The doctor will see you now: How machine learning and artificial intelligence can extend our understanding and treatment of asthma

Examining the effectiveness of artificial intelligence applications in asthma and COPD outpatient support in terms of patient health and public cost: SWOT analysis

This research aimed to examine the effectiveness of artificial intelligence applications in asthma and chronic obstructive pulmonary disease (COPD) outpatient treatment support in terms of patient health and public costs. The data obtained in the research using semiotic analysis, content analysis and trend analysis methods were analyzed with strengths, weakness, opportunities, threats (SWOT) analysis. In this context, 18 studies related to asthma, COPD and artificial intelligence were evaluated. The strengths of artificial intelligence applications in asthma and COPD outpatient treatment stand out as early diagnosis, access to more patients and reduced costs. The points that stand out among the weaknesses are the acceptance and use of technology and vulnerabilities related to artificial intelligence. Opportunities arise in developing differential diagnoses of asthma and COPD and in examining prognoses for the diseases more effectively. Malicious use, commercial data leaks and data security issues stand out among the threats. Although artificial intelligence applications provide great convenience in the outpatient treatment process for asthma and COPD diseases, precautions must be taken on a global scale and with the participation of international organizations against weaknesses and threats. In addition, there is an urgent need for accreditation for the practices to be carried out in this regard.

Investigating Machine Learning Techniques for Predicting Risk of Asthma Exacerbations: A Systematic Review

Asthma, a common chronic respiratory disease among children and adults, affects more than 200 million people worldwide and causes about 450,000 deaths each year. Machine learning is increasingly applied in healthcare to assist health practitioners in decision-making. In asthma management, machine learning excels in performing well-defined tasks, such as diagnosis, prediction, medication, and management. However, there remain uncertainties about how machine learning can be applied to predict asthma exacerbation. This study aimed to systematically review recent applications of machine learning techniques in predicting the risk of asthma attacks to assist asthma control and management. A total of 860 studies were initially identified from five databases. After the screening and full-text review, 20 studies were selected for inclusion in this review. The review considered recent studies published from January 2010 to February 2023. The 20 studies used machine learning techniques to support future asthma risk prediction by using various data sources such as clinical, medical, biological, and socio-demographic data sources, as well as environmental and meteorological data. While some studies considered prediction as a category, other studies predicted the probability of exacerbation. Only a group of studies applied prediction windows. The paper proposes a conceptual model to summarise how machine learning and available data sources can be leveraged to produce effective models for the early detection of asthma attacks. The review also generated a list of data sources that other researchers may use in similar work. Furthermore, we present opportunities for further research and the limitations of the preceding studies.

Tele-Monitoring Applications in Respiratory Allergy

Respiratory allergic diseases affect over 500 million people globally and pose a substantial burden in terms of morbidity, mortality, and healthcare costs. Restrictive factors such as geographical disparities, infectious pandemics, limitations in resources, and shortages of allergy specialists in underserved areas impede effective management. Telemedicine encompasses real-time visits, store-and-forward option triage, and computer-based technologies for establishing efficient doctor-patient communication. Recent advances in digital technology, including designated applications, informative materials, digital examination devices, wearables, digital inhalers, and integrated platforms, facilitate personalized and evidence-based care delivery. The integration of telemonitoring in respiratory allergy care has shown beneficial effects on disease control, adherence, and quality of life. While the COVID-19 pandemic accelerated the adoption of telemedicine, certain concerns regarding technical requirements, platform quality, safety, reimbursement, and regulatory considerations remain unresolved. The integration of artificial intelligence (AI) in telemonitoring applications holds promise for data analysis, pattern recognition, and personalized treatment plans. Striking the balance between AI-enabled insights and human expertise is crucial for optimizing the benefits of telemonitoring. While telemonitoring exhibits potential for enhancing patient care and healthcare delivery, critical considerations have to be addressed in order to ensure the successful integration of telemonitoring into the healthcare landscape.

Prediction of short-acting beta-agonist usage in patients with asthma using temporal-convolutional neural networks

Objective

Changes in short-acting beta-agonist (SABA) use are an important signal of asthma control and risk of asthma exacerbations. Inhaler sensors passively capture SABA use and may provide longitudinal data to identify at-riskpatients. We evaluate the performance of several ML models in predicting daily SABA use for participants with asthma and determine relevant features for predictive accuracy.

Methods

Participants with self-reported asthma enrolled in a digital health platform (Propeller Health, WI), which included a smartphone application and inhaler sensors that collected the date and time of SABA use. Linear regression, random forests, and temporal convolutional networks (TCN) were applied to predict expected SABA puffs/person/day from SABA usage and environmental triggers. The models were compared with a simple baseline model using explained variance (R2), as well as using average precision (AP) and area under the receiving operator characteristic curve (ROC AUC) for predicting days with ≥1-10 puffs.

