Mental disorders and medical comorbidities: Association rule mining approach

Developing a Chatbot to Support Individuals With Neurodevelopmental Disorders: Tutorial

Families of individuals with neurodevelopmental disabilities or differences (NDDs) often struggle to find reliable health information on the web. NDDs encompass various conditions affecting up to 14% of children in high-income countries, and most individuals present with complex phenotypes and related conditions. It is challenging for their families to develop literacy solely by searching information on the internet. While in-person coaching can enhance care, it is only available to a minority of those with NDDs. Chatbots, or computer programs that simulate conversation, have emerged in the commercial sector as useful tools for answering questions, but their use in health care remains limited. To address this challenge, the researchers developed a chatbot named CAMI (Coaching Assistant for Medical/Health Information) that can provide information about trusted resources covering core knowledge and services relevant to families of individuals with NDDs. The chatbot was developed, in collaboration with individuals with lived experience, to provide information about trusted resources covering core knowledge and services that may be of interest. The developers used the Django framework (Django Software Foundation) for the development and used a knowledge graph to depict the key entities in NDDs and their relationships to allow the chatbot to suggest web resources that may be related to the user queries. To identify NDD domain-specific entities from user input, a combination of standard sources (the Unified Medical Language System) and other entities were used which were identified by health professionals as well as collaborators. Although most entities were identified in the text, some were not captured in the system and therefore went undetected. Nonetheless, the chatbot was able to provide resources addressing most user queries related to NDDs. The researchers found that enriching the vocabulary with synonyms and lay language terms for specific subdomains enhanced entity detection. By using a data set of numerous individuals with NDDs, the researchers developed a knowledge graph that established meaningful connections between entities, allowing the chatbot to present related symptoms, diagnoses, and resources. To the researchers' knowledge, CAMI is the first chatbot to provide resources related to NDDs. Our work highlighted the importance of engaging end users to supplement standard generic ontologies to named entities for language recognition. It also demonstrates that complex medical and health-related information can be integrated using knowledge graphs and leveraging existing large datasets. This has multiple implications: generalizability to other health domains as well as reducing the need for experts and optimizing their input while keeping health care professionals in the loop. The researchers' work also shows how health and computer science domains need to collaborate to achieve the granularity needed to make chatbots truly useful and impactful.

CauRuler: Causal irredundant association rule miner for complex patient trajectory modelling

BACKGROUND AND OBJECTIVES

Discovering causal associations between variables is one of the main goals of clinical trials, with the ultimate aim of identifying the causes of specific health status. Prior knowledge of causal paths could help ensure patients do not develop the resultant conditions. In recent years, thanks to the enormous amount of health data stored with the support of digital tools, attempts have been made to employ Machine Learning to infer causality. Those methodologies suffer from some deficiencies in controlling cofounders when analysing causality, as well as providing causal rules general enough to be useful in healthcare practice. Conversely, this work presents and evaluates CauRuler, a new approach to deal with causality from association rules. The proposed approach uses a pruning strategy to reduce the association rule set, which does not compromise the causality learning capability of the algorithm. This behaviour makes the algorithm suitable for exploiting large health databases with thousands of patients and medical instances. CauRuler can control a larger number of confounders than other proposals, bringing robustness to causal analysis and avoiding the identification of spurious associations. Additionally, the method generalizes causality using anti-monotone properties to obtain complex and general causal paths. The method can target correct causal associations in complex medical databases with retrospective data.

METHOD

CauRuler extends association rule mining with an irredundancy property so that the set of rules learnt is reduced in size and generalized. General association rules, conformed by fewer items, enable controlling more confounding variables to verify, with more statistical evidence on available data, if they represent causal paths in patient disease trajectories.

RESULTS

CauRuler has been tested on a complex real medical database (3,5 M visits to the primary care services between 2019 and 2020, and controlling over 15.000 different variables including diagnoses and demographic and other clinical patient data). The reduction of the rule set achieved by the pruning strategy goes from 7.732 to 2.240 rules, from which 46 have been found to have causality relationships in the patient trajectories, and generalized to 14 rules tested as true causal relationships thanks to the confounding analysis. These rules have been validated by clinicians with the support of a graphical map. The obtained causal paths control in average of 906 confounder variables, retrieving robust results.

CONCLUSIONS

Causal relationships enable predicting causal paths between health conditions according to patient trajectories. Knowing these causal paths is crucial for understanding and preventing the appearance or worsening of diseases in patients. CauRuler, with high demanding thresholds, has proven its efficiency and effectiveness in targeting previously known causal associations between diagnoses, reaching consensus in the medical community. Softening these thresholds should help target interesting general causal paths.

