Prediction model of acute kidney injury induced by cisplatin in older adults using a machine learning algorithm

Okawa, Takaya; Mizuno, Tomohiro; Hanabusa, Shogo; Ikeda, Takeshi; Mizokami, Fumihiro; Koseki, Takenao; Takahashi, Kazuo; Tsuboi, Naotake; Yamada, Shigeki; Kameya, Yoshitaka

doi:10.1371/journal.pone.0262021

Cited by 9 publications

(6 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore, we developed and validated a nomogram for risk assessment of AKI that included these biomarkers. Several nomogram models for predicting AKI have been reported in previous studies [25][26][27][28][29]. However, previous studies only focused on the risk assessment of AKI after the first use of cisplatin.…”

Section: Discussionmentioning

confidence: 99%

Acute Kidney Injury after Multiple Cycles of Cisplatin Chemotherapy: A Nomogram for Risk Assessment

Zhu¹,

Li²,

Tang³

et al. 2023

Kidney Blood Press Res

View full text Add to dashboard Cite

Introduction: Acute kidney injury (AKI) caused by cisplatin is common and has a higher incidence of multiple use, resulting in a poor short- and long-term prognosis for patients. There is currently no good premedication AKI risk assessment tool. The aim of this study was to establish an AKI risk assessment nomogram for patients with multiple cisplatin applications. Methods: This study was a retrospective analysis of patients who were treated with non-first-time cisplatin chemotherapy regimen at Changzhou Second People’s Hospital affiliated to Nanjing Medical University from January 2016 to January 2022. All data from the development group were used to screen the impact factors of AKI via univariate and multivariate analyses. A nomogram was developed based on these impact factors and verified with verification group. The area under the curve (AUC) of receiver operating characteristic (ROC) curve, calibration curves, and decision curve analyses (DCAs) were used to evaluate the nomogram. Results: Among the 256 patients enrolled in 450 cycles of chemotherapy, 282 were in the development cohort (97 AKI), and 168 were in the validation cohort (61 AKI). Multivariate logistic regression revealed that age, hypertension, diabetes, serum cystatin C (sCysC), urinary kidney injury molecule-1 (uKim1), and a single dose of cisplatin were independently associated with AKI. The results showed that our model yielded satisfied diagnostic performance with an AUC value of 0.887 and 0.906 using the development group and on verification group. The calibration plots and DCA showed the superior clinical applicability of the nomogram. These results were verified in the validation cohort. Conclusion: A nomogram combining functional (sCysC) and tubular (uKim1) injury biomarkers with conventional clinical factors might assess the risk of AKI after multiple cycles of cisplatin chemotherapy.

show abstract

Section: Discussionmentioning

confidence: 99%

Acute Kidney Injury after Multiple Cycles of Cisplatin Chemotherapy: A Nomogram for Risk Assessment

Zhu¹,

Li²,

Tang³

et al. 2023

Kidney Blood Press Res

View full text Add to dashboard Cite

show abstract

“…Careful use of renal replacement therapy also considered in cases where the patient already has acute kidney injury to prevent high serum peak levels of cisplatin. It is also important to note that severe sodium wasting can also be seen in Cisplatin induced nephrotoxicity [23 ▪ ,24 ▪▪ ,25,26 ▪ ,27,28].…”

Section: Reviewmentioning

confidence: 99%

“…A new trial has been designed to answer the question of whether magnesium supplementation can prevent cisplatin toxicity [23 ▪ ,24 ▪▪ ,25,26 ▪ ,27,28]. The PRAGMATIC trial, showed that magnesium loading attenuates Cisplatin toxicity and increases cumulative cisplatin dose used until AKI was detected [28].…”

Section: Reviewmentioning

confidence: 99%

“…Interestingly, there is a new artificial intelligence (AI) based model to predict who gets acute kidney injury versus who doesn’t. It will take a combination of precision medicine and machine learning efforts to predict who will get Cisplatin nephrotoxicity, versus, for whom it maybe mitigated by hydration, magnesium supplementation, or careful dosing [25]. See Table 1.…”

