Machine learning-based identification of colorectal advanced adenoma using clinical and laboratory data: a phase I exploratory study in accordance with updated World Endoscopy Organization guidelines for noninvasive colorectal cancer screening tests
ObjectiveThe recent World Endoscopy Organization (WEO) guidelines now recognize precursor lesions of colorectal cancer (CRC) as legitimate screening targets. However, an optimal screening method for detecting advanced adenoma (AA), a significant precursor lesion, remains elusive.MethodsWe employed f...
| Main Authors: | , , , , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2024-02-01
|
| Series: | Frontiers in Oncology |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fonc.2024.1325514/full |
| _version_ | 1827344756033716224 |
|---|---|
| author | Huijie Wang Xu Cao Ping Meng Caihua Zheng Jinli Liu Yong Liu Tianpeng Zhang Xiaofang Li Xiaoyang Shi Xiaoxing Sun Teng Zhang Haiying Zuo Zhichao Wang Xin Fu Huan Li Huanwei Zheng |
| author_facet | Huijie Wang Xu Cao Ping Meng Caihua Zheng Jinli Liu Yong Liu Tianpeng Zhang Xiaofang Li Xiaoyang Shi Xiaoxing Sun Teng Zhang Haiying Zuo Zhichao Wang Xin Fu Huan Li Huanwei Zheng |
| author_sort | Huijie Wang |
| collection | DOAJ |
| description | ObjectiveThe recent World Endoscopy Organization (WEO) guidelines now recognize precursor lesions of colorectal cancer (CRC) as legitimate screening targets. However, an optimal screening method for detecting advanced adenoma (AA), a significant precursor lesion, remains elusive.MethodsWe employed five machine learning methods, using clinical and laboratory data, to develop and validate a diagnostic model for identifying patients with AA (569 AAs vs. 3228 controls with normal colonoscopy). The best-performing model was selected based on sensitivity and specificity assessments. Its performance in recognizing adenoma-carcinoma sequence was evaluated in line with guidelines, and adjustable thresholds were established. For comparison, the Fecal Occult Blood Test (FOBT) was also selected.ResultsThe XGBoost model demonstrated superior performance in identifying AA, with a sensitivity of 70.8% and a specificity of 83.4%. It successfully detected 42.7% of non-advanced adenoma (NAA) and 80.1% of CRC. The model-transformed risk assessment scale provided diagnostic performance at different positivity thresholds. Compared to FOBT, the XGBoost model better identified AA and NAA, however, was less effective in CRC.ConclusionThe XGBoost model, compared to FOBT, offers improved accuracy in identifying AA patients. While it may not meet the recommendations of some organizations, it provides value for individuals who are unable to use FOBT for various reasons. |
| first_indexed | 2024-03-07T22:51:07Z |
| format | Article |
| id | doaj.art-1ae17cb4543241f3b67d294982fb15d5 |
| institution | Directory Open Access Journal |
| issn | 2234-943X |
| language | English |
| last_indexed | 2024-03-07T22:51:07Z |
| publishDate | 2024-02-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Oncology |
| spelling | doaj.art-1ae17cb4543241f3b67d294982fb15d52024-02-23T09:25:52ZengFrontiers Media S.A.Frontiers in Oncology2234-943X2024-02-011410.3389/fonc.2024.13255141325514Machine learning-based identification of colorectal advanced adenoma using clinical and laboratory data: a phase I exploratory study in accordance with updated World Endoscopy Organization guidelines for noninvasive colorectal cancer screening testsHuijie Wang0Xu Cao1Ping Meng2Caihua Zheng3Jinli Liu4Yong Liu5Tianpeng Zhang6Xiaofang Li7Xiaoyang Shi8Xiaoxing Sun9Teng Zhang10Haiying Zuo11Zhichao Wang12Xin Fu13Huan Li14Huanwei Zheng15Department of Endoscopy, Shijiazhuang Traditional Chinese Medicine Hospital, Shijiazhuang, ChinaDepartment of Endoscopy, Shijiazhuang Traditional Chinese Medicine Hospital, Shijiazhuang, ChinaDepartment of Gastroenterology, Shijiazhuang Traditional Chinese Medicine Hospital, Shijiazhuang, ChinaDepartment of Gastroenterology, Shijiazhuang Traditional Chinese Medicine Hospital, Shijiazhuang, ChinaDepartment of Gastroenterology, Shijiazhuang Traditional Chinese Medicine Hospital, Shijiazhuang, ChinaDepartment of Endoscopy, Shijiazhuang Traditional Chinese Medicine Hospital, Shijiazhuang, ChinaDepartment of Anus & Intestine