Results

Data included 1.2 million days of data from 13 202 participants. A TCN outperformed other models in predicting puff count (R2 = 0.562) and day-over-day change in puff count (R2 = 0.344). The TCN predicted days with ≥10 puffs with an ROC AUC score of 0.952 and an AP of 0.762 for predicting a day with ≥1 puffs. SABA use over the preceding 7 days had the highest feature importance, with a smaller but meaningful contribution from air pollutant features.

Conclusion

Predicted SABA use may serve as a valuable forward-looking signal to inform early clinical intervention and self-management. Further validation with known exacerbation events is needed.

Early Prediction of Asthma

The clinical manifestations of asthma in children are highly variable, are associated with different molecular and cellular mechanisms, and are characterized by common symptoms that may diversify in frequency and intensity throughout life. It is a disease that generally begins in the first five years of life, and it is essential to promptly identify patients at high risk of developing asthma by using different prediction models. The aim of this review regarding the early prediction of asthma is to summarize predictive factors for the course of asthma, including lung function, allergic comorbidity, and relevant data from the patient's medical history, among other factors. This review also highlights the epigenetic factors that are involved, such as DNA methylation and asthma risk, microRNA expression, and histone modification. The different tools that have been developed in recent years for use in asthma prediction, including machine learning approaches, are presented and compared. In this review, emphasis is placed on molecular mechanisms and biomarkers that can be used as predictors of asthma in children.

Where Is the Artificial Intelligence Applied in Dentistry? Systematic Review and Literature Analysis

This literature research had two main objectives. The first objective was to quantify how frequently artificial intelligence (AI) was utilized in dental literature from 2011 until 2021. The second objective was to distinguish the focus of such publications; in particular, dental field and topic. The main inclusion criterium was an original article or review in English focused on dental utilization of AI. All other types of publications or non-dental or non-AI-focused were excluded. The information sources were Web of Science, PubMed, Scopus, and Google Scholar, queried on 19 April 2022. The search string was “artificial intelligence” AND (dental OR dentistry OR tooth OR teeth OR dentofacial OR maxillofacial OR orofacial OR orthodontics OR endodontics OR periodontics OR prosthodontics). Following the removal of duplicates, all remaining publications were returned by searches and were screened by three independent operators to minimize the risk of bias. The analysis of 2011–2021 publications identified 4413 records, from which 1497 were finally selected and calculated according to the year of publication. The results confirmed a historically unprecedented boom in AI dental publications, with an average increase of 21.6% per year over the last decade and a 34.9% increase per year over the last 5 years. In the achievement of the second objective, qualitative assessment of dental AI publications since 2021 identified 1717 records, with 497 papers finally selected. The results of this assessment indicated the relative proportions of focal topics, as follows: radiology 26.36%, orthodontics 18.31%, general scope 17.10%, restorative 12.09%, surgery 11.87% and education 5.63%. The review confirms that the current use of artificial intelligence in dentistry is concentrated mainly around the evaluation of digital diagnostic methods, especially radiology; however, its implementation is expected to gradually penetrate all parts of the profession.

Does machine learning have a role in the prediction of asthma in children?

Asthma is the most common chronic lung disease in childhood. There has been a significant worldwide effort to develop tools/methods to identify children's risk for asthma as early as possible for preventative and early management strategies. Unfortunately, most childhood asthma prediction tools using conventional statistical models have modest accuracy, sensitivity, and positive predictive value. Machine learning is an approach that may improve on conventional models by finding patterns and trends from large and complex datasets. Thus far, few studies have utilized machine learning to predict asthma in children. This review aims to critically assess these studies, describe their limitations, and discuss future directions to move from proof-of-concept to clinical application.

Difficult-to-Treat Asthma Management in School-Age Children

The World Health Organization divides severe asthma into three categories: untreated severe asthma; difficult-to-treat severe asthma; and severe, therapy-resistant asthma. The apparent frequency of severe asthma in the general population of asthmatic children is probably around 5%. Upon referral of these children, it is important to evaluate the diagnosis of asthma carefully before modifying management and applying a long-term monitoring plan. Identification of pathophysiologic phenotypes using objective biomarkers is essential in our routine assessments of severe asthma. Although conventional pharmacologic approaches should be attempted first, there is growing recognition that children with difficult-to-treat asthma may have unique clinical phenotypes that may necessitate alternative treatment approaches including asthma biologics. These new medications, especially those with effects on multiple pathologic features of asthma, raise the hope that new treatment strategies could induce remission. Besides introducing new medications, the opportunity for closer monitoring is feasible with advances in digital health. Therefore, we have the opportunity to improve response to medications, individualize treatment, and monitor response along with potential steps to prevent severe asthma.

