economy. Scientists worldwide are competing to develop therapeutics and vaccines; currently, three drugs and two vaccine candidates have been given emergency authorization use. However, there are still questions of efficacy with regard to specific subgroups of patients and the vaccine's scalability to the general public. Under such circumstances, understanding COVID-19 symptoms is vital in initial triage; it is crucial to distinguish the severity of cases for effective management and treatment. This study aimed to discover symptom patterns and overall symptom rules, including rules disaggregated by age, sex, chronic condition, and mortality status, among COVID-19 patients.

METHODS

This study was a retrospective analysis of COVID-19 patient data made available online by the Wolfram Data Repository through May 27, 2020. We applied a widely used rule-based machine learning technique called association rule mining to identify frequent symptoms and define patterns in the rules discovered.

RESULT

In total, 1,560 patients with COVID-19 were included in the study, with a median age of 52 years. The most frequently occurring symptom was fever (67%), followed by cough (37%), malaise/body soreness (11%), pneumonia (11%), and sore throat (8%). Myocardial infarction, heart failure, and renal disease were present in less than 1% of patients. The top ten significant symptom rules (out of 71 generated) showed cough, septic shock, and respiratory distress syndrome as frequent consequents. If a patient had a breathing problem and sputum production, then, there was higher confidence of that patient having a cough; if cardiac disease, renal disease, or pneumonia was present, then there was a higher confidence of septic shock or respiratory distress syndrome. Symptom rules differed between younger and older patients and between male and female patients. Patients who had chronic conditions or died of COVID-19 had more severe symptom rules than those patients who did not have chronic conditions or survived of COVID-19. Concerning chronic condition rules among 147 patients, if a patient had diabetes, prerenal azotemia, and coronary bypass surgery, there was a certainty of hypertension.

CONCLUSION

The most frequently reported symptoms in patients with COVID-19 were fever, cough, pneumonia, and sore throat; while 1% had severe symptoms, such as septic shock, respiratory distress syndrome, and respiratory failure. Symptom rules differed by age and sex. Patients with chronic disease and patients who died of COVID-19 had severe symptom rules more specifically, cardiovascular-related symptoms accompanied by pneumonia, fever, and cough as consequents.

Rocha C, V. Maurer-Morelli C, Perez Orrico SR, Cirelli JA, Von Zuben FJ, Mantuaneli Scarel-Caminaga R. Using association rule mining to jointly detect clinical features and differentially expressed genes related to chronic inflammatory diseases

OBJECTIVE

It is increasingly common to find patients affected by a combination of type 2 diabetes mellitus (T2DM), dyslipidemia (DLP) and periodontitis (PD), which are chronic inflammatory diseases. More studies able to capture unknown relationships among these diseases will contribute to raise biological and clinical evidence. The aim of this study was to apply association rule mining (ARM) to discover whether there are consistent patterns of clinical features (CFs) and differentially expressed genes (DEGs) relevant to these diseases. We intend to reinforce the evidence of the T2DM-DLP-PD-interplay and demonstrate the ARM ability to provide new insights into multivariate pattern discovery.

METHODS

We utilized 29 clinical glycemic, lipid and periodontal parameters from 143 patients divided into five groups based upon diabetic, dyslipidemic and periodontal conditions (including a healthy-control group). At least 5 patients from each group were selected to assess the transcriptome by microarray. ARM was utilized to assess relevant association rules considering: (i) only CFs; and (ii) CFs+DEGs, such that the identified DEGs, specific to each group of patients, were submitted to gene expression validation by quantitative polymerase chain reaction (qPCR).

RESULTS

We obtained 78 CF-rules and 161 CF+DEG-rules. Based on their clinical significance, Periodontists and Geneticist experts selected 11 CF-rules, and 5 CF+DEG-rules. From the five DEGs prospected by the rules, four of them were validated by qPCR as significantly different from the control group; and two of them validated the previous microarray findings.

CONCLUSIONS

ARM was a powerful data analysis technique to identify multivariate patterns involving clinical and molecular profiles of patients affected by specific pathological panels. ARM proved to be an effective mining approach to analyze gene expression with the advantage of including patient's CFs. A combination of CFs and DEGs might be employed in modeling the patient's chance to develop complex diseases, such as those studied here.