Surgery, Shijiazhuang Traditional Chinese Medicine Hospital, Shijiazhuang, ChinaDepartment of Endoscopy, Shijiazhuang Traditional Chinese Medicine Hospital, Shijiazhuang, ChinaDepartment of Endoscopy, Shijiazhuang Traditional Chinese Medicine Hospital, Shijiazhuang, ChinaDepartment of Endoscopy, Shijiazhuang Traditional Chinese Medicine Hospital, Shijiazhuang, ChinaInstitute of Traditional Chinese Medicine, North China University of Science and Technology, Tangshan, ChinaGraduate School, Hebei North University, Zhangjiakou, ChinaGraduate School, Hebei North University, Zhangjiakou, ChinaResearch and Development Department, Wuhan Metware Biotechnology Co., Ltd, Wuhan, ChinaResearch and Development Department, Wuhan Metware Biotechnology Co., Ltd, Wuhan, ChinaDepartment of Gastroenterology, Shijiazhuang Traditional Chinese Medicine Hospital, Shijiazhuang, ChinaObjectiveThe recent World Endoscopy Organization (WEO) guidelines now recognize precursor lesions of colorectal cancer (CRC) as legitimate screening targets. However, an optimal screening method for detecting advanced adenoma (AA), a significant precursor lesion, remains elusive.MethodsWe employed five machine learning methods, using clinical and laboratory data, to develop and validate a diagnostic model for identifying patients with AA (569 AAs vs. 3228 controls with normal colonoscopy). The best-performing model was selected based on sensitivity and specificity assessments. Its performance in recognizing adenoma-carcinoma sequence was evaluated in line with guidelines, and adjustable thresholds were established. For comparison, the Fecal Occult Blood Test (FOBT) was also selected.ResultsThe XGBoost model demonstrated superior performance in identifying AA, with a sensitivity of 70.8% and a specificity of 83.4%. It successfully detected 42.7% of non-advanced adenoma (NAA) and 80.1% of CRC. The model-transformed risk assessment scale provided diagnostic performance at different positivity thresholds. Compared to FOBT, the XGBoost model better identified AA and NAA, however, was less effective in CRC.ConclusionThe XGBoost model, compared to FOBT, offers improved accuracy in identifying AA patients. While it may not meet the recommendations of some organizations, it provides value for individuals who are unable to use FOBT for various reasons.https://www.frontiersin.org/articles/10.3389/fonc.2024.1325514/fulladvanced colorectal adenomamachine learningnon-invasive testrisk assessmentadjustable thresholds |
| spellingShingle | Huijie Wang Xu Cao Ping Meng Caihua Zheng Jinli Liu Yong Liu Tianpeng Zhang Xiaofang Li Xiaoyang Shi Xiaoxing Sun Teng Zhang Haiying Zuo Zhichao Wang Xin Fu Huan Li Huanwei Zheng Machine learning-based identification of colorectal advanced adenoma using clinical and laboratory data: a phase I exploratory study in accordance with updated World Endoscopy Organization guidelines for noninvasive colorectal cancer screening tests Frontiers in Oncology advanced colorectal adenoma machine learning non-invasive test risk assessment adjustable thresholds |
| title | Machine learning-based identification of colorectal advanced adenoma using clinical and laboratory data: a phase I exploratory study in accordance with updated World Endoscopy Organization guidelines for noninvasive colorectal cancer screening tests |
| title_full | Machine learning-based identification of colorectal advanced adenoma using clinical and laboratory data: a phase I exploratory study in accordance with updated World Endoscopy Organization guidelines for noninvasive colorectal cancer screening tests |
| title_fullStr | Machine learning-based identification of colorectal advanced adenoma using clinical and laboratory data: a phase I exploratory study in accordance with updated World Endoscopy Organization guidelines for noninvasive colorectal cancer screening tests |
| title_full_unstemmed | Machine learning-based identification of colorectal advanced adenoma using clinical and laboratory data: a phase I exploratory study in accordance with updated World Endoscopy Organization guidelines for noninvasive colorectal cancer screening tests |
| title_short | Machine learning-based identification of colorectal advanced adenoma using clinical and laboratory data: a phase I exploratory study in accordance with updated World Endoscopy Organization guidelines for noninvasive colorectal cancer screening tests |