Exploring Machine Learning Techniques to Predict the Response to Omalizumab in Chronic Spontaneous Urticaria

Background: Omalizumab is the best treatment for patients with chronic spontaneous urticaria (CSU). Machine learning (ML) approaches can be used to predict response to therapy and the effectiveness of a treatment. No studies are available on the use of ML techniques to predict the response to Omalizumab in CSU. Methods: Data from 132 CSU outpatients were analyzed. Urticaria Activity Score over 7 days (UAS7) and treatment efficacy were assessed. Clinical and demographic characteristics were used for training and validating ML models to predict the response to treatment. Two methodologies were used to label the data based on the response to treatment (UAS7 ≥ 6): (A) at 1, 3 and 5 months; (B) classifying the patients as early responders (ER), late responders (LR) or non-responders (NR) (ER: UAS 7 ≥ 6 at first month, LR: UAS 7 ≥ 6 at third month, NR: if none of the previous conditions occurred). Results: ER were predominantly characterized by hypertension, while LR mainly suffered from asthma and hypothyroidism. A slight positive correlation (R² = 0.21) was found between total IgE levels and UAS7 at 1 month. Variable Importance Analysis (VIA) reported D-dimer and C-reactive proteins as the key blood tests for the performance of learning techniques. Using methodology (A), SVM (specificity of 0.81) and k-NN (sensitivity of 0.8) are the best models to predict LR at the third month. Conclusion: k-NN plus the SVM model could be used to identify the response to treatment. D-dimer and C-reactive proteins have greater predictive power in training ML models.

The Beginning of a New Era: Artificial Intelligence in Healthcare

The healthcare sector is considered to be one of the largest and fast-growing industries in the world. Innovations and novel approaches have always remained the prime aims in order to bring massive development. Before the emergence of technology, the healthcare sector was dependent on manpower, which was time-consuming and less accurate with lack of efficiency. With the recent advancements in machine learning, the condition has been steadily revolutionizing. Artificial intelligence (AI) lies in the computer science department, which stresses on the intelligent machines’ creation, that work and react just like human beings. Currently, the applications of AI have been expanding into those fields, which was once thought to be the only domain of human expertise such as healthcare sector. In this review, we have shed light on the present usage of AI in the healthcare sector, such as its working, and the way this system is being implemented in different domains, such as drug discovery, diagnosis of diseases, clinical trials, remote patient monitoring, and nanotechnology. We have also briefly touched upon its applications in other sectors as well. The public opinions have also been analyzed and discussed along with the future prospects. We have discussed the merits, and the other side of AI, i.e. the disadvantages in the last part of the manuscript.

Interest in technology among medical students early in their clinical experience

BACKGROUND

The world is in the midst of the "digital" revolution characterized by the ascendency of computerization, information systems and artificial intelligence with an emphasis on innovation and creativity. This revolution has affected current medical practice and promises to significantly impact it in the future. This requires physician's understanding and participation in adopting such technology. This study aimed to explore the role technology plays in the future career plans of medical students.

METHODS

A questionnaire examining selection criteria for medical specialty choice, criteria for choosing a post-residency job and demographic data was completed by a convenience sample of 5th-year Israeli medical students.

RESULTS

Two-hundred forty-two students (51 % men) completed the questionnaire, an 84 % response rate. Only a third (35 %) rated the specialty selection criterion "provides mechanical/ technological challenges" as important, while only 7% considered as important that a specialty requires skills in computer science. Few students were interested in post-residency positions requiring much technological knowledge (25 %) and requiring much skill with computerized information systems (13 %). Male students were significantly more interested than females in such positions and these students more often reported that they were considering careers in surgery and its subspecialties. This surgical bent was confirmed by the 42 % of students interested in post-residency positions that include time in the operating room having more interest in positions requiring much technological knowledge than the students not interested in operating room time.

CONCLUSIONS

This preliminary study demonstrated that as a group the students' expressed relatively little interest in medical specialties and post-residency positions involving technological challenges and knowledge of information (computer) science. Yet, the sub-group interested in the surgical specialties had such interests. These findings were perplexing since the students belong to Generations Y and Z who are steeped in the use of smartphones and social media. Therefore, we failed to support our hypothesis that Generation Y and Z students would be attracted to specialties and positions that provide them with technological challenges. Furthermore, medical educators need to explore this apparent lack of interest in technology in order to insure that the future physician workforce is ready to face future "digital" challenges.

Developing and evaluating a pediatric asthma severity computable phenotype derived from electronic health records

BACKGROUND

Extensive data available in electronic health records (EHRs) have the potential to improve asthma care and understanding of factors influencing asthma outcomes. However, this work can be accomplished only when the EHR data allow for accurate measures of severity, which at present are complex and inconsistent.

