Urine based near-infrared spectroscopy analysis reveals a noninvasive and convenient diagnosis method for cancers: a pilot study
Background The challenges in cancer diagnosis underline the need for continued research and development of new diagnostic tools and methods. This study aims to explore an effective, noninvasive, and convenient diagnostic tool using urine based near-infrared spectroscopy (NIRS) analysis combined with...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
PeerJ Inc.
2023-08-01
|
| Series: | PeerJ |
| Subjects: | |
| Online Access: | https://peerj.com/articles/15895.pdf |
| _version_ | 1797424969234251776 |
|---|---|
| author | Jing Zhu Siyu Zhang Ruting Wang Ruhua Fang Lan Lei Ji Zheng Zhongjian Chen |
| author_facet | Jing Zhu Siyu Zhang Ruting Wang Ruhua Fang Lan Lei Ji Zheng Zhongjian Chen |
| author_sort | Jing Zhu |
| collection | DOAJ |
| description | Background The challenges in cancer diagnosis underline the need for continued research and development of new diagnostic tools and methods. This study aims to explore an effective, noninvasive, and convenient diagnostic tool using urine based near-infrared spectroscopy (NIRS) analysis combined with machine learning algorithm. Methods Urine samples were collected from a total of 327 participants, including 181 cancer cases and 146 healthy controls. These participants were randomly spit into train set (n = 218) and test set (n = 109). NIRS analysis (4,000 ∼10,000 cm−1) was performed for each sample in both train and test sets. Five pretreatment methods, including Savitzky-Golay (SG) smoothing, multiplicative scatter correction (MSC), baseline removal (BSL) with fitting polynomials to be used as baselines, the first derivative (DERIV1), and the second derivative (DERIV2), and combination with “scaling” and “center”, were investigated. Then partial least-squares (PLS) and linear support-vector machine (SVM) classification models were established, and prediction performance was evaluated in test set. Results NIRS had greatly overlapping in peaks, and PCA analysis failed in separation between cancers and healthy controls. In modeling with urine based NIRS data, PLS model showed its highest prediction accuracy of 0.780, with DERIV2, “scaling” and “center” pretreatment, while linear SVM displayed its best prediction accuracy of 0.844, with raw NIRS. With optimization in SVM, the prediction accuracy could improve to 0.862, when the top 262 features were involved as variables. Discussion This pilot study combining urine based NIRS analysis and machine learning is effective and convenient that might facilitate in cancer diagnosis, encouraging further evaluation with a large-size multi-center study. |
| first_indexed | 2024-03-09T08:09:15Z |
| format | Article |
| id | doaj.art-25e15d90e952481db88038046524f779 |
| institution | Directory Open Access Journal |
| issn | 2167-8359 |
| language | English |
| last_indexed | 2024-03-09T08:09:15Z |
| publishDate | 2023-08-01 |
| publisher | PeerJ Inc. |
| record_format | Article |
| series | PeerJ |
| spelling | doaj.art-25e15d90e952481db88038046524f7792023-12-02T23:31:01ZengPeerJ Inc.PeerJ2167-83592023-08-0111e1589510.7717/peerj.15895Urine based near-infrared spectroscopy analysis reveals a noninvasive and convenient diagnosis method for cancers: a pilot studyJing Zhu0Siyu Zhang1Ruting Wang2Ruhua Fang3Lan Lei4Ji Zheng5Zhongjian Chen6Department of Clinical Laboratory, Zhejiang Cancer Hospital, Hangzhou, Zhejiang, ChinaDepartment of Clinical Pharmacy, The First Affiliated Hospital, Zhejiang University School of Medicine, Hangzhou, Zhejiang, ChinaExperimental Research Center, Zhejiang Cancer Hospital, Hangzhou, Zhejiang, ChinaDepartment of Clinical Laboratory, Zhejiang Cancer Hospital, Hangzhou, Zhejiang, ChinaZhejiang Hospital, Hangzhou, Zhejiang, ChinaDepartment of Radiotherapy and Chemotherapy, Ningbo No. 2 Hospital, Ningbo, Zhejiang, ChinaExperimental Research Center, Zhejiang Cancer Hospital, Hangzhou, Zhejiang, ChinaBackground The challenges in cancer diagnosis underline the need for continued research and development of new diagnostic tools