| title_sort | machine learning based identification of colorectal advanced adenoma using clinical and laboratory data a phase i exploratory study in accordance with updated world endoscopy organization guidelines for noninvasive colorectal cancer screening tests |
| topic | advanced colorectal adenoma machine learning non-invasive test risk assessment adjustable thresholds |
| url | https://www.frontiersin.org/articles/10.3389/fonc.2024.1325514/full |
| work_keys_str_mv | AT huijiewang machinelearningbasedidentificationofcolorectaladvancedadenomausingclinicalandlaboratorydataaphaseiexploratorystudyinaccordancewithupdatedworldendoscopyorganizationguidelinesfornoninvasivecolorectalcancerscreeningtests AT xucao machinelearningbasedidentificationofcolorectaladvancedadenomausingclinicalandlaboratorydataaphaseiexploratorystudyinaccordancewithupdatedworldendoscopyorganizationguidelinesfornoninvasivecolorectalcancerscreeningtests AT pingmeng machinelearningbasedidentificationofcolorectaladvancedadenomausingclinicalandlaboratorydataaphaseiexploratorystudyinaccordancewithupdatedworldendoscopyorganizationguidelinesfornoninvasivecolorectalcancerscreeningtests AT caihuazheng machinelearningbasedidentificationofcolorectaladvancedadenomausingclinicalandlaboratorydataaphaseiexploratorystudyinaccordancewithupdatedworldendoscopyorganizationguidelinesfornoninvasivecolorectalcancerscreeningtests AT jinliliu machinelearningbasedidentificationofcolorectaladvancedadenomausingclinicalandlaboratorydataaphaseiexploratorystudyinaccordancewithupdatedworldendoscopyorganizationguidelinesfornoninvasivecolorectalcancerscreeningtests AT yongliu machinelearningbasedidentificationofcolorectaladvancedadenomausingclinicalandlaboratorydataaphaseiexploratorystudyinaccordancewithupdatedworldendoscopyorganizationguidelinesfornoninvasivecolorectalcancerscreeningtests AT tianpengzhang machinelearningbasedidentificationofcolorectaladvancedadenomausingclinicalandlaboratorydataaphaseiexploratorystudyinaccordancewithupdatedworldendoscopyorganizationguidelinesfornoninvasivecolorectalcancerscreeningtests AT xiaofangli machinelearningbasedidentificationofcolorectaladvancedadenomausingclinicalandlaboratorydataaphaseiexploratorystudyinaccordancewithupdatedworldendoscopyorganizationguidelinesfornoninvasivecolorectalcancerscreeningtests AT xiaoyangshi machinelearningbasedidentificationofcolorectaladvancedadenomausingclinicalandlaboratorydataaphaseiexploratorystudyinaccordancewithupdatedworldendoscopyorganizationguidelinesfornoninvasivecolorectalcancerscreeningtests AT xiaoxingsun machinelearningbasedidentificationofcolorectaladvancedadenomausingclinicalandlaboratorydataaphaseiexploratorystudyinaccordancewithupdatedworldendoscopyorganizationguidelinesfornoninvasivecolorectalcancerscreeningtests AT tengzhang machinelearningbasedidentificationofcolorectaladvancedadenomausingclinicalandlaboratorydataaphaseiexploratorystudyinaccordancewithupdatedworldendoscopyorganizationguidelinesfornoninvasivecolorectalcancerscreeningtests AT haiyingzuo machinelearningbasedidentificationofcolorectaladvancedadenomausingclinicalandlaboratorydataaphaseiexploratorystudyinaccordancewithupdatedworldendoscopyorganizationguidelinesfornoninvasivecolorectalcancerscreeningtests AT zhichaowang machinelearningbasedidentificationofcolorectaladvancedadenomausingclinicalandlaboratorydataaphaseiexploratorystudyinaccordancewithupdatedworldendoscopyorganizationguidelinesfornoninvasivecolorectalcancerscreeningtests AT xinfu machinelearningbasedidentificationofcolorectaladvancedadenomausingclinicalandlaboratorydataaphaseiexploratorystudyinaccordancewithupdatedworldendoscopyorganizationguidelinesfornoninvasivecolorectalcancerscreeningtests AT huanli machinelearningbasedidentificationofcolorectaladvancedadenomausingclinicalandlaboratorydataaphaseiexploratorystudyinaccordancewithupdatedworldendoscopyorganizationguidelinesfornoninvasivecolorectalcancerscreeningtests AT huanweizheng machinelearningbasedidentificationofcolorectaladvancedadenomausingclinicalandlaboratorydataaphaseiexploratorystudyinaccordancewithupdatedworldendoscopyorganizationguidelinesfornoninvasivecolorectalcancerscreeningtests |