Abstract:
BACKGROUND:Predicting survival of recipients after liver transplantation is regarded as one of the most important challenges in contemporary medicine. Hence, improving on current prediction models is of great interest.Nowadays, there is a strong discussion in the medical field about machine learning (ML) and whether it has greater potential than traditional regression models when dealing with complex data. Criticism to ML is related to unsuitable performance measures and lack of interpretability which is important for clinicians. METHODS:In this paper, ML techniques such as random forests and neural networks are applied to large data of 62294 patients from the United States with 97 predictors selected on clinical/statistical grounds, over more than 600, to predict survival from transplantation. Of particular interest is also the identification of potential risk factors. A comparison is performed between 3 different Cox models (with all variables, backward selection and LASSO) and 3 machine learning techniques: a random survival forest and 2 partial logistic artificial neural networks (PLANNs). For PLANNs, novel extensions to their original specification are tested. Emphasis is given on the advantages and pitfalls of each method and on the interpretability of the ML techniques. RESULTS:Well-established predictive measures are employed from the survival field (C-index, Brier score and Integrated Brier Score) and the strongest prognostic factors are identified for each model. Clinical endpoint is overall graft-survival defined as the time between transplantation and the date of graft-failure or death. The random survival forest shows slightly better predictive performance than Cox models based on the C-index. Neural networks show better performance than both Cox models and random survival forest based on the Integrated Brier Score at 10 years. CONCLUSION:In this work, it is shown that machine learning techniques can be a useful tool for both prediction and interpretation in the survival context. From the ML techniques examined here, PLANN with 1 hidden layer predicts survival probabilities the most accurately, being as calibrated as the Cox model with all variables. TRIAL REGISTRATION:Retrospective data were provided by the Scientific Registry of Transplant Recipients under Data Use Agreement number 9477 for analysis of risk factors after liver transplantation.
journal_name
BMC Med Res Methodoljournal_title
BMC medical research methodologyauthors
Kantidakis G,Putter H,Lancia C,Boer J,Braat AE,Fiocco Mdoi
10.1186/s12874-020-01153-1subject
Has Abstractpub_date
2020-11-16 00:00:00pages
277issue
1issn
1471-2288pii
10.1186/s12874-020-01153-1journal_volume
20pub_type
杂志文章abstract:BACKGROUND:The BSI-18 contains the three six-item scales somatization, depression, and anxiety as well as the Global Severity Index (GSI), including all 18 items. The BSI-18 is the latest and shortest of the multidimensional versions of the Symptom-Checklist 90-R, but its psychometric properties have not been sufficien...
journal_title:BMC medical research methodology
pub_type: 杂志文章
doi:10.1186/s12874-016-0283-3
更新日期:2017-01-26 00:00:00
abstract::The quality of a consultation provided by a physician can have a profound impact on the quality of care and patient engagement in treatment decisions. When the COPD Assessment Test (CAT) was developed, one of its aims was to aid the communication between physician and patient about the impact of COPD. We developed a n...
journal_title:BMC medical research methodology
pub_type: 信件
doi:10.1186/1471-2288-13-63
更新日期:2013-05-10 00:00:00
abstract:BACKGROUND:Polypharmacy can be either beneficial or harmful to children. We conducted a scoping review to examine the concept of pediatric polypharmacy: its definition, prevalence, extent and gaps in research. In this manuscript, we report our transdisciplinary scoping review methodology. METHODS:After establishing a ...
journal_title:BMC medical research methodology
pub_type: 杂志文章
doi:10.1186/s12874-018-0560-4
更新日期:2018-10-04 00:00:00
abstract:BACKGROUND:We developed and validated an automated database case definition for diabetes in children and youth to facilitate pharmacoepidemiologic investigations of medications and the risk of diabetes. METHODS:The present study was part of an in-progress retrospective cohort study of antipsychotics and diabetes in Te...
journal_title:BMC medical research methodology
pub_type: 杂志文章
doi:10.1186/1471-2288-12-128
更新日期:2012-08-24 00:00:00
abstract:BACKGROUND:Longitudinal studies using data collected as part of usual care risk providing biased results if visit times are related to the outcome of interest. Statistical methods for mitigating this bias are available but rarely used. This lack of use could be attributed to a lack of need or to a lack of awareness of ...
journal_title:BMC medical research methodology
pub_type: 杂志文章,评审
doi:10.1186/s12874-017-0418-1
更新日期:2017-09-06 00:00:00
abstract:BACKGROUND:The "real" effect size of a medical therapy is constant over time. In contrast, the effect size reported in randomised controlled trials (RCTs) may change over time because the sum of all kinds of bias influencing the reported effectiveness is not necessarily constant. As this would affect the validity of me...
journal_title:BMC medical research methodology
pub_type: 杂志文章,meta分析
doi:10.1186/1471-2288-6-25
更新日期:2006-05-11 00:00:00
abstract:BACKGROUND:Primary care databases are a major source of data for epidemiological and health services research. However, most studies are based on coded information, ignoring information stored in free text. Using the early presentation of rheumatoid arthritis (RA) as an exemplar, our objective was to estimate the exten...
