1
|
Zakosek M, Bulatovic D, Pavlovic V, Filipovic A, Igic A, Galun D, Jovanovic D, Sisevic J, Masulovic D. Prognostic Nutritional Index (PNI) and Neutrophil to Lymphocyte Ratio (NLR) as Predictors of Short-Term Survival in Patients with Advanced Malignant Biliary Obstruction Treated with Percutaneous Transhepatic Biliary Drainage. J Clin Med 2022; 11:jcm11237055. [PMID: 36498630 PMCID: PMC9741251 DOI: 10.3390/jcm11237055] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/29/2022] [Revised: 11/16/2022] [Accepted: 11/25/2022] [Indexed: 12/02/2022] Open
Abstract
BACKGROUND Effective biliary tree decompression plays a central role in the palliation of malignant biliary obstruction (MBO). When endoscopic drainage is unfeasible or unsuccessful, percutaneous transhepatic biliary drainage (PTBD) is the method of choice and preferred treatment approach in advanced hilar MBO. The prognostic nutritional index (PNI) reflects the patient's immunonutritional status, while the neutrophil to lymphocyte ratio (NLR) reflects the patient's inflammation status. The aim of the present study was to evaluate the prognostic value of preprocedural PNI and NLR on short-term survival in the advanced stage MBO population threatened with PTBD and to characterize the differences in immunonutritional and inflammatory status between 60-day survivors and non-survivors, as well as analyze other variables influencing short-term survival. METHODS This single-center retrospective study was conducted on patients undergoing palliative PTBD caused by MBO as a definitive therapeutic treatment between March 2020 and February 2022. After the procedure, patients were followed until the end of August 2022. RESULTS A total of 136 patients with malignant biliary obstruction were included in the study. Based on receiver operating characteristic (ROC) curve analysis, optimal cut off-values for NLR (3) and PNI (36.7) were determined. In univariate regression analysis, age, absolute neutrophil count, albumin level, NLR ≤ 3, and PNI ≥ 36.7 were significant predictors of 60-day survival. Level of obstruction and PNI ≥ 36.7 were statistically significant independent predictors of 60-day survival in a multivariate regression model. Using PNI ≥ 36.7 as a significant coefficient from the multivariate regression model with the addition of NLR ≤ 3 from univariate analysis, a 60-day survival score was developed. CONCLUSIONS PNI and NLR are easy to calculate from routine blood analysis, which is regularly conducted for cancer patients. As such, they represent easily available, highly reproducible, and inexpensive tests capable of expressing the severity of systemic inflammatory responses in patients with cancer. Our study highlights that preprocedural PNI and NLR values provide predictors of short-term survival in patients with MBO treated with palliative PTBD. In addition, the proposed 60-day survival score can contribute to better selection of future candidates for PTBD and recognition of high-risk patients with expected poor outcomes.
Collapse
Affiliation(s)
- Milos Zakosek
- Center for Radiology, University Clinical Center of Serbia, 11000 Belgrade, Serbia
| | - Dusan Bulatovic
- Center for Radiology, University Clinical Center of Serbia, 11000 Belgrade, Serbia
- Correspondence:
| | - Vedrana Pavlovic
- Institute of Medical Statistics and Informatics, Faculty of Medicine, University of Belgrade, 11000 Belgrade, Serbia
| | - Aleksandar Filipovic
- Center for Radiology, University Clinical Center of Serbia, 11000 Belgrade, Serbia
- Faculty of Medicine, University of Belgrade, 11000 Belgrade, Serbia
| | - Aleksa Igic
- Center for Radiology, University Clinical Center of Serbia, 11000 Belgrade, Serbia
| | - Danijel Galun
- Faculty of Medicine, University of Belgrade, 11000 Belgrade, Serbia
- HPB Unit, Clinic for Digestive Surgery, University Clinical Center of Serbia, 11000 Belgrade, Serbia
| | - Darko Jovanovic
- Clinic of Urology, University Clinical Center of Serbia, 11000 Belgrade, Serbia
| | - Jelena Sisevic
- Center for Radiology, University Clinical Center of Serbia, 11000 Belgrade, Serbia
| | - Dragan Masulovic
- Center for Radiology, University Clinical Center of Serbia, 11000 Belgrade, Serbia
- Faculty of Medicine, University of Belgrade, 11000 Belgrade, Serbia
| |
Collapse
|
2
|