and methods. This study aims to explore an effective, noninvasive, and convenient diagnostic tool using urine based near-infrared spectroscopy (NIRS) analysis combined with machine learning algorithm. Methods Urine samples were collected from a total of 327 participants, including 181 cancer cases and 146 healthy controls. These participants were randomly spit into train set (n = 218) and test set (n = 109). NIRS analysis (4,000 ∼10,000 cm−1) was performed for each sample in both train and test sets. Five pretreatment methods, including Savitzky-Golay (SG) smoothing, multiplicative scatter correction (MSC), baseline removal (BSL) with fitting polynomials to be used as baselines, the first derivative (DERIV1), and the second derivative (DERIV2), and combination with “scaling” and “center”, were investigated. Then partial least-squares (PLS) and linear support-vector machine (SVM) classification models were established, and prediction performance was evaluated in test set. Results NIRS had greatly overlapping in peaks, and PCA analysis failed in separation between cancers and healthy controls. In modeling with urine based NIRS data, PLS model showed its highest prediction accuracy of 0.780, with DERIV2, “scaling” and “center” pretreatment, while linear SVM displayed its best prediction accuracy of 0.844, with raw NIRS. With optimization in SVM, the prediction accuracy could improve to 0.862, when the top 262 features were involved as variables. Discussion This pilot study combining urine based NIRS analysis and machine learning is effective and convenient that might facilitate in cancer diagnosis, encouraging further evaluation with a large-size multi-center study.https://peerj.com/articles/15895.pdfMachine learningDiagnosisUrineNear-infrared spectroscopyPartial least-squares (PLS)Support-vector machine (SVM) |
| spellingShingle | Jing Zhu Siyu Zhang Ruting Wang Ruhua Fang Lan Lei Ji Zheng Zhongjian Chen Urine based near-infrared spectroscopy analysis reveals a noninvasive and convenient diagnosis method for cancers: a pilot study PeerJ Machine learning Diagnosis Urine Near-infrared spectroscopy Partial least-squares (PLS) Support-vector machine (SVM) |
| title | Urine based near-infrared spectroscopy analysis reveals a noninvasive and convenient diagnosis method for cancers: a pilot study |
| title_full | Urine based near-infrared spectroscopy analysis reveals a noninvasive and convenient diagnosis method for cancers: a pilot study |
| title_fullStr | Urine based near-infrared spectroscopy analysis reveals a noninvasive and convenient diagnosis method for cancers: a pilot study |
| title_full_unstemmed | Urine based near-infrared spectroscopy analysis reveals a noninvasive and convenient diagnosis method for cancers: a pilot study |
| title_short | Urine based near-infrared spectroscopy analysis reveals a noninvasive and convenient diagnosis method for cancers: a pilot study |
| title_sort | urine based near infrared spectroscopy analysis reveals a noninvasive and convenient diagnosis method for cancers a pilot study |
| topic | Machine learning Diagnosis Urine Near-infrared spectroscopy Partial least-squares (PLS) Support-vector machine (SVM) |
| url | https://peerj.com/articles/15895.pdf |
| work_keys_str_mv | AT jingzhu urinebasednearinfraredspectroscopyanalysisrevealsanoninvasiveandconvenientdiagnosismethodforcancersapilotstudy AT siyuzhang urinebasednearinfraredspectroscopyanalysisrevealsanoninvasiveandconvenientdiagnosismethodforcancersapilotstudy AT rutingwang urinebasednearinfraredspectroscopyanalysisrevealsanoninvasiveandconvenientdiagnosismethodforcancersapilotstudy AT ruhuafang urinebasednearinfraredspectroscopyanalysisrevealsanoninvasiveandconvenientdiagnosismethodforcancersapilotstudy AT lanlei urinebasednearinfraredspectroscopyanalysisrevealsanoninvasiveandconvenientdiagnosismethodforcancersapilotstudy AT jizheng urinebasednearinfraredspectroscopyanalysisrevealsanoninvasiveandconvenientdiagnosismethodforcancersapilotstudy AT zhongjianchen urinebasednearinfraredspectroscopyanalysisrevealsanoninvasiveandconvenientdiagnosismethodforcancersapilotstudy |