Introduction of a new approach to interpret pulmonary function tests (PFT) based on Machine learning and Game theory

Introduction: Quantitative computed tomography (qCT) is an emergent technique for diagnostics and research in patients with chronic obstructive pulmonary disease (COPD). qCT parameters demonstrate a correlation with pulmonary function tests and symptoms. However, qCT only provides anatomical, not functional, information. We evaluated five distinct, partial-machine learning-based mathematical models to predict lung function parameters from qCT values in comparison with pulmonary function tests. Methods: 75 patients with diagnosed COPD underwent body plethysmography and a dose-optimized qCT examination on a third-generation, dual-source CT with inspiration and expiration. Delta values (inspiration—expiration) were calculated afterwards. Four parameters were quantified: mean lung density, lung volume low-attenuated volume, and full width at half maximum. Five models were evaluated for best prediction: average prediction, median prediction, k-nearest neighbours (kNN), gradient boosting, and multilayer perceptron. Results: The lowest mean relative error (MRE) was calculated for the kNN model with 16%. Similar low MREs were found for polynomial regression as well as gradient boosting-based prediction. Other models led to higher MREs and thereby worse predictive performance. Beyond the sole MRE, distinct differences in prediction performance, dependent on the initial dataset (expiration, inspiration, delta), were found. Conclusion: Different, partially machine learning-based models allow the prediction of lung function values from static qCT parameters within a reasonable margin of error. Therefore, qCT parameters may contain more information than we currently utilize and can potentially augment standard functional lung testing.

Download Full-text

A Machine Learning Application to Predict Early Lung Involvement in Scleroderma: A Feasibility Evaluation

Diagnostics ◽

10.3390/diagnostics11101880 ◽

2021 ◽

Vol 11 (10) ◽

pp. 1880

Author(s):

Giuseppe Murdaca ◽

Simone Caprioli ◽

Alessandro Tonacci ◽

Lucia Billeci ◽

Monica Greco ◽

...

Keyword(s):

Machine Learning ◽

Random Forest ◽

Pulmonary Function ◽

Small Sample Size ◽

Pulmonary Function Tests ◽

Pulmonary Involvement ◽

Small Sample ◽

Lung Involvement ◽

High Resolution Computed Tomography ◽

Function Tests

Introduction: Systemic sclerosis (SSc) is a systemic immune-mediated disease, featuring fibrosis of the skin and organs, and has the greatest mortality among rheumatic diseases. The nervous system involvement has recently been demonstrated, although actual lung involvement is considered the leading cause of death in SSc and, therefore, should be diagnosed early. Pulmonary function tests are not sensitive enough to be used for screening purposes, thus they should be flanked by other clinical examinations; however, this would lead to a risk of overtesting, with considerable costs for the health system and an unnecessary burden for the patients. To this extent, Machine Learning (ML) algorithms could represent a useful add-on to the current clinical practice for diagnostic purposes and could help retrieve the most useful exams to be carried out for diagnostic purposes. Method: Here, we retrospectively collected high resolution computed tomography, pulmonary function tests, esophageal pH impedance tests, esophageal manometry and reflux disease questionnaires of 38 patients with SSc, applying, with R, different supervised ML algorithms, including lasso, ridge, elastic net, classification and regression trees (CART) and random forest to estimate the most important predictors for pulmonary involvement from such data. Results: In terms of performance, the random forest algorithm outperformed the other classifiers, with an estimated root-mean-square error (RMSE) of 0.810. However, this algorithm was seen to be computationally intensive, leaving room for the usefulness of other classifiers when a shorter response time is needed. Conclusions: Despite the notably small sample size, that could have prevented obtaining fully reliable data, the powerful tools available for ML can be useful for predicting early lung involvement in SSc patients. The use of predictors coming from spirometry and pH impedentiometry together might perform optimally for predicting early lung involvement in SSc.

Download Full-text

Study of pulmonary function tests in tobacco factory workers

MedPulse International Journal of Physiology ◽

10.26611/103632 ◽

2018 ◽

Vol 6 (3) ◽

pp. 16-19

Author(s):

Gajanan V Patil ◽

◽

Atish Pagar ◽

U S Patil ◽

M K Parekh ◽

...

Keyword(s):

Pulmonary Function ◽

Pulmonary Function Tests ◽

Factory Workers ◽

Function Tests

Download Full-text

A study on Variations of pulmonary function tests in different stages of pregnancy

Asian Pacific Journal of Health Sciences ◽

10.21276/apjhs.2016.3.3.7 ◽

2016 ◽

Vol 3 (3) ◽

pp. 45-48

Author(s):

N Bhaskar Rao ◽

◽

Ch Rambabu

Keyword(s):

Pulmonary Function ◽

Pulmonary Function Tests ◽

Function Tests

Download Full-text

Pulmonary Function Tests in European Birth Cohorts

Current Respiratory Medicine Reviews ◽

10.2174/1573398x11309010002 ◽

2013 ◽

Vol 9 (1) ◽

pp. 3-10

Author(s):

Linus Grabenhenrich ◽

Cynthia Hohmann ◽

Remy Slama ◽

Joachim Heinrich ◽

Magnus Wickman ◽

...

