Optimizing the Capabilities of Gaussian Process Models for Pulmonary Effusion Prediction Analysis

R. Kavitha; Preeti Naval; Murli Manohar Gour; Manish Kaushik

doi:10.1007/978-981-97-8043-3_111

Optimizing the Capabilities of Gaussian Process Models for Pulmonary Effusion Prediction Analysis

R. Kavitha
, Preeti Naval
, Murli Manohar Gour
, Manish Kaushik

Research output: Chapter in Book/Report › Conference contribution › peer-review

Abstract

Gaussian method fashions (GPMs) are typically used to investigate complex physiologic statistics for the cause of identifying patterns and predicting outcomes of disorder states. In this study, 14-day pre-operative facts from 73 patients with white-blood-cellular-negative spontaneous pleural effusions were used to optimize the capacity of GPMs to predict postoperative pulmonary effusion formation. The statistics contained scientific measures (pre-operative temperature, albumin degrees, radiographic features (pleural flocculation, and so on.), and echocardiography measures (right atria length, etc.) as input variables for the GPMs. Through optimization of hyper parameters, pre-processing techniques, and characteristic choice algorithms, the performance of the GPMs was advanced drastically, with an AUC price that passed 0.95.

Original language	American English
Title of host publication	Proceedings of the 5th International Conference on Data Science, Machine Learning and Applications - ICDSMLA 2023
Editors	Amit Kumar, Vinit Kumar Gunjan, Sabrina Senatore, Yu-Chen Hu
Publisher	Springer Science and Business Media Deutschland GmbH
Pages	711-716
Number of pages	6
ISBN (Print)	9789819780426
DOIs	https://doi.org/10.1007/978-981-97-8043-3_111
State	Indexed - 2025
Externally published	Yes
Event	5th International Conference on Data Science, Machine Learning and Applications, ICDSMLA 2023 - Hyderabad, India Duration: 15 Dec 2023 → 16 Dec 2023

Publication series

Name	Lecture Notes in Electrical Engineering
Volume	1274 LNEE
ISSN (Print)	1876-1100
ISSN (Electronic)	1876-1119

Conference

Conference	5th International Conference on Data Science, Machine Learning and Applications, ICDSMLA 2023
Country/Territory	India
City	Hyderabad
Period	15/12/23 → 16/12/23

Bibliographical note

Publisher Copyright:
© The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

Keywords

Demonstrates
Gaussian
Hyper Parameters
Postoperative
Procedure

Access to Document

10.1007/978-981-97-8043-3_111

Cite this

Kavitha, R., Naval, P., Gour, M. M., & Kaushik, M. (2025). Optimizing the Capabilities of Gaussian Process Models for Pulmonary Effusion Prediction Analysis. In A. Kumar, V. K. Gunjan, S. Senatore, & Y.-C. Hu (Eds.), Proceedings of the 5th International Conference on Data Science, Machine Learning and Applications - ICDSMLA 2023 (pp. 711-716). (Lecture Notes in Electrical Engineering; Vol. 1274 LNEE). Springer Science and Business Media Deutschland GmbH. https://doi.org/10.1007/978-981-97-8043-3_111

Kavitha, R. ; Naval, Preeti ; Gour, Murli Manohar et al. / Optimizing the Capabilities of Gaussian Process Models for Pulmonary Effusion Prediction Analysis. Proceedings of the 5th International Conference on Data Science, Machine Learning and Applications - ICDSMLA 2023. editor / Amit Kumar ; Vinit Kumar Gunjan ; Sabrina Senatore ; Yu-Chen Hu. Springer Science and Business Media Deutschland GmbH, 2025. pp. 711-716 (Lecture Notes in Electrical Engineering).

@inproceedings{e2d01a73691a4f4a8e1d582e85efa883,

title = "Optimizing the Capabilities of Gaussian Process Models for Pulmonary Effusion Prediction Analysis",

abstract = "Gaussian method fashions (GPMs) are typically used to investigate complex physiologic statistics for the cause of identifying patterns and predicting outcomes of disorder states. In this study, 14-day pre-operative facts from 73 patients with white-blood-cellular-negative spontaneous pleural effusions were used to optimize the capacity of GPMs to predict postoperative pulmonary effusion formation. The statistics contained scientific measures (pre-operative temperature, albumin degrees, radiographic features (pleural flocculation, and so on.), and echocardiography measures (right atria length, etc.) as input variables for the GPMs. Through optimization of hyper parameters, pre-processing techniques, and characteristic choice algorithms, the performance of the GPMs was advanced drastically, with an AUC price that passed 0.95.",

keywords = "Demonstrates, Gaussian, Hyper Parameters, Postoperative, Procedure",

author = "R. Kavitha and Preeti Naval and Gour, \{Murli Manohar\} and Manish Kaushik",

note = "Publisher Copyright: {\textcopyright} The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.; 5th International Conference on Data Science, Machine Learning and Applications, ICDSMLA 2023 ; Conference date: 15-12-2023 Through 16-12-2023",

