Identification of potentially undiagnosed patients with nontuberculous mycobacterial lung disease using machine learning applied to primary care data in the UK

Efficient lung cancer detection using computational intelligence and ensemble learning

Lung cancer emerges as a major factor in cancer-related fatalities in the current generation, and it is predicted to continue having a long-term impact. Detecting symptoms early becomes crucial for effective treatment, underscoring innovative therapy's necessity. Many researchers have conducted extensive work in this area, yet challenges such as high false-positive rates and achieving high accuracy in detection continue to complicate accurate diagnosis. In this research, we aim to develop an ecologically considerate lung cancer therapy prototype model that maximizes resource utilization by leveraging recent advancements in computational intelligence. We also propose an Internet of Medical Things (IoMT)-based, consumer-focused integrated framework to implement the suggested approach, providing patients with appropriate care. Our proposed method employs Logistic Regression, MLP Classifier, Gaussian NB Classifier, and Intelligent Feature Selection using K-Means and Fuzzy Logic to enhance detection procedures in lung cancer dataset. Additionally, ensemble learning is incorporated through a voting classifier. The proposed model's effectiveness is improved through hyperparameter tuning via grid search. The proposed model's performance is demonstrated through comparative analysis with existing NB, J48, and SVM approaches, achieving a 98.50% accuracy rate. The efficiency gains from this approach have the potential to save a significant amount of time and cost. This study underscores the potential of computational intelligence and IoMT in developing effective, resource-efficient lung cancer therapies.

Supporting Patients with Nontuberculous Mycobacterial Pulmonary Disease: Ensuring Best Practice in UK Healthcare Settings

Nontuberculous mycobacterial pulmonary disease (NTM-PD) results from opportunistic lung infections by mycobacteria other than Mycobacterium tuberculosis or Mycobacterium leprae species. Similar to many other countries, the incidence of NTM-PD in the United Kingdom (UK) is on the rise for reasons that are yet to be determined. Despite guidelines established by the American Thoracic Society (ATS), the Infectious Diseases Society of America, and the British Thoracic Society, NTM-PD diagnosis and management remain a significant clinical challenge. In this review article, we comprehensively discuss key challenges in NTM-PD diagnosis and management, focusing on the UK healthcare setting. We also propose countermeasures to overcome these challenges and improve the detection and treatment of patients with NTM-PD.

Objectivizing issues in the diagnosis of complex rare diseases: lessons learned from testing existing diagnosis support systems on ciliopathies

BACKGROUND

There are approximately 8,000 different rare diseases that affect roughly 400 million people worldwide. Many of them suffer from delayed diagnosis. Ciliopathies are rare monogenic disorders characterized by a significant phenotypic and genetic heterogeneity that raises an important challenge for clinical diagnosis. Diagnosis support systems (DSS) applied to electronic health record (EHR) data may help identify undiagnosed patients, which is of paramount importance to improve patients' care. Our objective was to evaluate three online-accessible rare disease DSSs using phenotypes derived from EHRs for the diagnosis of ciliopathies.

METHODS

Two datasets of ciliopathy cases, either proven or suspected, and two datasets of controls were used to evaluate the DSSs. Patient phenotypes were automatically extracted from their EHRs and converted to Human Phenotype Ontology terms. We tested the ability of the DSSs to diagnose cases in contrast to controls based on Orphanet ontology.

RESULTS

A total of 79 cases and 38 controls were selected. Performances of the DSSs on ciliopathy real world data (best DSS with area under the ROC curve = 0.72) were not as good as published performances on the test set used in the DSS development phase. None of these systems obtained results which could be described as "expert-level". Patients with multisystemic symptoms were generally easier to diagnose than patients with isolated symptoms. Diseases easily confused with ciliopathy generally affected multiple organs and had overlapping phenotypes. Four challenges need to be considered to improve the performances: to make the DSSs interoperable with EHR systems, to validate the performances in real-life settings, to deal with data quality, and to leverage methods and resources for rare and complex diseases.