Prevalence of dental caries in preschool children born preterm and/or with low birth weight: A systematic review with meta-analysis of prevalence data

The aim of the present systematic review and meta-analysis was to evaluate the prevalence of dental caries among preschool children who had been born preterm and/or with low birth weight (LBW) compared with those who had been born full term and/or with normal birth weight (NBW). Eight electronic databases were searched from interception up to November 2018 with no restrictions imposed regarding the date of publication or language. Two independent reviewers screened studies, extracted data, and assessed the risk of bias. A random-effects meta-analysis was run to pool the crude prevalence of dental caries according to gestational age and birth weight. We performed a narrative synthesis and assessed the certainty of evidence using the Grading of Recommendations, Assessment, Development, and Evaluation (GRADE). Fifty-nine observational studies were included (55 in the meta-analysis). The prevalence of dental caries was 39% among preterm children, 30% among full-term children, 40% among LBW children, and 33% among NBW children (I² :97%-99%). The majority of studies reported that dental caries was not associated with gestational age or birth weight, with very low certainty of evidence. Preschool children born preterm or with LBW have similar dental caries experience as those born full term or with NBW, with very low certainty of evidence (PROSPERO #CDR42018118086).

Pediatric population health analysis of southern and central Illinois region: A cross sectional retrospective study using association rule mining and multiple logistic regression

BACKGROUND

Southern Illinois University School of Medicine (SIUSOM) collects large amounts of data every day. SIUSOM and other similar healthcare systems are always looking for better ways to use the data to understand and address population level problems. The purpose of this study is to analyze the administrative dataset for pediatric patients served by Southern Illinois University School of Medicine (SIUSOM) to uncover patterns that correlate specific demographic information to diagnoses of pediatric diseases. The study uses a cross-sectional database of medical billing information for all pediatric patients served by SIUSOM between June 2013 and December 2016. The dataset consists of about 980.9K clinical visits for 65.4K unique patients and includes patient demographic identifiers such as their sex, date of birth, race, anonymous zipcode and primary and secondary insurance plan as well as the related pediatric diagnosis codes. The goal is to find unknown correlations in this database.

METHOD

We proposed a two step methodology to derive unknown correlations in SIUSOM administrative database. First, Class association rule mining was used as a well-established data mining method to generate hypothesis and derive associations of the form D → M, where D is diagnosis code of a pediatric disease and M is a patient demographic identifier (age,sex, anonymous zipcode, insurance plan, or race). The resulting associations were pruned and filtered using measures such as lift, odds ratio, relative risk, and confidence. The final associations were selected by a pediatric doctor based on their clinical significance. Second,each association rule in the final set was further validated and adjusted odds ratios were obtained using multiple logistic regression.

RESULTS

Several associations were found correlating specific patients' residential zip codes with the diagnosis codes for viral hepatitis carrier, exposure to communicable diseases, screening for mental and developmental disorder in childhood, history allergy to medications, disturbance of emotions specific to childhood, and acute sinusitis. In addition, the results show that African American patients are more likely to be screened for mental and developmental disorders compared to White patients for SIUSOM pediatric population (Odds Ratio (OR):3.56, 95% Confidence Interval (CI):[3.29,3.85]).

CONCLUSION

Class association rule mining is an effective method for detecting signals in a large patient administrative database and generating hypotheses which correlate patients' demographics with diagnosis of pediatric diseases. A post processing of the hypotheses generated by this method is necessary to prune spurious associations and select a set of clinically relevant hypotheses.

A Descriptive Study of Musculoskeletal Injuries in Long-Haul Truck Drivers: A NIOSH National Survey

Long-haul truck drivers are significantly affected by musculoskeletal injuries with incidence rates 3.5 times higher than the national average. Yet, little is known about injuries that affect long-haul trucks drivers. In 2010, interviewers collected data from 1,265 long-haul truck drivers at 32 truck stops across the United States. These surveys were analyzed to describe all self-reported musculoskeletal injuries. Injuries to the arm (26.3%) and back (21.1%) were the two areas most reported in the survey. Musculoskeletal injuries were most often caused by falls (38.9%) and contact with an object or equipment (33.7%) resulting most commonly in sprains/strains (60%). This large scale survey highlights the significance of musculoskeletal injuries in long-haul truck drivers and suggests the need to develop interventions to prevent injuries and improve recovery once injuries occur.

The Association between Cariogenic Factors and the Occurrence of Early Childhood Caries in Children from Salem District of India

INTRODUCTION

Various aetiological factors for Early Childhood Caries (ECC) have been suggested in literature, but the role of each factor has been disputed in various studies.