year = "2025",

doi = "10.1007/978-981-97-8043-3\_111",

language = "American English",

isbn = "9789819780426",

series = "Lecture Notes in Electrical Engineering",

publisher = "Springer Science and Business Media Deutschland GmbH",

pages = "711--716",

editor = "Amit Kumar and Gunjan, \{Vinit Kumar\} and Sabrina Senatore and Yu-Chen Hu",

booktitle = "Proceedings of the 5th International Conference on Data Science, Machine Learning and Applications - ICDSMLA 2023",

address = "Germany",

}

Kavitha, R, Naval, P, Gour, MM & Kaushik, M 2025, Optimizing the Capabilities of Gaussian Process Models for Pulmonary Effusion Prediction Analysis. in A Kumar, VK Gunjan, S Senatore & Y-C Hu (eds), Proceedings of the 5th International Conference on Data Science, Machine Learning and Applications - ICDSMLA 2023. Lecture Notes in Electrical Engineering, vol. 1274 LNEE, Springer Science and Business Media Deutschland GmbH, pp. 711-716, 5th International Conference on Data Science, Machine Learning and Applications, ICDSMLA 2023, Hyderabad, India, 15/12/23. https://doi.org/10.1007/978-981-97-8043-3_111

Optimizing the Capabilities of Gaussian Process Models for Pulmonary Effusion Prediction Analysis. / Kavitha, R.; Naval, Preeti; Gour, Murli Manohar et al.
Proceedings of the 5th International Conference on Data Science, Machine Learning and Applications - ICDSMLA 2023. ed. / Amit Kumar; Vinit Kumar Gunjan; Sabrina Senatore; Yu-Chen Hu. Springer Science and Business Media Deutschland GmbH, 2025. p. 711-716 (Lecture Notes in Electrical Engineering; Vol. 1274 LNEE).

Research output: Chapter in Book/Report › Conference contribution › peer-review

TY - GEN

T1 - Optimizing the Capabilities of Gaussian Process Models for Pulmonary Effusion Prediction Analysis

AU - Kavitha, R.

AU - Naval, Preeti

AU - Gour, Murli Manohar

AU - Kaushik, Manish

N1 - Publisher Copyright: © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

PY - 2025

Y1 - 2025

N2 - Gaussian method fashions (GPMs) are typically used to investigate complex physiologic statistics for the cause of identifying patterns and predicting outcomes of disorder states. In this study, 14-day pre-operative facts from 73 patients with white-blood-cellular-negative spontaneous pleural effusions were used to optimize the capacity of GPMs to predict postoperative pulmonary effusion formation. The statistics contained scientific measures (pre-operative temperature, albumin degrees, radiographic features (pleural flocculation, and so on.), and echocardiography measures (right atria length, etc.) as input variables for the GPMs. Through optimization of hyper parameters, pre-processing techniques, and characteristic choice algorithms, the performance of the GPMs was advanced drastically, with an AUC price that passed 0.95.

AB - Gaussian method fashions (GPMs) are typically used to investigate complex physiologic statistics for the cause of identifying patterns and predicting outcomes of disorder states. In this study, 14-day pre-operative facts from 73 patients with white-blood-cellular-negative spontaneous pleural effusions were used to optimize the capacity of GPMs to predict postoperative pulmonary effusion formation. The statistics contained scientific measures (pre-operative temperature, albumin degrees, radiographic features (pleural flocculation, and so on.), and echocardiography measures (right atria length, etc.) as input variables for the GPMs. Through optimization of hyper parameters, pre-processing techniques, and characteristic choice algorithms, the performance of the GPMs was advanced drastically, with an AUC price that passed 0.95.

KW - Demonstrates

KW - Gaussian

KW - Hyper Parameters

KW - Postoperative

KW - Procedure

UR - https://www.scopus.com/pages/publications/85208194076

U2 - 10.1007/978-981-97-8043-3_111

DO - 10.1007/978-981-97-8043-3_111

M3 - Conference contribution

AN - SCOPUS:85208194076

SN - 9789819780426

T3 - Lecture Notes in Electrical Engineering

SP - 711

EP - 716

BT - Proceedings of the 5th International Conference on Data Science, Machine Learning and Applications - ICDSMLA 2023

A2 - Kumar, Amit

A2 - Gunjan, Vinit Kumar

A2 - Senatore, Sabrina

A2 - Hu, Yu-Chen

PB - Springer Science and Business Media Deutschland GmbH

T2 - 5th International Conference on Data Science, Machine Learning and Applications, ICDSMLA 2023

Y2 - 15 December 2023 through 16 December 2023

ER -

Kavitha R, Naval P, Gour MM, Kaushik M. Optimizing the Capabilities of Gaussian Process Models for Pulmonary Effusion Prediction Analysis. In Kumar A, Gunjan VK, Senatore S, Hu YC, editors, Proceedings of the 5th International Conference on Data Science, Machine Learning and Applications - ICDSMLA 2023. Springer Science and Business Media Deutschland GmbH. 2025. p. 711-716. (Lecture Notes in Electrical Engineering). doi: 10.1007/978-981-97-8043-3_111

Optimizing the Capabilities of Gaussian Process Models for Pulmonary Effusion Prediction Analysis

Abstract

Publication series

Conference

Bibliographical note

Keywords

Access to Document

Fingerprint

Cite this