Diaphragm motion and lung function prediction in patients operated for lung cancer--a pilot study on 27 patients

The role of the diaphragm in prediction of respiratory function in the immediate postoperative period in lung cancer patients using a machine learning model

BACKGROUND

The prediction of postoperative respiratory function is necessary in identifying patients that are at greater risk of complications. There are not enough studies on the effect of the diaphragm on postoperative respiratory function prediction in lung cancer surgical patients. The objective of this study is to estimate the precision of machine learning methods in the prediction of respiratory function in the immediate postoperative period and how diaphragm function contributes to that prediction.

MATERIALS AND METHODS

Our prospective study included 79 patients who underwent lung cancer surgery. Diaphragm function was estimated by its mobility measured both ultrasonographically and radiographically and by noninvasive muscle strength tests. We present a new machine learning multilayer regression metamodel, which predicts FEV1 for each patient based on preoperative measurements.

RESULTS

The proposed regression models are specifically trained to predict FEV1 in the immediate postoperative period and were proved to be highly accurate (mean absolute error in the range from 8 to 11%). Predictive models based on resected segments give two to three times less precise results. Measured FEV1 was 44.68% ± 14.07%, 50.95% ± 15.80%, and 58.0%1 ± 14.78%, and predicted postoperative (ppo) FEV1 was 43.85% ± 8.80%, 50.62% ± 9.28%, and 57.85% ± 10.58% on the first, fourth, and seventh day, respectively. By interpreting the obtained model, the diaphragm contributes to ppoFEV1 13.62% on the first day, 10.52% on the fourth, and 9.06% on the seventh day.

CONCLUSION

The machine learning metamodel gives more accurate predictions of postoperative lung function than traditional calculations. The diaphragm plays a notable role in the postoperative FEV1 prediction.

Evaluation of diaphragm thickening by diaphragm ultrasonography: a reproducibility and a repeatability study

PURPOSE

We have focused on the two-dimensional (B-mode) and the time-motion (M-mode) analysis of the zone of apposition to determine the reliability of diaphragm ultrasonography in the clinical environment.

METHODS

Ten healthy volunteers were enrolled and studied by three operators with different skills in ultrasonography. For every volunteer, each operator acquired three images of the diaphragm for each side, both in B-mode and in M-mode. Then a fourth operator calculated the thickening fraction (TF), by means of the formula TF = (TEI - TEE)/TEE (TEI is the thickness at end inspiration and TEE the thickness at end expiration). Afterwards, intraclass correlation coefficients (ICCs) were computed on TF to establish reproducibility and repeatability both in the B- and M-modes. A Coefficient of Repeatability or repeatability (CR) ≤ 0.3 was considered acceptable.

RESULTS

Both B-mode (CRs 0.16-0.26) and M-mode (CRs 0.10-0.15) were sufficiently repeatable to assess TF, except for the less experienced operator (CRs B-Mode 0.20-0.32). Reproducibility was moderate to good between operators with CRs much narrower for the M-Mode (0.13-0.14).

CONCLUSIONS

The results of our study have shown that diaphragm ultrasound is repeatable and reproducible when carried out by a radiologist or an intensivist with a basic curriculum in ultrasonography. The method is more accurate when using the M-mode for less experienced operators, and in this case, repeatability and reproducibility are not sufficient to make clinical decisions. No TF value lower than 36% was obtained using both techniques. This suggests the existence of a cut-off value that could be used as an initial tool to discriminate healthy subjects from those affected by diaphragmatic dysfunction.

CLINICAL TRIAL REGISTRATION

EUDRACT 2015-004635-12.

Lung ultrasonography as a tool to guide perioperative atelectasis treatment bundle in head and neck cancer patients undergoing free flap reconstructive surgeries: a preliminary observational study

Introduction

General anesthesia causes pulmonary atelectasis within few minutes of induction. This can have significant impact on postoperative outcome of cancer patients undergoing prolonged reconstructive surgeries.

Objective

The purpose of this study was to evaluate the impact of sonographically detected perioperative atelectasis on the need for postoperative oxygen supplementation, bronchodilator therapy and assisted chest physiotherapy in patients undergoing free flap surgeries for head and neck carcinoma.