Section: Reviewmentioning

confidence: 99%

See 1 more Smart Citation

Onconephrology: mitigation of renal injury in chemotherapy administration

Selamet,

Ahdoot,

Salasnek

et al. 2023

Current Opinion in Nephrology &Amp; Hypertension

View full text Add to dashboard Cite

Purpose of review Onconephrology was first coined as a name for the intersection of cancer medicine and nephrology in the early 2010s. It was recognized then that beyond and understanding of kidney physiology, a new generation of nephrologists skilled in both molecular biology and precision medicine were needed to deal with the challenges of emerging cancer therapies. Stem cell transplants, biologic agents, adjuvants blocking basic cellular signaling pathways, immunotherapy were found to promote novel anticancer outcomes, but also to pose new risks to the kidneys. The field rapidly overlapped with emerging expertise in vascular glomerular disease, glomerular disease, and the same biologic agents now applied to auto immune systemic and kidney diseases. Recent findings Many categories of chemotherapeutic agents have been discovered to have adverse renal side effects. In this review, we address classic chemotherapeutic nephrotoxicity and oncologic clinical situations leading to acute kidney injury. We also review the frontiers of nephrotoxicity reported with cell cycle inhibitors, diverse classes of tyrosine kinase inhibitors, immune checkpoint inhibitors, chimeric antigen receptor T-cell therapy, anticancer vaccines, and thrombotic microangiopathies triggered by malignancy and chemotherapy. The aim will be to focus on published strategies to mitigate nephrotoxicity. Summary As onconephrology expands into its own field, it gives birth to new subdisciplines. An understanding that patient populations want the benefits of chemotherapy without the renal (and other) systemic toxicities is emerging. A need to develop a new class of molecular and genetic experts in onconephrology to mitigate nephrotoxicity from chemotherapy is apparent and urgent.

show abstract

“…Cisplatin-induced nephrotoxicity (CIN) is a common side effect affecting 20%-45% of patients, which is also the main limitation for its use [2][3][4] . Chemotherapy itself can cause renal tubular injury, interstitial nephritis, and thrombotic microvascular disease [5] . As cisplatin uptake and excretion are mainly mediated by proximal tubule transporters, its accumulation in renal proximal tubule cells can lead to cell injury [2] .…”

Section: Introductionmentioning

confidence: 99%

Development and Validation of a LASSO Prediction Model for cisplatin induced nephrotoxicity: A Case-Control Study in China

Zhang,

Luo,

Fan

et al. 2023

Preprint

View full text Add to dashboard Cite

Background: Early identification of high-risk individuals with cisplatin-induced nephrotoxicity (CIN) is crucial for avoiding CIN and improving prognosis. In this study, we developed and validated a CIN prediction model based on general clinical data, laboratory indications, and genetic features of lung cancer patients before chemotherapy. Method: We retrospectively included 696 lung cancer patients using platinum chemotherapy regimens from June 2019 to June 2021 as the test set to construct a predictive model using Absolute shrinkage and selection operator (LASSO) regression, cross validation, and Akaike's information criterion (AIC) to select important variables. We prospectively selected 283 independent lung cancer patients from July 2021 to December 2022 as the validation set to evaluate the model's performance. Result: The prediction model showed good discrimination and calibration, with AUCs of 0.9217 and 0.8288, sensitivity of 79.89% and 45.07%, specificity of 94.48% and 94.81%, in the test and validation sets respectively. Clinical decision curve analysis suggested that the model has value for clinical use when the risk threshold ranges between 0.1 and 0.9. Conclusion: Predictive models based on laboratory and demographic variables can serve as a beneficial complementary tool for identifying high-risk populations with CIN.

show abstract

Prediction model of acute kidney injury induced by cisplatin in older adults using a machine learning algorithm

Cited by 9 publications

References 34 publications

Acute Kidney Injury after Multiple Cycles of Cisplatin Chemotherapy: A Nomogram for Risk Assessment

Acute Kidney Injury after Multiple Cycles of Cisplatin Chemotherapy: A Nomogram for Risk Assessment

Onconephrology: mitigation of renal injury in chemotherapy administration

Development and Validation of a LASSO Prediction Model for cisplatin induced nephrotoxicity: A Case-Control Study in China

Contact Info

Product

Resources

About