journal_title:BMC medical research methodology
pub_type: 杂志文章
doi:10.1186/1471-2288-13-105
更新日期:2013-08-21 00:00:00
abstract:BACKGROUND:We would expect information on adverse drug reactions in randomised clinical trials to be easily retrievable from specific searches of electronic databases. However, complete retrieval of such information may not be straightforward, for two reasons. First, not all clinical drug trials provide data on the fre...
journal_title:BMC medical research methodology
pub_type: 杂志文章
doi:10.1186/1471-2288-1-7
更新日期:2001-01-01 00:00:00
abstract:BACKGROUND:To provide empirical evidence about prevalence, reporting and handling of missing outcome data in systematic reviews with network meta-analysis and acknowledgement of their impact on the conclusions. METHODS:We conducted a systematic survey including all published systematic reviews of randomized controlled...
journal_title:BMC medical research methodology
pub_type: 杂志文章
doi:10.1186/s12874-018-0576-9
更新日期:2018-10-24 00:00:00
abstract:BACKGROUND:Multiple Imputation as usually implemented assumes that data are Missing At Random (MAR), meaning that the underlying missing data mechanism, given the observed data, is independent of the unobserved data. To explore the sensitivity of the inferences to departures from the MAR assumption, we applied the meth...
journal_title:BMC medical research methodology
pub_type: 杂志文章
doi:10.1186/1471-2288-12-73
更新日期:2012-06-08 00:00:00
abstract:BACKGROUND:Family members are increasingly involved in the care of cancer patients, however many are not prepared for this challenging role. Intervention-based studies are valuable to inform the most appropriate and effective support for caregivers. Barriers in the recruitment of patient/caregiver dyads exist but the r...
journal_title:BMC medical research methodology
pub_type: 杂志文章,多中心研究,随机对照试验
doi:10.1186/s12874-018-0614-7
更新日期:2018-11-21 00:00:00
abstract:BACKGROUND:Two most important considerations in evaluation of survival prediction models are 1) predictability - ability to predict survival risks accurately and 2) reproducibility - ability to generalize to predict samples generated from different studies. We present approaches for assessment of reproducibility of sur...
journal_title:BMC medical research methodology
pub_type: 杂志文章,多中心研究
doi:10.1186/1471-2288-13-25
更新日期:2013-02-20 00:00:00
abstract:BACKGROUND:Cluster randomised trials with unequal sized clusters often have lower precision than with clusters of equal size. To allow for this, sample sizes are inflated by a modified version of the design effect for clustering. These inflation factors are valid under the assumption that randomisation is stratified by...
journal_title:BMC medical research methodology
pub_type: 杂志文章
doi:10.1186/s12874-019-0760-6
更新日期:2019-06-14 00:00:00
abstract:BACKGROUND:The Public Population Project in Genomics (P3G) is an organisation that aims to promote collaboration between researchers in the field of population-based genomics. The main objectives of P3G are to encourage collaboration between researchers and biobankers, optimize study design, promote the harmonization o...
journal_title:BMC medical research methodology
pub_type: 杂志文章
doi:10.1186/1471-2288-11-135
更新日期:2011-10-05 00:00:00
abstract:BACKGROUND:There is increasing awareness that meta-analyses require a sufficiently large information size to detect or reject an anticipated intervention effect. The required information size in a meta-analysis may be calculated from an anticipated a priori intervention effect or from an intervention effect suggested b...
journal_title:BMC medical research methodology
pub_type: 杂志文章
doi:10.1186/1471-2288-9-86
更新日期:2009-12-30 00:00:00
abstract:BACKGROUND:Missing data are common in medical research, which can lead to a loss in statistical power and potentially biased results if not handled appropriately. Multiple imputation (MI) is a statistical method, widely adopted in practice, for dealing with missing data. Many academic journals now emphasise the importa...
journal_title:BMC medical research methodology
pub_type: 杂志文章,评审
doi:10.1186/s12874-015-0022-1
更新日期:2015-04-07 00:00:00
abstract:BACKGROUND:A recent paper found that terminal digits of statistical values in Nature deviated significantly from an equiprobable distribution, indicating errors or inconsistencies in rounding. This finding, as well as the discovery that a large percentage of p values were inconsistent with reported test statistics, led...
journal_title:BMC medical research methodology
pub_type: 评论,杂志文章
doi:10.1186/1471-2288-6-45
更新日期:2006-09-13 00:00:00
abstract:BACKGROUND:This paper focuses on measuring the efficiency and effectiveness of two diagramming methods employed in key informant interviews with clinicians and health care administrators. The two methods are 'participatory diagramming', where the respondent creates a diagram that assists in their communication of answe...