CONCLUSION

Our study provides insights into the complexities of diagnosing highly heterogenous rare diseases and offers lessons derived from evaluation existing DSSs in real-world settings. These insights are not only beneficial for ciliopathy diagnosis but also hold relevance for the enhancement of DSS for various complex rare disorders, by guiding the development of more clinically relevant rare disease DSSs, that could support early diagnosis and finally make more patients eligible for treatment.

Multiparameter immunoprofiling for the diagnosis and differentiation of progressive versus nonprogressive nontuberculous mycobacterial lung disease-A pilot study

Clinical prediction of nontuberculous mycobacteria lung disease (NTM-LD) progression remains challenging. We aimed to evaluate antigen-specific immunoprofiling utilizing flow cytometry (FC) of activation-induced markers (AIM) and IFN-γ enzyme-linked immune absorbent spot assay (ELISpot) accurately identifies patients with NTM-LD, and differentiate those with progressive from nonprogressive NTM-LD. A Prospective, single-center, and laboratory technician-blinded pilot study was conducted to evaluate the FC and ELISpot based immunoprofiling in patients with NTM-LD (n = 18) and controls (n = 22). Among 18 NTM-LD patients, 10 NTM-LD patients were classified into nonprogressive, and 8 as progressive NTM-LD based on clinical and radiological features. Peripheral blood mononuclear cells were collected from patients with NTM-LD and control subjects with negative QuantiFERON results. After stimulation with purified protein derivative (PPD), mycobacteria-specific peptide pools (MTB300, RD1-peptides), and control antigens, we performed IFN-γ ELISpot and FC AIM assays to access their diagnostic accuracies by receiver operating curve (ROC) analysis across study groups. Patients with NTM-LD had significantly higher percentage of CD4+/CD8+ T-cells co-expressing CD25+CD134+ in response to PPD stimulation, differentiating between NTM-LD and controls. Among patients with NTM-LD, there was a significant difference in CD25+CD134+ co-expression in MTB300-stimulated CD8+ T-cells (p <0.05; AUC-ROC = 0.831; Sensitivity = 75% [95% CI: 34.9-96.8]; Specificity = 90% [95% CI: 55.5-99.7]) between progressors and nonprogressors. Significant differences in the ratios of antigen-specific IFN-γ ELISpot responses were also seen for RD1-nil/PPD-nil and RD1-nil/anti-CD3-nil between patients with nonprogressive vs. progressive NTM-LD. Our results suggest that multiparameter immunoprofiling can accurately identify patients with NTM-LD and may identify patients at risk of disease progression. A larger longitudinal study is needed to further evaluate this novel immunoprofiling approach.

Performance and clinical utility of a new supervised machine-learning pipeline in detecting rare ciliopathy patients based on deep phenotyping from electronic health records and semantic similarity

BACKGROUND

Rare diseases affect approximately 400 million people worldwide. Many of them suffer from delayed diagnosis. Among them, NPHP1-related renal ciliopathies need to be diagnosed as early as possible as potential treatments have been recently investigated with promising results. Our objective was to develop a supervised machine learning pipeline for the detection of NPHP1 ciliopathy patients from a large number of nephrology patients using electronic health records (EHRs).

METHODS AND RESULTS

We designed a pipeline combining a phenotyping module re-using unstructured EHR data, a semantic similarity module to address the phenotype dependence, a feature selection step to deal with high dimensionality, an undersampling step to address the class imbalance, and a classification step with multiple train-test split for the small number of rare cases. The pipeline was applied to thirty NPHP1 patients and 7231 controls and achieved good performances (sensitivity 86% with specificity 90%). A qualitative review of the EHRs of 40 misclassified controls showed that 25% had phenotypes belonging to the ciliopathy spectrum, which demonstrates the ability of our system to detect patients with similar conditions.