Recommender systems for mental health apps: advantages and ethical challenges

Recommender systems assist users in receiving preferred or relevant services and information. Using such technology could be instrumental in addressing the lack of relevance digital mental health apps have to the user, a leading cause of low engagement. However, the use of recommender systems for digital mental health apps, particularly those driven by personal data and artificial intelligence, presents a range of ethical considerations. This paper focuses on considerations particular to the juncture of recommender systems and digital mental health technologies. While separate bodies of work have focused on these two areas, to our knowledge, the intersection presented in this paper has not yet been examined. This paper identifies and discusses a set of advantages and ethical concerns related to incorporating recommender systems into the digital mental health (DMH) ecosystem. Advantages of incorporating recommender systems into DMH apps are identified as (1) a reduction in choice overload, (2) improvement to the digital therapeutic alliance, and (3) increased access to personal data & self-management. Ethical challenges identified are (1) lack of explainability, (2) complexities pertaining to the privacy/personalization trade-off and recommendation quality, and (3) the control of app usage history data. These novel considerations will provide a greater understanding of how DMH apps can effectively and ethically implement recommender systems.

Comorbidity combinations in schizophrenia inpatients and their associations with service utilization: A medical record-based analysis using association rule mining

BACKGROUND

Comorbidities are common among patients with schizophrenia yet the prevalence of comorbidity combinations and their associations with inpatient service utilization and readmission have been scarcely explored.

METHODS

Data were extracted from discharge summaries of patients whose primary diagnosis was schizophrenia spectrum disorders (ICD-10: F20-F29). We identified 30 most frequent comorbidities in patients' secondary diagnoses and then used the association rule mining (ARM) method to derive comorbidity combinations associated with length of stay (LOS), daily expense and one-year readmission.

RESULTS

The study included data from 8252 patients. The top five most common comorbidities were extrapyramidal syndrome (EPS, 44.58%), constipation (31.63%), common cold (21.80%), hyperlipidemia (20.99%) and tachycardia (19.13%). Most comorbidity combinations identified by ARM were significantly associated with longer LOS (≥70 days), few were associated with higher daily expenses, and fewer with readmission. The 3-way combination of common cold, hyperlipidemia and fatty liver had the strongest association with longer LOS (adjusted OR (aOR): 3.38, 95% CI: 2.12-5.38). The combination of EPS and mild cognitive disorder was associated with higher daily expense (≥700 RMB) (aOR: 1.67, 95% CI: 1.20-2.31). The combination of constipation, tachycardia and fatty liver were associated with higher 1-year readmission (aOR: 2.05, 95% CI: 1.03-4.09).

CONCLUSION

EPS, constipation, and tachycardia were among the most commonly reported comorbidities in schizophrenia patients in Beijing, China. Specific groups of comorbidities may contribute to higher inpatient psychiatric service utilization and readmission. The mechanism behind the associations and potential interventions to optimize service use warrant further investigation.

Hypertension and Obesity: Risk Factors for Thyroid Disease

Thyroid disease instances have rapidly increased in the past few decades; however, the cause of the disease remains unclear. Understanding the pathogenesis of thyroid disease will potentially reduce morbidity and mortality rates. Currently, the identified risk factors from existing studies are controversial as they were determined through qualitative analysis and were not further confirmed by quantitative implementations. Association rule mining, as a subset of data mining techniques, is dedicated to revealing underlying correlations among multiple attributes from a complex heterogeneous dataset, making it suitable for thyroid disease pathogenesis identification. This study adopts two association rule mining algorithms (i.e., Apriori and FP-Growth Tree) to identify risk factors correlated with thyroid disease. Extensive experiments were conducted to reach impartial findings with respect to knowledge discovery through two independent digital health datasets. The findings confirmed that gender, hypertension, and obesity are positively related to thyroid disease development. The history of I₁₃₁ treatment and Triiodothyronine level can be potential factors for evaluating subsequent thyroid disease.

Discovery of Association Rules Patterns and Prevalence of Comorbidities in Adult Patients Hospitalized with Mental and Behavioral Disorders

The objectives of this study were to identify the prevalence of comorbidities of mental and behavioral disorders and to identify the association rules related to comorbidities as a way to improve patient management efficiently. We extracted comorbidities of 20,690 patients (≥19 years old) whose principal diagnosis was a mental disorder from the Korean National Hospital Discharge In-depth Injury Survey (KNHDS) between 2006 and 2016. Association rules analysis between comorbid diseases using the Apriori algorithm was used. The prevalence of comorbidities in all patients was 61.98%. The frequent comorbidities of mental and behavioral disorders were analyzed in the order of hypertensive diseases (11.06%), mood disorders (8.34%), diabetes mellitus (7.98%), and diseases of esophagus, stomach, and duodenum (7.04%). Nine major association pathways were analyzed. Significant pathways were analyzed as diabetes mellitus and hypertensive diseases (IS scale = 0.386), hypertensive diseases, and cerebrovascular diseases (IS scale = 0.240). The association pathway of diabetes mellitus and hypertensive diseases was common in subgroups of mental and behavioral disorders, excluding mood disorders and disorders of adult personality and behavior. By monitoring related diseases based on major patterns, it can predict comorbid diseases in advance, improve the efficiency of managing patients with mental and behavioral disorders, and furthermore, it can be used to establish related health policies.