OBJECTIVE

Our aims were to create and evaluate a standardized pediatric asthma severity phenotype based in clinical asthma guidelines for use in EHR-based health initiatives and studies and also to examine the presence and absence of these data in relation to patient characteristics.

METHODS

We developed an asthma severity computable phenotype and compared the concordance of different severity components contributing to the phenotype to trends in the literature. We used multivariable logistic regression to assess the presence of EHR data relevant to asthma severity.

RESULTS

The asthma severity computable phenotype performs as expected in comparison with national statistics and the literature. Severity classification for a child is maximized when based on the long-term medication regimen component and minimized when based only on the symptom data component. Use of the severity phenotype results in better, clinically grounded classification. Children for whom severity could be ascertained from these EHR data were more likely to be seen for asthma in the outpatient setting and less likely to be older or Hispanic. Black children were less likely to have lung function testing data present.

CONCLUSION

We developed a pragmatic computable phenotype for pediatric asthma severity that is transportable to other EHRs.

Predicting Severe Asthma Exacerbations in Children: Blueprint for Today and Tomorrow

Severe asthma exacerbations are the primary cause of morbidity and mortality in children with asthma. Accurate prediction of children at risk for severe exacerbations, defined as those requiring systemic corticosteroids, emergency department visit, and/or hospitalization, would considerably reduce health care utilization and improve symptoms and quality of life. Substantial progress has been made in identifying high-risk exacerbation-prone children. Known risk factors for exacerbations include demographic characteristics (ie, low income, minority race/ethnicity), poor asthma control, environmental exposures (ie, aeroallergen exposure/sensitization, concomitant viral infection), inflammatory biomarkers, genetic polymorphisms, and markers from other "omic" technologies. The strongest risk factor for a future severe exacerbation remains having had one in the previous year. Combining risk factors into composite scores and use of advanced predictive analytic techniques such as machine learning are recent methods used to achieve stronger prediction of severe exacerbations. However, these methods are limited in prediction efficiency and are currently unable to predict children at risk for impending (within days) severe exacerbations. Thus, we provide a commentary on strategies that have potential to allow for accurate and reliable prediction of children at risk for impending exacerbations. These approaches include implementation of passive, real-time monitoring of impending exacerbation predictors, use of population health strategies, prediction of severe exacerbation responders versus nonresponders to conventional exacerbation management, and considerations for preschool-age children who can be especially high risk. Rigorous prediction and prevention of severe asthma exacerbations is needed to advance asthma management and improve the associated morbidity and mortality.

Artificial Intelligence/Machine Learning in Respiratory Medicine and Potential Role in Asthma and COPD Diagnosis

Artificial intelligence (AI) and machine learning, a subset of AI, are increasingly used in medicine. AI excels at performing well-defined tasks, such as image recognition; for example, classifying skin biopsy lesions, determining diabetic retinopathy severity, and detecting brain tumors. This article provides an overview of the use of AI in medicine and particularly in respiratory medicine, where it is used to evaluate lung cancer images, diagnose fibrotic lung disease, and more recently is being developed to aid the interpretation of pulmonary function tests and the diagnosis of a range of obstructive and restrictive lung diseases. The development and validation of AI algorithms requires large volumes of well-structured data, and the algorithms must work with variable levels of data quality. It is important that clinicians understand how AI can function in the context of heterogeneous conditions such as asthma and chronic obstructive pulmonary disease where diagnostic criteria overlap, how AI use fits into everyday clinical practice, and how issues of patient safety should be addressed. AI has a clear role in providing support for doctors in the clinical workplace, but its relatively recent introduction means that confidence in its use still has to be fully established. Overall, AI is expected to play a key role in aiding clinicians in the diagnosis and management of respiratory diseases in the future, and it will be exciting to see the benefits that arise for patients and doctors from its use in everyday clinical practice.

Advances in understanding and reducing the burden of severe asthma in children

Severe asthma in children is rare, accounting for only a small proportion of childhood asthma. After addressing modifiable factors such as adherence to treatment, comorbidities, and adverse exposures, children whose disease is not well controlled on high doses of medication form a heterogeneous group of severe asthma phenotypes. Over the past decade, considerable advances have been made in understanding the pathophysiology of severe therapy-resistant asthma in children. However, asthma attacks and hospital admissions are frequent and mortality is still unacceptably high. Strategies to modify the natural history of asthma, prevent severe exacerbations, and prevent lung function decline are needed. Mechanistic studies have led to the development of several biologics targeting type 2 inflammation. This growing pipeline has the potential to reduce the burden of severe asthma; however, detailed assessment and characterisation of each child with seemingly severe asthma is necessary so that the most effective and appropriate management strategy can be implemented. Risk stratification, remote monitoring, and the integration of multiple data sources could help to tailor management for the individual child with severe asthma.