CONCLUSIONS

Our pipeline reached very encouraging performance scores for pre-diagnosing ciliopathy patients. The identified patients could then undergo genetic testing. The same data-driven approach can be adapted to other rare diseases facing underdiagnosis challenges.

Risk Factors for Nontuberculous Mycobacterial Pulmonary Disease: A Systematic Literature Review and Meta-Analysis

BACKGROUND

Nontuberculous mycobacterial pulmonary disease (NTM-PD) is widely underdiagnosed, and certain patient groups, such as those with underlying respiratory diseases, are at increased risk of developing the disease. Understanding patients at risk is essential to allow for prompt testing and diagnosis and appropriate management to prevent disease progression.

RESEARCH QUESTION

What are the risk factors for NTM-PD that should prompt a physician to consider NTM testing and diagnosis?

STUDY DESIGN AND METHODS

Electronic searches of PubMed and EMBASE were conducted in July 2021 for the period 2011-2021. Inclusion criteria were studies of patients with NTM-PD with associated risk factors. Data were extracted and assessed using the Newcastle-Ottawa Scale. Data analysis was conducted using the R-based "meta" package. Only studies that reported association outcomes for cases with NTM-PD compared with control participants (healthy populations or participants without NTM-PD) were considered for the meta-analysis.

RESULTS

Of the 9,530 searched publications, 99 met the criteria for the study. Of these, 24 formally reported an association between possible risk factors and the presence of NTM-PD against a control population and were included in the meta-analysis. Comorbid respiratory disease was associated with a significant increase in the OR for NTM-PD (bronchiectasis [OR, 21.43; 95% CI, 5.90-77.82], history of TB [OR, 12.69; 95% CI, 2.39-67.26], interstitial lung disease [OR, 6.39; 95% CI, 2.65-15.37], COPD [OR, 6.63; 95% CI, 4.57-9.63], and asthma [OR, 4.15; 95% CI, 2.81-6.14]). Other factors noted to be associated with an increased risk of NTM-PD were the use of inhaled corticosteroids (OR 4.46; 95% CI, 2.13-9.35), solid tumors (OR, 4.66; 95% CI, 1.04-20.94) and the presence of pneumonia (OR, 5.54; 95% CI, 2.72-11.26).

INTERPRETATION

The greatest risk for NTM-PD is conferred by comorbid respiratory diseases such as bronchiectasis. These findings could help with identification of patient populations at risk for NTM-PD to drive prompt testing and appropriate initiation of therapy.

Building a model for the differential diagnosis of non-tuberculous mycobacterial lung disease and pulmonary tuberculosis: A case-control study based on immunological and radiological features

BACKGROUND

Although the incidence of non-tuberculous mycobacterial pulmonary disease (NTM-PD) is increasing annually, it is easily misdiagnosed as pulmonary tuberculosis (PTB). This study aimed to screen and identify the immunological and radiological characteristics that differentiate NTM-PD from PTB and to construct a discriminatory diagnostic model for NTM-PD, providing new tools for its differential diagnosis.

METHODS

Hospitalised patients diagnosed with NTM-PD or PTB between January 2019 and June 2023 were included in the study. Immunological and radiological characteristics were compared between the two groups. Based on the selected differential features, a logistic regression algorithm was used to construct a discriminatory diagnostic model for NTM-PD, and its diagnostic performance was preliminarily analysed.

RESULTS

Patients with NTM-PD were significantly older than those with PTB and the tuberculosis-specific interferon-gamma release assay (TB-IGRA) positivity rate was significantly lower in the NTM-PD group. Moreover, the absolute counts of total T lymphocytes, CD4+ T lymphocytes, CD8+ T lymphocytes, NK cells, and B lymphocytes were significantly lower in patients with NTM-PD and PTB than in healthy controls. Additionally, patients with NTM-PD had a significantly lower absolute count of B lymphocytes than the PTB group. Radiological analysis revealed significant differences between patients with NTM-PD and PTB in terms of cavity wall thickness, bronchial dilation, lung consolidation, pulmonary nodule size, pulmonary emphysema, lung bullae, lymph node calcification, pleural effusion, mediastinal and hilar lymphadenopathy, and the tree-in-bud sign. Bronchial dilation was identified as the predominant risk factor of NTM-PD, whereas TB-IGRA positivity, lymph node calcification, pleural effusion, and mediastinal and hilar lymphadenopathies were protective factors. Based on this, we constructed a discriminatory diagnostic model for NTM-PD. Its receiver operating characteristic curve demonstrated good diagnostic performance, with an area under the curve of 0.938. At the maximum Youden index of 0.746, the sensitivity and specificity were 0.835 and 0.911, respectively.

