Machine Learning Algorithms to Predict Recurrence within 10 Years after Breast Cancer Surgery: A Prospective Cohort Study

Lou, Shi-Jer; Hou, Ming‐Feng; Chang, Hong‐Tai; Chiu, Chong‐Chi; Lee, Hao-Hsien; Yeh, Shu-Chuan Jennifer; Shi, Hon-Yi

doi:10.3390/cancers12123817

Cited by 41 publications

(33 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The unit of statistical analysis in this Taiwanese study was the individual elderly patient [26,27]. Sample size calculations determined that, for a power of 0.80, a minimum sample of 120 study participants was needed with an alpha of 0.05 [28].…”

Section: Discussionmentioning

confidence: 99%

Cost and Effectiveness of Long-Term Care Following Integrated Discharge Planning: A Prospective Cohort Study

et al. 2021

Self Cite

View full text Add to dashboard Cite

Little is known about the effects of seamless hospital discharge planning on long-term care (LTC) costs and effectiveness. This study evaluates the cost and effectiveness of the recently implemented policy from hospital to LTC between patients discharged under seamless transition and standard transition. A total of 49 elderly patients in the standard transition cohort and 119 in the seamless transition cohort were recruited from November 2016 to February 2018. Data collected from medical records included the Multimorbidity Frailty Index, Activities of Daily Living Scale, and Malnutrition Universal Screening Tool during hospitalization. Multiple linear regression and Cox regression models were used to explore risk factors for medical resource utilization and medical outcomes. After adjustment for effective predictors, the seamless cohort had lower direct medical costs, a shorter length of stay, a higher survival rate, and a lower unplanned readmission rate compared to the standard cohort. However, only mean total direct medical costs during hospitalization and 6 months after discharge were significantly (p < 0.001) lower in the seamless cohort (USD 6192) compared to the standard cohort (USD 8361). Additionally, the annual per-patient economic burden in the seamless cohort approximated USD 2.9–3.3 billion. Analysis of the economic burden of disability in the elderly population in Taiwan indicates that seamless transition planning can save approximately USD 3 billion in annual healthcare costs. Implementing this policy would achieve continuous improvement in LTC quality and reduce the financial burden of healthcare on the Taiwanese government.

show abstract

Section: Discussionmentioning

confidence: 99%

Cost and Effectiveness of Long-Term Care Following Integrated Discharge Planning: A Prospective Cohort Study

et al. 2021

Self Cite

View full text Add to dashboard Cite

show abstract

“…The sigmoid was adopted as the final activation layer. This model was modified from a previous study in the medical fields [ 10 ].…”

Section: Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

“…Machine learning algorithms use large-scale clinical data and learn patterns to assess outcomes [ 10 ]. In the medical field, automatic prediction of cancer recurrence has been reported using artificial neural networks (ANNs) [ 10 , 11 , 12 ]. While ANNs are biologically based on studies of the nervous system, they aim for nonlinear regression of classification, and are not biologically realistic in their details [ 13 ].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Machine Learning Algorithms: Prediction and Feature Selection for Clinical Refracture after Surgically Treated Fragility Fracture

Shimizu

Enda

Shimizu

et al. 2022

JCM

View full text Add to dashboard Cite

Background: The number of patients with fragility fracture has been increasing. Although the increasing number of patients with fragility fracture increased the rate of fracture (refracture), the causes of refracture are multifactorial, and its predictors are still not clarified. In this issue, we collected a registry-based longitudinal dataset that contained more than 7000 patients with fragility fractures treated surgically to detect potential predictors for clinical refracture. Methods: Based on the fact that machine learning algorithms are often used for the analysis of a large-scale dataset, we developed automatic prediction models and clarified the relevant features for patients with clinical refracture. Formats of input data containing perioperative clinical information were table data. Clinical refracture was documented as the primary outcome if the diagnosis of fracture was made at postoperative outpatient care. A decision-tree-based model, LightGBM, had moderate accuracy for the prediction in the test and the independent dataset, whereas the other models had poor accuracy or worse. Results: From a clinical perspective, rheumatoid arthritis (RA) and chronic kidney disease (CKD) were noted as the relevant features for patients with clinical refracture, both of which were associated with secondary osteoporosis. Conclusion: The decision-tree-based algorithm showed the precise prediction of clinical refracture, in which RA and CKD were detected as the potential predictors. Understanding these predictors may improve the management of patients with fragility fractures.

show abstract

“…Novel techniques in AI can bring together diverse data types to expand novel insights gained from the multiomics datasets. It is well acknowledged that enrichment of high-quality data coupled with machine learning, a subset of AI, can help investigate the areas of changing patients’ unhealthy behaviors [ 22 ], risk prediction or recurrence prediction of chronic diseases after a surgery [ 23 ] and curative treatment [ 24 ], progression and survivability of patients with chronic diseases [ 25 ], therapeutic need, enhanced clinical trial interpretation, and novel targets [ 26 ]. However, a major criticism of incorporating AI, particularly deep learning, into medical fields is the idea that AI is essentially a mechanistically uninterpretable opaque “black box” [ 27 , 28 , 29 ], and hence may not meet the required high level of accountability, transparency, and reliability in medical decisions [ 30 ].…”

Section: Introductionmentioning

confidence: 99%

Explainable Artificial Intelligence Reveals Novel Insight into Tumor Microenvironment Conditions Linked with Better Prognosis in Patients with Breast Cancer

Chakraborty

Ivan

Amero

et al. 2021

Cancers

View full text Add to dashboard Cite

We investigated the data-driven relationship between immune cell composition in the tumor microenvironment (TME) and the ≥5-year survival rates of breast cancer patients using explainable artificial intelligence (XAI) models. We acquired TCGA breast invasive carcinoma data from the cbioPortal and retrieved immune cell composition estimates from bulk RNA sequencing data from TIMER2.0 based on EPIC, CIBERSORT, TIMER, and xCell computational methods. Novel insights derived from our XAI model showed that B cells, CD8+ T cells, M0 macrophages, and NK T cells are the most critical TME features for enhanced prognosis of breast cancer patients. Our XAI model also revealed the inflection points of these critical TME features, above or below which ≥5-year survival rates improve. Subsequently, we ascertained the conditional probabilities of ≥5-year survival under specific conditions inferred from the inflection points. In particular, the XAI models revealed that the B cell fraction (relative to all cells in a sample) exceeding 0.025, M0 macrophage fraction (relative to the total immune cell content) below 0.05, and NK T cell and CD8+ T cell fractions (based on cancer type-specific arbitrary units) above 0.075 and 0.25, respectively, in the TME could enhance the ≥5-year survival in breast cancer patients. The findings could lead to accurate clinical predictions and enhanced immunotherapies, and to the design of innovative strategies to reprogram the breast TME.

show abstract

Machine Learning Algorithms to Predict Recurrence within 10 Years after Breast Cancer Surgery: A Prospective Cohort Study

Cited by 41 publications

References 33 publications

Cost and Effectiveness of Long-Term Care Following Integrated Discharge Planning: A Prospective Cohort Study

Cost and Effectiveness of Long-Term Care Following Integrated Discharge Planning: A Prospective Cohort Study

Machine Learning Algorithms: Prediction and Feature Selection for Clinical Refracture after Surgically Treated Fragility Fracture

Explainable Artificial Intelligence Reveals Novel Insight into Tumor Microenvironment Conditions Linked with Better Prognosis in Patients with Breast Cancer

Contact Info

Product

Resources

About