Comorbidity Patterns of Older Lung Cancer Patients in Northeast China: An Association Rules Analysis Based on Electronic Medical Records

Purposes: This study aims to identify the comorbidity patterns of older men with lung cancer in China. Methods: We analyzed the electronic medical records (EMRs) of lung cancer patients over age 65 in the Jilin Province of China. The data studied were obtained from 20 hospitals of Jilin Province in 2018. In total, 1510 patients were identified. We conducted a rank–frequency analysis and social network analysis to identify the predominant comorbidities and comorbidity networks. We applied the association rules to mine the comorbidity combination with the values of confidence and lift. A heatmap was utilized to visualize the rules. Results: Our analyses discovered that (1) there were 31 additional medical conditions in older patients with lung cancer. The most frequent comorbidities were pneumonia, cerebral infarction, and hypertension. (2) The network-based analysis revealed seven subnetworks. (3) The association rules analysis provided 41 interesting rules. The results revealed that hypertension, ischemic cardiomyopathy, and pneumonia are the most frequent comorbid combinations. Heart failure may not have a strong implicating role in these comorbidity patterns. Cerebral infarction was rarely combined with other diseases. In addition, glycoprotein metabolism disorder comorbid with hyponatremia or hypokalemia increased the risk of anemia by more than eight times in older lung cancer patients. Conclusions: This study provides evidence on the comorbidity patterns of older men with lung cancer in China. Understanding the comorbidity patterns of older patients with lung cancer can assist clinicians in their diagnoses and contribute to developing healthcare policies, as well as allocating resources.

Comorbidity in Older Patients Hospitalized with Cancer in Northeast China based on Hospital Discharge Data

Patients with cancer often carry the dual burden of the cancer itself and other co-existing medical conditions. The problems associated with comorbidities among elderly cancer patients are more prominent compared with younger patients. This study aimed to identify common cancer-related comorbidities in elderly patients through routinely collected hospital discharge data and to use association rules to analyze the prevalence and patterns of these comorbidities in elderly cancer patients at different cancer sites. We collected the discharge data of 80,574 patients who were diagnosed with cancers of the esophagus, stomach, colorectum, liver, lung, female breast, cervix, and thyroid between 2016 and 2018. The same number of non-cancer patients were randomly selected as the control group and matched with the case group by age and gender. The results showed that cardiovascular diseases, metabolic diseases, digestive diseases, and anemia were the most common comorbidities in elderly patients with cancer. The comorbidity patterns differed based on the cancer site. Elderly patients with liver cancer had the highest risk of comorbidities, followed by lung cancer, gastrointestinal cancer, thyroid cancer, and reproductive cancer. For example, elderly patients with liver cancer had the higher risk of the comorbid infectious and digestive diseases, whereas patients with lung cancer had the higher risk of the comorbid respiratory system diseases. The findings can assist clinicians in diagnosing comorbidities and contribute to the allocation of medical resources.

Extracting Production Rules for Cerebrovascular Examination Dataset through Mining of Non-Anomalous Association Rules

Today, patients generate a massive amount of health records through electronic health records (EHRs). Extracting usable knowledge of patients’ pathological conditions or diagnoses is essential for the reasoning process in rule-based systems to support the process of clinical decision making. Association rule mining is capable of discovering hidden interesting knowledge and relations among attributes in datasets, including medical datasets, yet is more likely to produce many anomalous rules (i.e., subsumption and circular redundancy) depends on the predefined threshold, which lead to logical errors and affects the reasoning process of rule-based systems. Therefore, the challenge is to develop a method to extract concise rule bases and improve the coverage of non-anomalous rule bases, i.e., one that not only reduces anomalous rules but also finds the most comprehensive rules from the dataset. In this study, we generated non-anomalous association rules (NAARs) from a cerebrovascular examination dataset through several steps: obtaining a frequent closed itemset, generating association rule bases, subsumption checking, and circularity checking, to fit production rules (PRs) in rule-based systems. Toward the end, the rule inferencing part was performed by PROLOG to obtain possible conclusions toward a specific query given by a user. The experiment shows that compared with the traditional method, the proposed method eliminated a significant number of anomalous rules while improving computational time.