AIM

To evaluate the association between ECC and its related factors in children between three to six years of age, from rural, semi-urban and urban schools in the district of Salem (India).

MATERIALS AND METHODS

The study consisted of children between three to six years of age, selected randomly from schools in semi-urban, urban and rural schools at Salem. Questionnaire (comprising of the factors associated with ECC) and parental consent forms were sent to each of the parents of the school children. Filled questionnaires and parental consent forms were obtained from a total of 2771 children, out of which 1771 were boys and 1000 were girls. Clinical examination for ECC was carried out according to the WHO criteria, by a single examiner and an assistant to eliminate inter-examiner variability. Statistical analysis was carried out using the student's independent t-test and ANOVA (one way analysis of variance).

RESULTS

Out of a total of 2771 children examined, only 443 (315 boys and 128 girls) children were found to have ECC (16 %). Significant correlations were found between the occurrence of ECC and various factors like age of parents, number of siblings, on-demand breast feeding and bottle feeding habits and sweetened pacifier use. However, factors such as age and gender of the child, type of birth and duration of pregnancy, had no significant correlation with the occurrence of ECC.

CONCLUSION

The need for educating parents on the ill effects of improper breast feeding and bottle feeding habits is important.

Comorbidity study of borderline personality disorder: applying association rule mining to the Taiwan national health insurance research database

Background

Borderline personality disorder (BPD) is a complex clinical state with highly polymorphic symptoms and signs. Studies have demonstrated that people with a BPD diagnosis are likely to have numerous co-occurring psychiatric disorders and physical comorbidities. The aim of our study was to obtain further insight about the associations among comorbidities of BPD and to demonstrate the practicality of using association rule mining (ARM) technique in clinical databases.

Methods

A retrospective case–control study was conducted on information of 1460 patients (292 BPD patients and 1168 control patients) selected from the Taiwan National Health Insurance Research Database. Information on physical and psychiatric comorbidities, which were diagnosed within 3 years before and after enrollment, was collected. A logistic regression model was used to calculate the odds ratios of comorbidities between patients with and without BPD. ARM technique was used to study the associations of BPD and two or more psychiatric comorbidities.

Results

We classified physical comorbidities into 13 categories according to the International Classification of Diseases, Ninth Revision, Clinical Modification system, and the results indicated that the 12 categories were more common in the BPD patients than in the control patients (except congenital anomalies). However, psychiatric comorbidities, including depressive disorder, bipolar disorder, anxiety disorder, sleep disorder, substance use disorder, and mental retardation were more common in the BPD patients than in the control patients. Furthermore, the associations of BPD and two or more comorbidities were evaluated.

Conclusion

Most physical and psychiatric disorders were more common in the BPD patients than in the control patients. Because the failure to remit from BPD is associated with suffering from chronic physical conditions and because psychiatric comorbidities may lead to delays in diagnosis of BPD, clinicians caring for people with BPD should be aware of possible comorbidities.

Polypharmacy in older adults: Association Rule and Frequent-Set Analysis to evaluate concomitant medication use

The aim of this study was to apply Association Rule and Frequent-Set analysis, and novel means of data visualisation to ascertain patterns of medication use and medication combinations contributing to medication group clusters according to geriatric syndrome status in older adults. Participants were community-dwelling men (aged ≥70 years, n=1686), Sydney, Australia. Medication exposure was categorised at medication class level and data were analysed according to geriatric syndrome status (presence of at least one syndrome including frailty, falls, cognitive impairment and urinary incontinence). Association Rule and Frequent-Set analysis were performed to identify "interesting" patterns of medication combinations that occur together. This analysis involves advanced computer algorithms that investigated all possible combinations of medications in the dataset in order to identify those which are observed more or much less frequently than expected. Frequent-Set Analysis demonstrated one unexpected medication combination, antiulcer and antidiabetic medications (3.5% of participants) in the overall population (n=1687). Frequency of medication combinations was similar in participants with (n=666) and without (n=1020) geriatric syndromes. Among participants with geriatric syndromes, the most frequent combinations included antigout with lipid-lowering agents (5.7%) followed by angiotensin II and diuretics combination (22%). This novel methodology can be used to detect common medication combinations overall by data visualisation, and against specific adverse drug reactions such as geriatric syndromes. This methodology may be a valuable pharmacovigilance approach to monitor large databases for the safety of medications.