An Evaluation of Artificial Neural Networks in Predicting Pancreatic Cancer Survival

Walczak, Steven; Velanovich, Vic

doi:10.1007/s11605-017-3518-7

Cited by 33 publications

(23 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…R 2 was reported in one study 19. Sensitivity and specificity were also poorly reported (n=2) 26 29. Internal validation was rarely performed.…”

Section: Resultsmentioning

confidence: 99%

“…The number of model development studies, with (n=3)18–20 and without (n=12) external validation,21–32 increased sharply in recent years (figure 2). Multivariable Cox regression proportional hazard regression was the most commonly employed modelling method (n=13)18–25 27–29 31 32 with two studies employing alternative machine learning techniques (Bayesian model: n=1; Artificial Neural Network (ANN): n=1) 26 30. Six models could be applied preoperatively 19 23 24 27 28 31.…”

Section: Resultsmentioning

confidence: 99%

“…Fourteen studies used backward elimination methods 18–21 23–32. This included an ANN that used single hidden layer back propagation to train the model,26 and a Bayesian model that employed backward step down selection process 30. Of the remaining 12 studies employing this method nominal p value was used as the criteria for predictor inclusion.…”

Section: Resultsmentioning

confidence: 99%

“…Internal validation was rarely performed. Three studies used bootstrapping21 22 28 and four studies used random split method 26 29–31. Three studies included external validation as part of model development 18–20.…”

Section: Resultsmentioning

confidence: 99%

See 3 more Smart Citations

A systematic review of methodological quality of model development studies predicting prognostic outcome for resectable pancreatic cancer

2019

View full text Add to dashboard Cite

ObjectivesTo assess the methodological quality of prognostic model development studies pertaining to post resection prognosis of pancreatic ductal adenocarcinoma (PDAC).Design/settingA narrative systematic review of international peer reviewed journalsData sourceSearches were conducted of: MEDLINE, Embase, PubMed, Cochrane database and Google Scholar for predictive modelling studies applied to the outcome of prognosis for patients with PDAC post resection. Predictive modelling studies in this context included prediction model development studies with and without external validation and external validation studies with model updating. Data was extracted following the Checklist for critical Appraisal and data extraction for systematic Reviews of prediction Modelling Studies (CHARMS) checklist.Primary and secondary outcome measuresPrimary outcomes were all components of the CHARMS checklist. Secondary outcomes included frequency of variables included across predictive models.Results263 studies underwent full text review. 15 studies met the inclusion criteria. 3 studies underwent external validation. Multivariable Cox proportional hazard regression was the most commonly employed modelling method (n=13). 10 studies were based on single centre databases. Five used prospective databases, seven used retrospective databases and three used cancer data registry. The mean number of candidate predictors was 19.47 (range 7 to 50). The most commonly included variables were tumour grade (n=9), age (n=8), tumour stage (n=7) and tumour size (n=5). Mean sample size was 1367 (range 50 to 6400). 5 studies reached statistical power. None of the studies reported blinding of outcome measurement for predictor values. The most common form of presentation was nomograms (n=5) and prognostic scores (n=5) followed by prognostic calculators (n=3) and prognostic index (n=2).ConclusionsAreas for improvement in future predictive model development have been highlighted relating to: general aspects of model development and reporting, applicability of models and sources of bias.Trial registration numberCRD42018105942

show abstract

“…R 2 was reported in one study 19. Sensitivity and specificity were also poorly reported (n=2) 26 29. Internal validation was rarely performed.…”

Section: Resultsmentioning

confidence: 99%

Section: Resultsmentioning

confidence: 99%

Section: Resultsmentioning

confidence: 99%

Section: Resultsmentioning

confidence: 99%

See 2 more Smart Citations

A systematic review of methodological quality of model development studies predicting prognostic outcome for resectable pancreatic cancer

2019

View full text Add to dashboard Cite

show abstract

“…However, if RFA were applied in PC, the results showed complication rates (15%) and a progression-free survival rate of 22% during the follow-up of 12 months [ 35 ]. Previous studies showed that the proportion of 7-month survival in PC patients in resection and no resection group was 53.19% versus 70.40% [ 36 ], and the 12-month overall survival in the radiation and nonradiation group was 43% and 29%, respectively [ 37 ]. In fact, as an emerging technique, IRE was usually conducted percutaneously or by open surgical or laparoscopic access, which was superior in unresectable lesions.…”

Section: Discussionmentioning

confidence: 99%

Irreversible Electroporation in Patients with Pancreatic Cancer: How Important Is the New Weapon?