Dhiman P, Ma J, Andaur Navarro CL, Speich B, Bullock G, Damen JAA, Hooft L, Kirtley S, Riley RD, Van Calster B, Moons KGM, Collins GS. Methodological conduct of prognostic prediction models developed using machine learning in oncology: a systematic review. BMC Med Res Methodol 2022; 22:101. [PMID: 35395724 PMCID: PMC8991704 DOI: 10.1186/s12874-022-01577-x] [Citation(s) in RCA: 34] [Impact Index Per Article: 17.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/21/2021] [Accepted: 03/18/2022] [Indexed: 12/13/2022] Open
Abstract
BACKGROUND Describe and evaluate the methodological conduct of prognostic prediction models developed using machine learning methods in oncology. METHODS We conducted a systematic review in MEDLINE and Embase between 01/01/2019 and 05/09/2019, for studies developing a prognostic prediction model using machine learning methods in oncology. We used the Transparent Reporting of a multivariable prediction model for Individual Prognosis Or Diagnosis (TRIPOD) statement, Prediction model Risk Of Bias ASsessment Tool (PROBAST) and CHecklist for critical Appraisal and data extraction for systematic Reviews of prediction Modelling Studies (CHARMS) to assess the methodological conduct of included publications. Results were summarised by modelling type: regression-, non-regression-based and ensemble machine learning models. RESULTS Sixty-two publications met inclusion criteria developing 152 models across all publications. Forty-two models were regression-based, 71 were non-regression-based and 39 were ensemble models. A median of 647 individuals (IQR: 203 to 4059) and 195 events (IQR: 38 to 1269) were used for model development, and 553 individuals (IQR: 69 to 3069) and 50 events (IQR: 17.5 to 326.5) for model validation. A higher number of events per predictor was used for developing regression-based models (median: 8, IQR: 7.1 to 23.5), compared to alternative machine learning (median: 3.4, IQR: 1.1 to 19.1) and ensemble models (median: 1.7, IQR: 1.1 to 6). Sample size was rarely justified (n = 5/62; 8%). Some or all continuous predictors were categorised before modelling in 24 studies (39%). 46% (n = 24/62) of models reporting predictor selection before modelling used univariable analyses, and common method across all modelling types. Ten out of 24 models for time-to-event outcomes accounted for censoring (42%). A split sample approach was the most popular method for internal validation (n = 25/62, 40%). Calibration was reported in 11 studies. Less than half of models were reported or made available. CONCLUSIONS The methodological conduct of machine learning based clinical prediction models is poor. Guidance is urgently needed, with increased awareness and education of minimum prediction modelling standards. Particular focus is needed on sample size estimation, development and validation analysis methods, and ensuring the model is available for independent validation, to improve quality of machine learning based clinical prediction models.
Collapse
Affiliation(s)
- Paula Dhiman
- Centre for Statistics in Medicine, Nuffield Department of Orthopaedics, Rheumatology and Musculoskeletal Sciences, University of Oxford, Oxford, OX3 7LD, UK.
- NIHR Oxford Biomedical Research Centre, Oxford University Hospitals NHS Foundation Trust, Oxford, UK.
| | - Jie Ma
- Centre for Statistics in Medicine, Nuffield Department of Orthopaedics, Rheumatology and Musculoskeletal Sciences, University of Oxford, Oxford, OX3 7LD, UK
| | - Constanza L Andaur Navarro
- Julius Center for Health Sciences and Primary Care, University Medical Center Utrecht, Utrecht University, Utrecht, The Netherlands
- Cochrane Netherlands, University Medical Center Utrecht, Utrecht University, Utrecht, The Netherlands
| | - Benjamin Speich
- Centre for Statistics in Medicine, Nuffield Department of Orthopaedics, Rheumatology and Musculoskeletal Sciences, University of Oxford, Oxford, OX3 7LD, UK
- Basel Institute for Clinical Epidemiology and Biostatistics, Department of Clinical Research, University Hospital Basel, University of Basel, Basel, Switzerland
| | - Garrett Bullock
- Nuffield Department of Orthopaedics, Rheumatology, and Musculoskeletal Sciences, University of Oxford, Oxford, UK
| | - Johanna A A Damen
- Julius Center for Health Sciences and Primary Care, University Medical Center Utrecht, Utrecht University, Utrecht, The Netherlands
- Cochrane Netherlands, University Medical Center Utrecht, Utrecht University, Utrecht, The Netherlands
| | - Lotty Hooft
- Julius Center for Health Sciences and Primary Care, University Medical Center Utrecht, Utrecht University, Utrecht, The Netherlands