Keyword(s):

Pulmonary Function ◽

Pulmonary Function Tests ◽

Birth Cohorts ◽

Function Tests

Download Full-text

Pulmonary Function Tests Fail to Predict Exercise Intolerance in Sheep with Emphysema

Medicine & Science in Sports & Exercise ◽

10.1249/01.mss.0000158992.87523.c4 ◽

2005 ◽

Vol 37 (4) ◽

pp. 550-556

Author(s):

MELISSA R. MAZAN ◽

EDWARD P. INGENITO ◽

LARRY TSAI ◽

ANDREW HOFFMAN

Keyword(s):

Pulmonary Function ◽

Pulmonary Function Tests ◽

Exercise Intolerance ◽

Function Tests

Download Full-text

ISOLATED ABNORMALITIES OF DIFFUSION CAPACITY (DLCO) IN PULMONARY FUNCTION TESTS AMONG INNER CITY PATIENTS

CHEST Journal ◽

10.1378/chest.134.4_meetingabstracts.s49004 ◽

2008 ◽

Vol 134 (4) ◽

pp. 49S

Author(s):

Ibrahim H. Abou Daya ◽

Muhammad U. Anwer ◽

Gilda Diaz-Fuentes ◽

Steve Blum ◽

Latha Menon

Keyword(s):

Pulmonary Function ◽

Inner City ◽

Pulmonary Function Tests ◽

Diffusion Capacity ◽

Function Tests

Download Full-text

Shrinking lung syndrome in pediatric systemic lupus erythematosus

Lupus ◽

10.1177/09612033211010331 ◽

2021 ◽

pp. 096120332110103

Author(s):

Alfonso Ragnar Torres Jimenez ◽

Nayma Ruiz Vela ◽

Adriana Ivonne Cespedes Cruz ◽

Alejandra Velazquez Cruz ◽

Alma Karina Bernardino Gonzalez

Keyword(s):

Systemic Lupus Erythematosus ◽

Pleural Effusion ◽

Pulmonary Function ◽

Lupus Erythematosus ◽

Pulmonary Function Tests ◽

Age At Diagnosis ◽

X Rays ◽

Systemic Lupus ◽

Function Tests ◽

Restrictive Pattern

Shrinking Lung Syndrome (SLS) is a rare and little known complication associated with Systemic Lupus Erythematosus (SLE), characterized by progressive and unexplainable dyspnea, pleuritic pain, small pulmonary volumes and elevation of the diaphragm on chest X-rays as well as restrictive pattern on pulmonary function tests. Objective To describe clinical, radiological and treatment characteristics in pediatric patients with SLS. Material and methods This is a descriptive and retrospective study in patients under 16 years old with the diagnosis of SLE complicated by SLS at the General Hospital. National Medical Center La Raza. Clinical, radiological and treatment variables were analyzed. Results are shown in frequencies and percentages. Results Data from 11 patients, 9 females and 2 males were collected. Mean age at diagnosis of SLS was 12.2 years. Age at diagnosis of SLE was 11.1 years. SLEDAI 17.3. Renal desease 72%, hematological 91%, lymphopenia 63%, mucocutaneous 72%, neurological 9%, arthritis 54%, serositis 91%, fever 81%, secondary antiphospholipid syndrome, low C3 72%, low C4 81%, positive ANA 91%, positive anti-DNA 91%. Regarding clinical manifestations of SLE: cough 81%, dyspnea 91%, hipoxemia 81%, pleuritic pain 71%, average oxygen saturation 83%. Chest X-rays findings: right hemidiaphragm affection 18%, left 63%, bilateral 18%. Elevated hemidiaphragm 91%, atelectasis 18%, pleural effusion 91%, over one third of the cardiac silhouette under the diphragm 36%, bulging diaphragm 45%, 5th. anterior rib that crosses over the diaphragm 91%. M-mode ultrasound: diaphragmatic hypomotility 100%, pleural effusion 63%. Pulmonary function tests: restrictive pattern in 45% of the cases. Treatment was with supplementary oxygen 100%, intubation 18%, antibiotics 100%, steroids 100%, intravenous immunoglobulin 54%, plasmapheresis 18%, cyclophosphamide 54% and rituximab 18%. The clinical course was favorable in 81%. Conclusions SLS should be suspected in patients with SLE and active disease who present hipoxemia, pleuritic pain, cough, dyspnea, pleural effusion and signs of restriction on chest X-rays. Therefore, a diaphragmatic M-mode ultrasound should be performed in order to establish the diagnosis.

Download Full-text