CONCLUSIONS

Patients with NTM-PD and PTB exhibited impaired humoral and cellular immune functions as well as significant differences in radiological features. The constructed NTM-PD diagnostic model demonstrated good diagnostic performance. This study provides a new tool for the differential diagnosis of NTM-PD.

Best Practices for the Management of Patients with Non-Tuberculous Mycobacterial Pulmonary Disease According to a German Nationwide Analysis of Expert Centers

Non-tuberculous mycobacterial pulmonary disease (NTM-PD) is a chronic inflammatory lung disease caused by infection with non-tuberculous mycobacteria (NTM). International guidelines provide evidence-based recommendations on appropriate diagnosis and treatment strategies, but there is a need for sharing day-to-day best practice between treatment centers to optimize patient care. This is particularly valuable for rare diseases like NTM-PD. In this cross-sectional analysis of NTM-PD management in Germany, medical and administrative staff from seven treatment centers were interviewed to identify best practice in the diagnosis, treatment, and ongoing management of patients with NTM-PD, including related hospital infrastructure and administration processes. A prioritization led to a collection of best practices for the management of patients with NTM-PD in Germany, which is presented here. Selected current best practices included performance of regular sputum tests for diagnosis, use of medical reports, and regular follow-up visits as well as increased interaction between physicians across different specialties. Future best practices that may be implemented to overcome current barriers comprised disease awareness activities, patient empowerment, and new approaches to enhance physician interaction. Challenges related to their implementation are also discussed and will help to raise disease awareness. The presented best practices may guide and optimize patient management in other centers.

A systematic review of clinical health conditions predicted by machine learning diagnostic and prognostic models trained or validated using real-world primary health care data

With the advances in technology and data science, machine learning (ML) is being rapidly adopted by the health care sector. However, there is a lack of literature addressing the health conditions targeted by the ML prediction models within primary health care (PHC) to date. To fill this gap in knowledge, we conducted a systematic review following the PRISMA guidelines to identify health conditions targeted by ML in PHC. We searched the Cochrane Library, Web of Science, PubMed, Elsevier, BioRxiv, Association of Computing Machinery (ACM), and IEEE Xplore databases for studies published from January 1990 to January 2022. We included primary studies addressing ML diagnostic or prognostic predictive models that were supplied completely or partially by real-world PHC data. Studies selection, data extraction, and risk of bias assessment using the prediction model study risk of bias assessment tool were performed by two investigators. Health conditions were categorized according to international classification of diseases (ICD-10). Extracted data were analyzed quantitatively. We identified 106 studies investigating 42 health conditions. These studies included 207 ML prediction models supplied by the PHC data of 24.2 million participants from 19 countries. We found that 92.4% of the studies were retrospective and 77.3% of the studies reported diagnostic predictive ML models. A majority (76.4%) of all the studies were for models' development without conducting external validation. Risk of bias assessment revealed that 90.8% of the studies were of high or unclear risk of bias. The most frequently reported health conditions were diabetes mellitus (19.8%) and Alzheimer's disease (11.3%). Our study provides a summary on the presently available ML prediction models within PHC. We draw the attention of digital health policy makers, ML models developer, and health care professionals for more future interdisciplinary research collaboration in this regard.

