Cost-effective survival prediction for patients with advanced prostate cancer using clinical trial and real-world hospital registry datasets

Murtojärvi, Mika; Halkola, Anni S.; Airola, Antti; Laajala, Teemu D.; Mirtti, Tuomas; Aittokallio, Tero; Pahikkala, Tapio

doi:10.1016/j.ijmedinf.2019.104014

Cited by 12 publications

(17 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The remaining 20 studies were read full text. [19][20][21][22][23][24][25][26][27][28][29][30][31][32][33][34][35][36][37][38] The relevant data were extracted and the 2 reviewers independently further assessed the quality of the articles per the CHEERS and Philips checklists.…”

Section: Search Resultsmentioning

confidence: 99%

“…A general overview of the included studies, including the details of the reported AI applications, is provided in Table 2. [19][20][21][22][23][24][25][26][27][28][29][30][31][32][33][34][35][36][37][38] The majority of studies was published in 2019 or later. The studies were conducted in a range of medical specialties, yet ophthalmology was evidently the dominant field.…”

Section: General Overview Of the Included Studiesmentioning

confidence: 99%

“…Two studies (10%) did not report a time horizon; nevertheless, 1 study evaluated incremental effectiveness on overall survival as health outcome. 23 A complete overview of the health economic methodological details of the included studies can be found in Table 3. [19][20][21][22][23][24][25][26][27][28][29][30][31][32][33][34][35][36][37][38]…”

Section: Health Economic Analysismentioning

confidence: 99%

See 2 more Smart Citations

Systematic Review of Health Economic Evaluations Focused on Artificial Intelligence in Healthcare: The Tortoise and the Cheetah

et al. 2022

View full text Add to dashboard Cite

This study aimed to systematically review recent health economic evaluations (HEEs) of artificial intelligence (AI) applications in healthcare. The aim was to discuss pertinent methods, reporting quality and challenges for future implementation of AI in healthcare, and additionally advise future HEEs.Methods: A systematic literature review was conducted in 2 databases (PubMed and Scopus) for articles published in the last 5 years. Two reviewers performed independent screening, full-text inclusion, data extraction, and appraisal. The Consolidated Health Economic Evaluation Reporting Standards and Philips checklist were used for the quality assessment of included studies.Results: A total of 884 unique studies were identified; 20 were included for full-text review, covering a wide range of medical specialties and care pathway phases. The most commonly evaluated type of AI was automated medical image analysis models (n = 9, 45%). The prevailing health economic analysis was cost minimization (n = 8, 40%) with the costs saved per case as preferred outcome measure. A total of 9 studies (45%) reported model-based HEEs, 4 of which applied a time horizon .1 year. The evidence supporting the chosen analytical methods, assessment of uncertainty, and model structures was underreported. The reporting quality of the articles was moderate as on average studies reported on 66% of Consolidated Health Economic Evaluation Reporting Standards items.Conclusions: HEEs of AI in healthcare are limited and often focus on costs rather than health impact. Surprisingly, modelbased long-term evaluations are just as uncommon as model-based short-term evaluations. Consequently, insight into the actual benefits offered by AI is lagging behind current technological developments.

show abstract

Section: Search Resultsmentioning

confidence: 99%

Section: General Overview Of the Included Studiesmentioning

confidence: 99%

Section: Health Economic Analysismentioning

confidence: 99%

See 1 more Smart Citation

Systematic Review of Health Economic Evaluations Focused on Artificial Intelligence in Healthcare: The Tortoise and the Cheetah

et al. 2022

View full text Add to dashboard Cite

show abstract

“…We estimated the classification performance for locally optimal subsets of features extracted from variable numbers of electrode channels, ranging from one electrode to a complete set of 64 electrodes. For finding such locally optimal subsets of electrodes for each subset cardinality, we used a custom budget-based greedy forward search algorithm 20 . We repeated the nested cross-validation procedure ten times in total, each time with a different random state used for dividing the data into training, validation and testing folds, and then averaged over the test performance estimates in order to mitigate the effect of chance on the performance estimates.…”

