Prediction of ameloblastoma recurrence using random forest—a machine learning algorithm

Wang, R.; Li, K.Y.; Su, Yu‐xiong

doi:10.1016/j.ijom.2021.11.017

Cited by 11 publications

(5 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The four most important variables influencing ameloblastoma recurrence were the time elapsed from treatment, initial surgical treatment, tumor size, and radiographic presentation. These were used in the algorithm to reliably predict recurrence [58]. Similarly, Yang et al have developed a favorable nomogram that accurately predicted the recurrence-free survival of patients with ameloblastoma based on individual characteristics, which could optimize tailored therapy and follow-up [59].…”

Section: Recent Advancesmentioning

confidence: 99%

Ameloblastoma: An Updated Narrative Review of an Enigmatic Tumor

Ghai¹

2022

Cureus

View full text Add to dashboard Cite

Ameloblastoma is one of the most common benign odontogenic tumors of the jaw that constitutes about 10% of all tumors that arise in the mandible and maxilla. It is a slow-growing but locally invasive tumor that presents with painless swelling of the mandible or maxilla. The World Health Organization (WHO) classification of 2017 describes ameloblastomas of the following four types: ameloblastoma; unicystic ameloblastoma; extraosseous/peripheral ameloblastoma; and metastasizing ameloblastoma. The diagnosis of ameloblastoma requires computerized tomography (CT) imaging as well as a biopsy. A biopsy is helpful in differentiating ameloblastoma from ossifying fibroma, osteomyelitis, giant cell tumor, cystic fibrous dysplasia, myeloma, and sarcoma. The best treatment of ameloblastoma is aggressive en bloc resection with simultaneous reconstruction. The high recurrence rate and large tissue defects have been long-standing issues in the treatment of ameloblastoma. Recent molecular developments strongly suggest the possibility of targeted therapy with better outcomes in ameloblastomas. We present a detailed updated narrative review of our current understanding and management of this enigmatic tumor.

show abstract

Section: Recent Advancesmentioning

confidence: 99%

Ameloblastoma: An Updated Narrative Review of an Enigmatic Tumor

Ghai¹

2022

Cureus

View full text Add to dashboard Cite

show abstract

“…Rate of recurrence following surgical resection of DA is 3.1% compared to 21.1% recurrence risk following enucleation and the average period until recurrence is 36.9 months ( 10 ). According to one study, the most important variables that influence recurrence of ameloblastoma are time elapsed from treatment, type of surgical treatment, tumor size, and radiographic presentation ( 23 ).…”

Section: Discussionmentioning

confidence: 99%

Desmoplastic histological subtype of ameloblastoma in 16 dogs

Feigin,

Bell

2024

Front. Vet. Sci.

View full text Add to dashboard Cite

Ameloblastoma in dogs most often has a highly conserved acanthomatous cell morphology and is recognized as canine acanthomatous ameloblastoma (CAA) while conventional ameloblastoma (CA) makes up a smaller yet morphologically diverse group of epithelial odontogenic tumors. In humans, a rare desmoplastic histological subtype has distinctive clinical, radiological, and microscopic features. Desmoplastic ameloblastoma (DA) has not previously been described in dogs, although it has been rarely referenced in the veterinary literature. This is the first thorough description of a case series of DA in dogs and describes clinical presentation, diagnostic imaging findings, histopathological features for diagnosis, and treatment outcome. Clinically, DA most often presents as a mass or swelling in the rostral mandible or maxilla of middle age to older dogs. On diagnostic imaging, the lesion has a radiolucent or mixed pattern with well-defined borders and variable loculation. As a solid, fibrous tumor with obscured odontogenic epithelium, DA is challenging to diagnose histologically and can mimic several other oral tumors, both benign and malignant. As an ameloblastoma, the biological behavior of DA is locally destructive yet benign and prognosis is favorable following surgical excision.

show abstract

“…Random forest algorithm has been widely used to predict various diseases or symptoms in the medical industry,such as the prediction of macrosomia and ameloblastoma recurrence [13,14]. In this paper, a whale optimization algorithm is added on the basis of random forest algorithm to fit the regression objective.…”

Section: Discussionmentioning

confidence: 99%

A novel approach for anaerobic threshold heart rate prediction using whale optimization algorithm based random forest algorithm

Li,

Xie,

Guo

2023

Preprint

View full text Add to dashboard Cite

Anaerobic threshold (AT) is the critical point at which the energy system produces different energy supply patterns during exercise. At present, the measurement of AT is obtained through cardiopulmonary exercise testing (CPET). The heart rate at which an individual enters the anaerobic threshold during cardiopulmonary exercise testing is referred to as the anaerobic threshold heart rate. When using sports prescription or exercise plan as a means to improve health status or quality of life, it is necessary to determine the specific exercise intensity according to the individual's anaerobic threshold heart rate. This paper aims to using whale optimization algorithm based random forest algorithm (WOA-RF) to predict the anaerobic threshold heart rate of individuals by collecting the basic physical characteristics, heart rate and load in CPET. Data that are easy to collect for daily measurement are selected: age, gender, height, weight, initial heart rate, initial load, relative heart rate increment at 30% maximum load, relative heart rate increment at 50% maximum load, relative heart rate increment at 70% maximum load, maximum heart rate, and maximum load.In the result of predicted value: RMSE=7.9445, MAE=6.4206, R2=0.7152. We consider the feasibility of prediction anaerobic threshold heart rate by WOA-RF machine learning algorithm to be acceptable.

show abstract

Prediction of ameloblastoma recurrence using random forest—a machine learning algorithm

Cited by 11 publications

References 24 publications

Ameloblastoma: An Updated Narrative Review of an Enigmatic Tumor

Ameloblastoma: An Updated Narrative Review of an Enigmatic Tumor

Desmoplastic histological subtype of ameloblastoma in 16 dogs

A novel approach for anaerobic threshold heart rate prediction using whale optimization algorithm based random forest algorithm

Contact Info

Product

Resources

About