Tian

Liu

Zhao

et al. 2018

BioMed Research International

View full text Add to dashboard Cite

Background Pancreatic cancer (PC) is a deadly disease with poor prognosis in the general population. We aimed to quantitate overall survival of patients with PC after irreversible electroporation (IRE) and the incidence of relevant complications. Methods We performed a literature search via five electronic databases (PubMed, Embase, Web of Science, Scopus, and Cochrane Library databases) up to August 2017. The primary outcomes were overall survival and prognosis. Secondary outcomes included the response of post-IRE complications. Fixed-effects or random-effects meta-analysis was conducted to pool these data. Results A total of 15 eligible articles involving 535 patients were included. The primary outcomes showed that the pooled prevalence estimates of overall survival were 94.1% (95% CI: 90.7–97.5), 80.9% (95% CI: 72.5–89.4), 54.5% (95% CI: 38.3–70.6), and 33.8% (95% CI: 14.2–53.5) at 3, 6, 12, and 24 months, and the pooled prevalence data of complete response (CR) at 2 months, partial response (PR) at 3 months, and progression at 3 months were 12.5% (95% CI: 2.9–22.2), 48.5% (95% CI: 39.4–57.6), and 19.7% (95% CI: 7.3–32.2), respectively. The secondary outcomes showed that the pooled prevalence values of post-IRE complications were abscess 6.6% (95% CI: 0.2–13), fistula 10.6% (95% CI: 2.5–18.7), pain 33.5% (95% CI: 14.5–52.5), infection 16.1% (95% CI: 3.9–28.4), thrombosis 4.9% (95% CI: 1.2–8.5), pancreatitis 7.2% (95% CI: 3.1–11.2), bleeding 4.2% (95% CI: −0.5–8.9), cholangitis 4.2% (95% CI: −0.5–8.9), nausea 9.6% (95% CI: 4.4–14.8), biliary obstruction 13.8% (95% CI: 4.2–23.3), chest tightness 7.6% (95% CI: 0.5–14.6), and hypoglycemia 5.9% (95% CI: −0.4–12.2). Conclusions This meta-analysis indicated a clear survival benefit for PC patients who received irreversible electroporation therapy, although future safety and effectivity monitoring from more large-scale studies will be needed.

show abstract

Otoscopic diagnosis using computer vision: An automated machine learning approach

Livingstone

Chau²

2019

The Laryngoscope

View full text Add to dashboard Cite

Objective: Access to otolaryngology is limited by lengthy wait lists and lack of specialists, especially in rural and remote areas. The objective of this study was to use an automated machine learning approach to build a computer vision algorithm for otoscopic diagnosis capable of greater accuracy than trained physicians. This algorithm could be used by primary care providers to facilitate timely referral, triage, and effective treatment.Methods: Otoscopic images were obtained from Google Images (Google Inc., Mountain View, CA), from open access repositories, and within otolaryngology clinics associated with our institution. After preprocessing, 1,366 unique images were uploaded to the Google Cloud Vision AutoML platform (Google Inc.) and annotated with one or more of 14 otologic diagnoses. A consensus set of labels for each otoscopic image was attained, and a multilabel classifier architecture algorithm was trained. The performance of the algorithm on an 89-image test set was compared to the performance of physicians from pediatrics, emergency medicine, otolaryngology, and family medicine.Results: For all diagnoses combined, the average precision (positive predictive value) of the algorithm was 90.9%, and the average recall (sensitivity) was 86.1%. The algorithm made 79 correct diagnoses with an accuracy of 88.7%. The average physician accuracy was 58.9%.Conclusion: We have created a computer vision algorithm using automated machine learning that on average rivals the accuracy of the physicians we tested. Fourteen different otologic diagnoses were analyzed. The field of medicine will be changed dramatically by artificial intelligence within the next few decades, and physicians of all specialties must be prepared to guide that process.

show abstract

An Evaluation of Artificial Neural Networks in Predicting Pancreatic Cancer Survival

Cited by 33 publications

References 38 publications

A systematic review of methodological quality of model development studies predicting prognostic outcome for resectable pancreatic cancer

A systematic review of methodological quality of model development studies predicting prognostic outcome for resectable pancreatic cancer

Irreversible Electroporation in Patients with Pancreatic Cancer: How Important Is the New Weapon?

Otoscopic diagnosis using computer vision: An automated machine learning approach

Contact Info

Product

Resources

About