Demystifying machine learning: a primer for physicians

Scott, Ian

doi:10.1111/imj.15200

Cited by 27 publications

(28 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Machine learning can discern patterns from large datasets. Identified patterns are then used to encode a mathematical model, which applies to new data for further validation ( 10 ). Applications of machine learning in medicine are being used in disease diagnosis, prognosis, therapy development, and treatment assessment.…”

Section: Discussionmentioning

confidence: 99%

Predicting Survival of Patients With Rectal Neuroendocrine Tumors Using Machine Learning: A SEER-Based Population Study

Cheng

et al. 2021

Front. Surg.

View full text Add to dashboard Cite

Background: The number of patients diagnosed with rectal neuroendocrine tumors (R-NETs) is increasing year by year. An integrated survival predictive model is required to predict the prognosis of R-NETs. The present study is aimed at exploring epidemiological characteristics of R-NETs based on a retrospective study from the Surveillance, Epidemiology, and End Results (SEER) database and predicting survival of R-NETs with machine learning.Methods: Data of patients with R-NETs were extracted from the SEER database (2000–2017), and data were also retrospectively collected from a single medical center in China. The main outcome measure was the 5-year survival status. Risk factors affecting survival were analyzed by Cox regression analysis, and six common machine learning algorithms were chosen to build the predictive models. Data from the SEER database were divided into a training set and an internal validation set according to the year 2010 as a time point. Data from China were chosen as an external validation set. The best machine learning predictive model was compared with the American Joint Committee on Cancer (AJCC) seventh staging system to evaluate its predictive performance in the internal validation dataset and external validation dataset.Results: A total of 10,580 patients from the SEER database and 68 patients from a single medical center were included in the analysis. Age, gender, race, histologic type, tumor size, tumor number, summary stage, and surgical treatment were risk factors affecting survival status. After the adjustment of parameters and algorithms comparison, the predictive model using the eXtreme Gradient Boosting (XGBoost) algorithm had the best predictive performance in the training set [area under the curve (AUC) = 0.87, 95%CI: 0.86–0.88]. In the internal validation, the predictive ability of XGBoost was better than that of the AJCC seventh staging system (AUC: 0.90 vs. 0.78). In the external validation, the XGBoost predictive model (AUC = 0.89) performed better than the AJCC seventh staging system (AUC = 0.83).Conclusions: The XGBoost algorithm had better predictive power than the AJCC seventh staging system, which had a potential value of the clinical application.

show abstract

Section: Discussionmentioning

confidence: 99%

Predicting Survival of Patients With Rectal Neuroendocrine Tumors Using Machine Learning: A SEER-Based Population Study

Cheng

et al. 2021

Front. Surg.

View full text Add to dashboard Cite

show abstract

“…Therefore, one major consideration of this project is clinical value, especially 32 . While in recent years, adoption of ML in the clinical workflow has increased, as seen by over 50 FDA cleared algorithms 33 , physicians often do not trust models they do not understand and many have very little familiarity with them 31,[34][35][36][37] . Therefore, in order for a model to have some clinical value, it is necessary to consider approaches that are not overly-complex.…”

Section: Statistical Methods and Machine Learning Algorithmsmentioning

confidence: 99%

Long-term survival and second malignant tumor prediction in pediatric, adolescent, and young adult cancer survivors using Random Survival Forests: a SEER analysis

Zhang

Hart

Qin

et al. 2023

Sci Rep

View full text Add to dashboard Cite

Survival and second malignancy prediction models can aid clinical decision making. Most commonly, survival analysis studies are performed using traditional proportional hazards models, which require strong assumptions and can lead to biased estimates if violated. Therefore, this study aims to implement an alternative, machine learning (ML) model for survival analysis: Random Survival Forest (RSF). In this study, RSFs were built using the U.S. Surveillance Epidemiology and End Results to (1) predict 30-year survival in pediatric, adolescent, and young adult cancer survivors; and (2) predict risk and site of a second tumor within 30 years of the first tumor diagnosis in these age groups. The final RSF model for pediatric, adolescent, and young adult survival has an average Concordance index (C-index) of 92.9%, 94.2%, and 94.4% and average time-dependent area under the receiver operating characteristic curve (AUC) at 30-years since first diagnosis of 90.8%, 93.6%, 96.1% respectively. The final RSF model for pediatric, adolescent, and young adult second malignancy has an average C-index of 86.8%, 85.2%, and 88.6% and average time-dependent AUC at 30-years since first diagnosis of 76.5%, 88.1%, and 99.0% respectively. This study suggests the robustness and potential clinical value of ML models to alleviate physician burden by quickly identifying highest risk individuals.

show abstract

“…For more information on machine learning and the ensemble approach, interested readers are encouraged to consult this study's supplemental . In addition, readers may consider previously published primers and tutorials which offer an accessible and clinically relevant introduction to machine learning principles and their associated decision making processes (Lekkas et al., 2021; Rosenbusch et al., 2021; Scott, 2021).…”

Section: Methodsmentioning

confidence: 99%

A machine learning investigation into the temporal dynamics of physical activity‐mediated emotional regulation in adolescents with anorexia nervosa and healthy controls

Lekkas

Gyorda

Jacobson

2022

Euro Eating Disorders Rev

View full text Add to dashboard Cite

Objective Anorexia nervosa (AN) is commonly experienced alongside difficulties of emotion regulation (ER). Previous works identified physical activity (PA) as a mechanism for AN sufferers to achieve desired affective states, with evidence towards mitigation of negative affect. However, temporal associations of PA with specific emotional state outcomes are unknown. Method Using lag‐ensemble machine learning and feature importance analyses, 888 affect‐based ecological momentary assessments across N = 75 adolescents with AN (N = 44) and healthy controls (N = 31) were analysed to explore significance of past PA, measured through passively collected wrist‐worn actigraphy, with subsequent self‐report momentary affect change across 9 affect constructs. Results Among AN adolescents, later lags (≥2.5 h) were important in predicting change across negative emotions (hostility, sadness, fear, guilt). AN‐specific model performance on held‐out test data revealed the holistic “negative affect” construct as significantly predictable. Only joviality and self‐assurance, both positively‐valenced constructs, were significantly predictable among healthy‐control‐specific models. Discussion Results recapitulated previous findings regarding the importance of PA in negative ER for AN individuals. Moreover, PA was found to play a uniquely prominent role in predicting negative affect 4.5–6 h later among AN adolescents. Future research into the PA‐ER dynamic will benefit from targeting specific negative emotions across greater temporal scales.

show abstract

Demystifying machine learning: a primer for physicians

Cited by 27 publications

References 41 publications

Predicting Survival of Patients With Rectal Neuroendocrine Tumors Using Machine Learning: A SEER-Based Population Study

Predicting Survival of Patients With Rectal Neuroendocrine Tumors Using Machine Learning: A SEER-Based Population Study

Long-term survival and second malignant tumor prediction in pediatric, adolescent, and young adult cancer survivors using Random Survival Forests: a SEER analysis

A machine learning investigation into the temporal dynamics of physical activity‐mediated emotional regulation in adolescents with anorexia nervosa and healthy controls

Contact Info

Product

Resources

About