Methods

Twenty eight head and neck cancer patients underwent bilateral pulmonary ultrasonographic assessments before and after lung surgery. Lung ultrasound scores, serum lactate, and PaO₂/FiO₂ ratio were measured both at the beginning and at end of the surgery. Patients were scanned in the supine position and the number of single and confluent B lines was noted. These values were correlated with the need for oxygen therapy, requirement of bronchodilators and total weaning time to predict the postoperative outcome. Other factors affecting weaning were also studied.

Results

Among twenty eight patients, seven had mean lung ultrasound score of ≥10.5 which correlated with prolonged weaning time (144.56 ± 33.5 min vs. 66.7 ± 15.7 min; p = 0.005). The change in lung ultrasound score significantly correlated with change in PaO₂/FiO₂ ratio (r = −0.56, p = 0.03). Elevated total leukocyte count >8200 μL and serum lactate >2.1 mmoL/L also predicted prolonged postoperative mechanical ventilation.

Conclusion

This preliminary study detected significant levels of perioperative atelectasis using point of care lung ultrasonography in head and neck cancer patients undergoing long duration surgical reconstructions. Higher lung ultrasound scores highlighted the need for frequent bronchodilator nebulizations as well as assisted chest physiotherapy and were associated with delayed weaning. We propose more frequent point of care lung ultrasonographic evaluations and use of recruitment maneuvers to reduce the impact of perioperative pulmonary atelectasis.

Impact of the crural diaphragm thickness on pulmonary function after lobectomy

Objective

The crural diaphragm is responsible for pulmonary ventilation in the early period after lobectomy. However, the role of its thickness in pulmonary ventilation remains unclear. We investigated the impact of crural diaphragm thickness on pulmonary oxygenation and gas exchange early after lobectomy.

Methods

We enrolled 32 patients with non-small-cell lung cancer who underwent video-assisted thoracoscopic lobectomy. Crural diaphragm thickness was defined as the average of the maximum thicknesses of the right and left crural diaphragm at the level of the median arcuate ligament on computed tomography. Pulmonary oxygenation and gas exchange were evaluated by the ratio of arterial oxygen tension/fraction of inspiratory oxygen and alveolar-arterial oxygen difference on the second postoperative day.

Results

Crural diaphragm thickness of 7.0 ± 1.7 mm was associated with vital capacity. After lobectomy, arterial oxygen tension/fraction of inspiratory oxygen decreased significantly and alveolar-arterial oxygen difference increased significantly. Five patients with oxygen saturation via pulse oximetry ≤92% had a lower arterial oxygen tension/fraction of inspiratory oxygen and higher alveolar-arterial oxygen difference than the others. Crural diaphragm thickness in these patients was less than in the others (5.5 ± 1.9 vs. 7.3 ± 1.5 mm, p = 0.033). In multivariate analysis, crural diaphragm thickness remained an independent factor affecting arterial oxygen tension/fraction of inspiratory oxygen and alveolar-arterial oxygen difference ( p = 0.044, p = 0.049). Crural diaphragm thickness was positively associated with arterial oxygen tension/fraction of inspiratory oxygen and negatively associated with alveolar-arterial oxygen difference.

Conclusion

Crural diaphragm thickness affects pulmonary ventilation early after lobectomy.

[Exploring the diaphragm: Ultrasound is essential]

The diaphragm is the muscle most implicated in breathing. Its morphological exploration usually depends on pulmonary radiography, fluoroscopy, CT-scanning and MRI. Its function is evaluated by the classical respiratory functional tests, the measurement of maximum inspiratory and expiratory pressures, the transdiaphragmatic pressure and even an electromyogram. Ultrasound is a technique still insufficiently used in respiratory medicine. It offers, however, many advantages: it is easy to implement, there is no irradiation, it is usable at the bedside, particularly when the patient is immobile or in intensive care. The results of the examination are immediately available. It allows morphological and dynamic study of each hemidiaphragm as well as providing invaluable information on the thoracic and subdiaphragmatic environment. Its field of exploration is extremely wide: raised hemidiaphragm, dyspnea following a stroke or a surgical procedure (thoracic or abdominal), road accident trauma, diagnosis and follow-up of a paresis or paralysis, evaluation of diaphragmatic mobility during the course of COPD (Chronic Obstructive Pulmonary Disease) and many other pathologies. Ultrasound is insufficiently used in pleural disease and even less so in the evaluation of the morphology and function of the diaphragm.