journal_title:BMC medical research methodology
pub_type: 杂志文章
doi:10.1186/1471-2288-8-53
更新日期:2008-08-08 00:00:00
abstract:BACKGROUND:Studies in both paediatric and psychiatric settings often experience problems in recruitment. This can compromise the ability of the study to recruit to target, meaning studies are potentially underpowered. It can also result in a biased sample if a non-representative group are selectively recruited. Recruit...
journal_title:BMC medical research methodology
pub_type: 杂志文章
doi:10.1186/s12874-019-0730-z
更新日期:2019-04-27 00:00:00
abstract:BACKGROUND:Given an observed test statistic and its degrees of freedom, one may compute the observed P value with most statistical packages. It is unknown to what extent test statistics and P values are congruent in published medical papers. METHODS:We checked the congruence of statistical results reported in all the ...
journal_title:BMC medical research methodology
pub_type: 杂志文章
doi:10.1186/1471-2288-4-13
更新日期:2004-05-28 00:00:00
abstract:BACKGROUND:In recent months, multiple efforts have sought to characterize COVID-19 social distancing policy responses. These efforts have used various coding frameworks, but many have relied on coding methodologies that may not adequately describe the gradient in social distancing policies as states "re-open." METHODS...
journal_title:BMC medical research methodology
pub_type: 杂志文章
doi:10.1186/s12874-020-01174-w
更新日期:2020-12-08 00:00:00
abstract:BACKGROUND:Clinical quality registries and other systems that conduct routine post-discharge surveillance of patient outcomes following surgery may have difficulty surveying patients who have limited proficiency in the language of the healthcare provider. Interpreter proxies (family and carers) are often used due to li...
journal_title:BMC medical research methodology
pub_type: 杂志文章
doi:10.1186/s12874-019-0854-1
更新日期:2019-11-14 00:00:00
abstract:BACKGROUND:The intraclass correlation coefficient (ICC) is widely used in biomedical research to assess the reproducibility of measurements between raters, labs, technicians, or devices. For example, in an inter-rater reliability study, a high ICC value means that noise variability (between-raters and within-raters) is...
journal_title:BMC medical research methodology
pub_type: 杂志文章
doi:10.1186/1471-2288-14-121
更新日期:2014-11-22 00:00:00
abstract:BACKGROUND:The primary aim of this study was to provide an estimate of effect size for the functional outcome of operative versus non-operative treatment for patients with an acute rupture of the Achilles tendon using accelerated rehabilitation for both groups of patients. The secondary aim was to assess the use of a c...
journal_title:BMC medical research methodology
pub_type: 杂志文章,随机对照试验
doi:10.1186/1471-2288-11-39
更新日期:2011-04-05 00:00:00
abstract:BACKGROUND:Compliance is a critical issue for parental questionnaires in school based epidemiological surveys and high compliance is difficult to achieve. The objective of this study was to determine trends and factors associated with parental questionnaire compliance during respiratory health surveys of school childre...
journal_title:BMC medical research methodology
pub_type: 杂志文章
doi:10.1186/1471-2288-12-53
更新日期:2012-04-20 00:00:00
abstract:BACKGROUND:Multi-centre randomized controlled clinical trials play an important role in modern evidence-based medicine. Advantages of collecting data from more than one site are numerous, including accelerated recruitment and increased generalisability of results. Mixed models can be applied to account for potential cl...
journal_title:BMC medical research methodology
pub_type: 杂志文章
doi:10.1186/s12874-018-0602-y
更新日期:2018-11-29 00:00:00
abstract:BACKGROUND:When discussing results medical research articles often tear substantive and statistical (methodical) contributions apart, just as if both were independent. Consequently, reasoning on bias tends to be vague, unclear and superficial. This can lead to over-generalized, too narrow and misleading conclusions, es...
journal_title:BMC medical research methodology
pub_type: 杂志文章,评审
doi:10.1186/s12874-018-0490-1
更新日期:2018-04-17 00:00:00
abstract:BACKGROUND:Postal self-completion questionnaires offer one of the least expensive modes of collecting patient based outcomes in health care research. The purpose of this review is to assess the efficacy of methods of increasing response to postal questionnaires in health care studies on patient populations. METHODS:Th...
journal_title:BMC medical research methodology
pub_type: 杂志文章,评审
doi:10.1186/1471-2288-6-5
更新日期:2006-02-23 00:00:00
abstract:BACKGROUND:This research aims to explore an identified gap in implementation science methodology, that is, how to assess context in implementation research. Context is among the strongest influences on implementation success but is a construct that is poorly understood and reported within the literature. Consequently, ...
journal_title:BMC medical research methodology
pub_type: 杂志文章
doi:10.1186/s12874-020-01044-5
更新日期:2020-06-15 00:00:00
abstract:BACKGROUND:Studies have shown that industry-sponsored meta-analyses of drugs lack scientific rigour and have biased conclusions. However, these studies have been restricted to certain medical specialities. We compared all industry-supported meta-analyses of drug-drug comparisons with those without industry support. ME...
journal_title:BMC medical research methodology
pub_type: 杂志文章
doi:10.1186/1471-2288-8-60
更新日期:2008-09-09 00:00:00