Identifying potentially undiagnosed nontuberculous mycobacterial lung disease among patients with chronic obstructive pulmonary disease: Development of a predictive algorithm using claims data

BACKGROUND: Nontuberculous mycobacterial lung disease (NTMLD) is a debilitating disease. Chronic obstructive pulmonary disease (COPD) is the leading comorbidity associated with NTMLD in the United States. Their similarities in symptoms and overlapping radiological findings may delay NTMLD diagnosis in patients with COPD. OBJECTIVE: To develop a predictive model that identifies potentially undiagnosed NTMLD among patients with COPD. METHODS: This retrospective cohort study developed a predictive model of NTMLD using US Medicare beneficiary claims data (2006 - 2017). Patients with COPD with NTMLD were matched 1:3 to patients with COPD without NTMLD by age, sex, and year of COPD diagnosis. The predictive model was developed using logistic regression modeling risk factors such as pulmonary symptoms, comorbidities, and health care resource utilization. The final model was based on model fit statistics and clinical inputs. Model performance was evaluated for both discrimination and generalizability with c-statistics and receiver operating characteristic curves. RESULTS: There were 3,756 patients with COPD with NTMLD identified and matched to 11,268 patients with COPD without NTMLD. A higher proportion of patients with COPD with NTMLD, compared with those with COPD without NTMLD, had claims for pulmonary symptoms and conditions, including hemoptysis (12.6% vs 1.4%), cough (63.4% vs 24.7%), dyspnea (72.5% vs 38.2%), pneumonia (59.2% vs 13.4%), chronic bronchitis (40.5% vs 16.3%), emphysema, (36.7% vs 11.1%), and lung cancer (15.7% vs 3.5%). A higher proportion of patients with COPD with NTMLD had pulmonologist and infectious disease (ID) specialist visits than patients with COPD without NTMLD (≥ 1 pulmonologist visit: 81.3% vs 23.6%, respectively; ≥ 1 ID visit: 28.3% vs 4.1%, respectively, P < 0.0001). The final model consists of 10 risk factors (≥ 2 ID specialist visits; ≥ 4 pulmonologist visits; the presence of hemoptysis, cough, emphysema, pneumonia, tuberculosis, lung cancer, or idiopathic interstitial lung disease; and being underweight during a 1-year pre-NTMLD period) predicting NTMLD with high sensitivity and specificity (c-statistic, 0.9). The validation of the model on new testing data demonstrated similar discrimination and showed the model was able to predict NTMLD earlier than the receipt of the first diagnostic claim for NTMLD. CONCLUSIONS: This predictive algorithm uses a set of criteria comprising patterns of health care use, respiratory symptoms, and comorbidities to identify patients with COPD and possibly undiagnosed NTMLD with high sensitivity and specificity. It has potential application in raising timely clinical suspicion of patients with possibly undiagnosed NTMLD, thereby reducing the period of undiagnosed NTMLD. DISCLOSURES: Dr Wang and Dr Hassan are employees of Insmed, Inc. Dr Chatterjee was an employee of Insmed, Inc, at the time of this study. Dr Marras is participating in multicenter clinical trials sponsored by Insmed, Inc, has consulted for RedHill Biopharma, and has received a speaker's honorarium from AstraZeneca. Dr Allison is an employee of Statistical Horizons, LLC. This study was funded by Insmed Inc.

Performance evaluation of deep learning techniques for lung cancer prediction

Due to the increase in pollution, the number of deaths caused by lung disease is rising rapidly. It is essential to predict the disease in earlier stages by means of high-level knowledge and acquaintance. Deep learning-based lung cancer prediction plays a vital role in assisting the medical practioners for diagnosing lung cancer in earlier stage. Computer-Aided diagnosis is considered to bring a boost to the field of medicine by tying it to automated systems. In this research paper, several models are experimented by using chest X-ray image or CT scan as an input to detect a particular disease. This research work is carried out to identify the best performing deep learning techniques for lung disease prediction. The performance of the method is evaluated using various performance metrics, such as precision, recall, accuracy and Jaccard index.