Section: Classificationmentioning

confidence: 99%

Resting state EEG as a biomarker of Parkinson’s disease: Influence of measurement conditions

Railo

Suuronen

Kaasinen

et al. 2020

Preprint

Self Cite

View full text Add to dashboard Cite

Resting state electroencephalographic (EEG) recording could provide cost-effective means to aid in the detection of neurological disorders such as Parkinson's disease (PD). We examined how many electrodes are needed for classification of PD based on EEG, which electrode locations provide most value for classification, and whether data recorded eyes open or closed yield comparable results. We used a nested cross-validated classifier which included a budgetbased search algorithm for selecting the optimal electrodes for classification. By iterating over variable budgets, we show that with eyes open recording, only 10 electrodes, localized over motor and occipital areas enable relatively accurate classification (AUC = .82) between PD patients (N=20) and age-matched healthy control participants (N=20). Classification accuracy only slightly increased when all 64 electrodes were included (AUC = .85). With the data recorded eyes closed, classification was not statistically significantly above chance even with full set of 64 electrodes (AUC = .55). These results show that classification based on small number of EEG electrodes is a promising tool for classifying PD, but measurement conditions and electrode locations can have a significant effect on classifier performance.

show abstract

“…Huang (2008) proposed a new variable selection and estimation method based on the lasso model, which can predict the correlation pattern between variables [16] . The lasso regression model has also been widely used in medical research for prediction and decision making [17][18][19][20][21][22] . Furthermore, many studies adopted the lasso model to screen variables and use them for optimization [23][24][25] .…”

Section: Introductionmentioning

confidence: 99%

Analysis of Influencing Factors of Community Management of Diabetes Based on Adaptive-Lasso Logistic Regression Model: A Community-based Study

Lin

Tian

Khoja

et al. 2021

Preprint

View full text Add to dashboard Cite

Background This study aimed to analyse which influencing factors may be more effective to achieve diabetes management targets in the community by the adaptive-lasso logistic regression model. Methods A cross-sectional study (N=1,127) was adopted to establish the adaptive-lasso logistic regression model of influencing factors for community management based on multi-stage cluster sampling data among patients with diabetes in China. Patient’s fasting blood glucose level, blood pressure, and triglycerides was collected. Results Overall, 90.6% of included people had a fasting glucose level higher than 6.1mol/L, and 9.4% of them were below 6.1mol/L. By cross-validation, after folding eight times, the variables involved in the adaptive lasso-logistic regression model include age, education level, main source of income, marital status, average monthly income, free medical service, basic medical insurance for residents, hospital history, number of follow-up evaluations by family doctor team, voluntary participation in community blood glucose measurement. The Akaike Information Criterion and Bayesian Information Criterion of adaptive lasso-logistic regression model were 1980 and 2021, which were lower than the full-variable logistic model (2041, 2245) and the ridge logistic model (2043, 2348). The adaptive-lasso logistic regression model was better than the other two models regarding time cost.Conclusions The adaptive-lasso logistic regression model can analyse the influencing factors of community management in patients with diabetes. Community intervention and intensive management measures can significantly improve the blood glucose status of patients with diabetes.

show abstract

Cost-effective survival prediction for patients with advanced prostate cancer using clinical trial and real-world hospital registry datasets

Cited by 12 publications

References 25 publications

Systematic Review of Health Economic Evaluations Focused on Artificial Intelligence in Healthcare: The Tortoise and the Cheetah

Systematic Review of Health Economic Evaluations Focused on Artificial Intelligence in Healthcare: The Tortoise and the Cheetah

Resting state EEG as a biomarker of Parkinson’s disease: Influence of measurement conditions

Analysis of Influencing Factors of Community Management of Diabetes Based on Adaptive-Lasso Logistic Regression Model: A Community-based Study

Contact Info

Product

Resources

About