- Cochrane Netherlands, University Medical Center Utrecht, Utrecht University, Utrecht, The Netherlands
| | - Shona Kirtley
- Centre for Statistics in Medicine, Nuffield Department of Orthopaedics, Rheumatology and Musculoskeletal Sciences, University of Oxford, Oxford, OX3 7LD, UK
| | - Richard D Riley
- Centre for Prognosis Research, School of Medicine, Keele University, Staffordshire, ST5 5BG, UK
| | - Ben Van Calster
- Department of Development and Regeneration, KU Leuven, Leuven, Belgium
- Department of Biomedical Data Sciences, Leiden University Medical Center, Leiden, the Netherlands
- EPI-centre, KU Leuven, Leuven, Belgium
| | - Karel G M Moons
- Julius Center for Health Sciences and Primary Care, University Medical Center Utrecht, Utrecht University, Utrecht, The Netherlands
- Cochrane Netherlands, University Medical Center Utrecht, Utrecht University, Utrecht, The Netherlands
| | - Gary S Collins
- Centre for Statistics in Medicine, Nuffield Department of Orthopaedics, Rheumatology and Musculoskeletal Sciences, University of Oxford, Oxford, OX3 7LD, UK
- NIHR Oxford Biomedical Research Centre, Oxford University Hospitals NHS Foundation Trust, Oxford, UK
| |
Collapse
|
3
|
Zhang JX, Ding Y, Yan HT, Zhou CG, Liu J, Liu S, Zu QQ, Shi HB. Skeletal-muscle index predicts survival after percutaneous transhepatic biliary drainage for obstructive jaundice due to perihilar cholangiocarcinoma. Surg Endosc 2020; 35:6073-6080. [PMID: 33090316 DOI: 10.1007/s00464-020-08099-x] [Citation(s) in RCA: 12] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/31/2020] [Accepted: 10/15/2020] [Indexed: 12/12/2022]
Abstract
BACKGROUND Sarcopenia is emerging as a prognostic factor in patients with malignant diseases. The prognostication of perihilar cholangiocarcinoma (PHC) with obstructive jaundice was complex, because these patients suffered compete mortality events beyond cancer itself. Our study was to investigate the association between low skeletal-muscle index and overall survival (OS) after percutaneous transhepatic biliary drainage (PTBD) for obstructive jaundice due to PHC. METHODS We performed a retrospective survival analysis of patients undergoing PTBD for PHC-related obstructive jaundice between January 2016 and March 2019. Using computed tomography, we measured skeletal-muscle mass at the third lumbar vertebra (L3) to obtain a skeletal-muscle index (SMI). Then, we compared OS between low- and high-SMI groups. Furthermore, factors that could potentially affect OS were assessed. RESULTS One hundred and four patients (56 males; mean age 66 ± 12 years) were analyzed. Median OS after PTBD was 150 days. OS was shorter in patients with low SMI than in those with high SMI (median OS, 120 vs. 270 days; P < 0.001). Multivariate analysis indicated that low SMI (hazard ratio [HR] 3.46; 95% confidence interval [CI] 1.14-5.60; P < 0.001), intrahepatic metastasis (HR 2.98; 95% CI 1.89-4.69; P < 0.001) and elevated carbohydrate antigen (CA) 19-9 level (HR 1.00; 95% CI 1.00-1.00; P = 0.04) were significantly associated with OS. CONCLUSION Low SMI was a predictor of dismal OS after PTBD for patients with PHC-related obstructive jaundice.
Collapse
Affiliation(s)
- Jin-Xing Zhang
- Department of Interventional Radiology, The First Affiliated Hospital With Nanjing Medical University, No. 300 Guangzhou Road, Nanjing, 210029, China
| | - Ye Ding
- Department of Maternal, Child and Adolescent Health, School of Public Health, Nanjing Medical University, Nanjing, 211166, China
| | - Hai-Tao Yan
- Department of Interventional Radiology, The First Affiliated Hospital With Nanjing Medical University, No. 300 Guangzhou Road, Nanjing, 210029, China
| | - Chun-Gao Zhou
- Department of Interventional Radiology, The First Affiliated Hospital With Nanjing Medical University, No. 300 Guangzhou Road, Nanjing, 210029, China
| | - Jin Liu
- Department of Clinical Medicine Research Institution, The First Affiliated Hospital With Nanjing Medical University, Nanjing, 210029, China
| | - Sheng Liu
- Department of Interventional Radiology, The First Affiliated Hospital With Nanjing Medical University, No. 300 Guangzhou Road, Nanjing, 210029, China
| | - Qing-Quan Zu
- Department of Interventional Radiology, The First Affiliated Hospital With Nanjing Medical University, No. 300 Guangzhou Road, Nanjing, 210029, China.
| | - Hai-Bin Shi
- Department of Interventional Radiology, The First Affiliated Hospital With Nanjing Medical University, No. 300 Guangzhou Road, Nanjing, 210029, China.
| |
Collapse
|