Patient-Patient Similarity-Based Screening of a Clinical Data Warehouse to Support Ciliopathy Diagnosis

A timely diagnosis is a key challenge for many rare diseases. As an expanding group of rare and severe monogenic disorders with a broad spectrum of clinical manifestations, ciliopathies, notably renal ciliopathies, suffer from important underdiagnosis issues. Our objective is to develop an approach for screening large-scale clinical data warehouses and detecting patients with similar clinical manifestations to those from diagnosed ciliopathy patients. We expect that the top-ranked similar patients will benefit from genetic testing for an early diagnosis. The dependence and relatedness between phenotypes were taken into account in our similarity model through medical concept embedding. The relevance of each phenotype to each patient was also considered by adjusted aggregation of phenotype similarity into patient similarity. A ranking model based on the best-subtype-average similarity was proposed to address the phenotypic overlapping and heterogeneity of ciliopathies. Our results showed that using less than one-tenth of learning sources, our language and center specific embedding provided comparable or better performances than other existing medical concept embeddings. Combined with the best-subtype-average ranking model, our patient-patient similarity-based screening approach was demonstrated effective in two large scale unbalanced datasets containing approximately 10,000 and 60,000 controls with kidney manifestations in the clinical data warehouse (about 2 and 0.4% of prevalence, respectively). Our approach will offer the opportunity to identify candidate patients who could go through genetic testing for ciliopathy. Earlier diagnosis, before irreversible end-stage kidney disease, will enable these patients to benefit from appropriate follow-up and novel treatments that could alleviate kidney dysfunction.

Nontuberculous Mycobacterial Pulmonary Disease: Clinical Epidemiologic Features, Risk Factors, and Diagnosis: The Nontuberculous Mycobacterial Series

Nontuberculous mycobacterial pulmonary disease (NTM-PD) continues to impose a significant clinical burden of disease on susceptible patients. The incidence of NTM-PD is rising globally, but it remains a condition that is challenging to diagnose and treat effectively. This review provides an update on the global epidemiologic features, risk factors, and diagnostic considerations associated with the management of NTM-PD.

Meeting the challenges of NTM-PD from the perspective of the organism and the disease process: innovations in drug development and delivery

Non-tuberculous mycobacterial pulmonary disease (NTM-PD) poses a substantial patient, healthcare, and economic burden. Managing NTM-PD remains challenging, and factors contributing to this include morphological, species, and patient characteristics as well as the treatment itself. This narrative review focusses on the challenges of NTM-PD from the perspective of the organism and the disease process. Morphological characteristics of non-tuberculous mycobacteria (NTM), antimicrobial resistance mechanisms, and an ability to evade host defences reduce NTM susceptibility to many antibiotics. Resistance to antibiotics, particularly macrolides, is of concern, and is associated with high mortality rates in patients with NTM-PD. New therapies are desperately needed to overcome these hurdles and improve treatment outcomes in NTM-PD. Amikacin liposome inhalation suspension (ALIS) is the first therapy specifically developed to treat refractory NTM-PD caused by Mycobacterium avium complex (MAC) and is approved in the US, EU and Japan. It provides targeted delivery to the lung and effective penetration of macrophages and biofilms and has demonstrated efficacy in treating refractory MAC pulmonary disease (MAC-PD) in the Phase III CONVERT study. Several other therapies are currently being developed including vaccination, bacteriophage therapy, and optimising host defences. Newly developed antibiotics have shown potential activity against NTM-PD and include benzimidazole, delamanid, and pretomanid. Antibiotics commonly used to treat other infections have also been repurposed for NTM-PD, including clofazimine and bedaquiline. Data from larger-scale studies are needed to determine the potential of many of these therapies for treating NTM-PD.

Nontuberculous mycobacterial lung disease caused by Mycobacterium avium complex - disease burden, unmet needs, and advances in treatment developments

INTRODUCTION

Nontuberculous mycobacterial (NTM) lung disease (LD) is the most common clinical manifestation of NTM infection and is a growing health concern. Up to 85% of NTM-LD cases are caused by Mycobacterium avium complex (MAC). Increased awareness of NTM-LD caused by MAC is needed as patients with this disease experience substantial burden and unmet treatment needs.

AREAS COVERED

This review provides clinicians and regulatory and healthcare decision makers an overview of the clinical, economic, and humanistic burden of NTM-LD and the unmet treatment needs faced by patients and clinicians. The review focuses on NTM-LD caused by MAC. A summary of the 2020 NTM guidelines specifically for MAC-LD and an overview of novel treatment options, including amikacin liposome inhalation suspension (ALIS) as the first approved therapy for refractory MAC-LD, and investigational drugs in testing phase are provided.

EXPERT OPINION

Key advancements in NTM-LD management include recent updates to clinical practice guidelines, approval of ALIS for the treatment of refractory MAC-LD, and ongoing clinical trials of investigational treatments. Yet opportunities still exist to improve patient outcomes, including development of better screening tools, such as reliable and responsive biomarkers to help identify high-risk patients, and addressing unmet treatment needs.

Using Artificial Intelligence in Fungal Lung Disease: CPA CT Imaging as an Example

This positioning paper aims to discuss current challenges and opportunities for artificial intelligence (AI) in fungal lung disease, with a focus on chronic pulmonary aspergillosis and some supporting proof-of-concept results using lung imaging. Given the high uncertainty in fungal infection diagnosis and analyzing treatment response, AI could potentially have an impactful role; however, developing imaging-based machine learning raises several specific challenges. We discuss recommendations to engage the medical community in essential first steps towards fungal infection AI with gathering dedicated imaging registries, linking with non-imaging data and harmonizing image-finding annotations.

Non tuberculous mycobacteria pulmonary disease: patients and clinicians working together to improve the evidence base for care

Non-tuberculous mycobacterial pulmonary disease is on the rise globally. It is often missed, and causes significant morbidity and even mortality. Here, members of a clinical research network and a patient support group discuss some of the current key issues in NTM management. In addition to the need for research into epidemiology, immunology and treatment, we recommend greater use of patient and clinician networks to: (i) educate primary and secondary care clinicians to develop a high index of suspicion when investigating and treating at risk populations. (ii) promote a multidisciplinary team. (iii) promote shared patient-clinician decision making throughout care. (iv) incorporate use of patient self-report measures to assess progress and outcomes. (v) increase education of patients on their illness and its management. (vi) recruit patients into research projects and registries to improve the clinical evidence base. (vii) increase co-production of research with key stakeholders such as patients and their families, using expert patients and patient groups. (viii) understand more about the psychological, social and economic consequences of the disease.

Predictive modeling of nontuberculous mycobacterial pulmonary disease epidemiology using German health claims data

OBJECTIVES

Administrative claims data are prone to underestimate the burden of non-tuberculous mycobacterial pulmonary disease (NTM-PD).

METHODS

We developed machine learning-based algorithms using historical claims data from cases with NTM-PD to predict patients with a high probability of having previously undiagnosed NTM-PD and to assess actual prevalence and incidence. Adults with incident NTM-PD were classified from a representative 5% sample of the German population covered by statutory health insurance during 2011-2016 by the International Classification of Diseases, 10th revision code A31.0. Pre-diagnosis characteristics (patient demographics, comorbidities, diagnostic and therapeutic procedures, and medications) were extracted and compared to that of a control group without NTM-PD to identify risk factors.

RESULTS

Applying a random forest model (area under the curve 0.847; total error 19.4%) and a risk threshold of >99%, prevalence and incidence rates in 2016 increased 5-fold and 9-fold to 19 and 15 cases/100,000 population, respectively, for both coded and non-coded vs. coded cases alone.

CONCLUSIONS

The use of a machine learning-based algorithm applied to German statutory health insurance claims data predicted a considerable number of previously unreported NTM-PD cases with high probabilty.