There is no such thing as a validated prediction model

External validation of models for predicting cumulative live birth over multiple complete cycles of IVF treatment

STUDY QUESTION

Can two prediction models developed using data from 1999 to 2009 accurately predict the cumulative probability of live birth per woman over multiple complete cycles of IVF in an updated UK cohort?

SUMMARY ANSWER

After being updated, the models were able to estimate individualized chances of cumulative live birth over multiple complete cycles of IVF with greater accuracy.

WHAT IS KNOWN ALREADY

The McLernon models were the first to predict cumulative live birth over multiple complete cycles of IVF. They were converted into an online calculator called OPIS (Outcome Prediction In Subfertility) which has 3000 users per month on average. A previous study externally validated the McLernon models using a Dutch prospective cohort containing data from 2011 to 2014. With changes in IVF practice over time, it is important that the McLernon models are externally validated on a more recent cohort of patients to ensure that predictions remain accurate.

STUDY DESIGN, SIZE, DURATION

A population-based cohort of 91 035 women undergoing IVF in the UK between January 2010 and December 2016 was used for external validation. Data on frozen embryo transfers associated with these complete IVF cycles conducted from 1 January 2017 to 31 December 2017 were also collected.

PARTICIPANTS/MATERIALS, SETTING, METHODS

Data on IVF treatments were obtained from the Human Fertilisation and Embryology Authority (HFEA). The predictive performances of the McLernon models were evaluated in terms of discrimination and calibration. Discrimination was assessed using the c-statistic and calibration was assessed using calibration-in-the-large, calibration slope, and calibration plots. Where any model demonstrated poor calibration in the validation cohort, the models were updated using intercept recalibration, logistic recalibration, or model revision to improve model performance.

MAIN RESULTS AND THE ROLE OF CHANCE

Following exclusions, 91 035 women who underwent 144 734 complete cycles were included. The validation cohort had a similar distribution age profile to women in the development cohort. Live birth rates over all complete cycles of IVF per woman were higher in the validation cohort. After calibration assessment, both models required updating. The coefficients of the pre-treatment model were revised, and the updated model showed reasonable discrimination (c-statistic: 0.67, 95% CI: 0.66 to 0.68). After logistic recalibration, the post-treatment model showed good discrimination (c-statistic: 0.75, 95% CI: 0.74 to 0.76). As an example, in the updated pre-treatment model, a 32-year-old woman with 2 years of primary infertility has a 42% chance of having a live birth in the first complete ICSI cycle and a 77% chance over three complete cycles. In a couple with 2 years of primary male factor infertility where a 30-year-old woman has 15 oocytes collected in the first cycle, a single fresh blastocyst embryo transferred in the first cycle and spare embryos cryopreserved, the estimated chance of live birth provided by the post-treatment model is 46% in the first complete ICSI cycle and 81% over three complete cycles.

LIMITATIONS, REASONS FOR CAUTION

Two predictors from the original models, duration of infertility and previous pregnancy, which were not available in the recent HFEA dataset, were imputed using data from the older cohort used to develop the models. The HFEA dataset does not contain some other potentially important predictors, e.g. BMI, ethnicity, race, smoking and alcohol intake in women, as well as measures of ovarian reserve such as antral follicle count.

WIDER IMPLICATIONS OF THE FINDINGS

Both updated models show improved predictive ability and provide estimates which are more reflective of current practice and patient case mix. The updated OPIS tool can be used by clinicians to help shape couples' expectations by informing them of their individualized chances of live birth over a sequence of multiple complete cycles of IVF.

STUDY FUNDING/COMPETING INTEREST(S)

This study was supported by an Elphinstone scholarship scheme at the University of Aberdeen and Aberdeen Fertility Centre, University of Aberdeen. S.B. has a commitment of research funding from Merck. D.J.M. and M.B.R. declare support for the present manuscript from Elphinstone scholarship scheme at the University of Aberdeen and Assisted Reproduction Unit at Aberdeen Fertility Centre, University of Aberdeen. D.J.M. declares grants received by University of Aberdeen from NHS Grampian, The Meikle Foundation, and Chief Scientist Office in the past 3 years. D.J.M. declares receiving an honorarium for lectures from Merck. D.J.M. is Associate Editor of Human Reproduction Open and Statistical Advisor for Reproductive BioMed Online. S.B. declares royalties from Cambridge University Press for a book. S.B. declares receiving an honorarium for lectures from Merck, Organon, Ferring, Obstetric and Gynaecological Society of Singapore, and Taiwanese Society for Reproductive Medicine. S.B. has received support from Merck, ESHRE, and Ferring for attending meetings as speaker and is on the METAFOR and CAPRE Trials Data Monitoring Committee.

TRIAL REGISTRATION NUMBER

N/A.

Implications of the Use of Artificial Intelligence Predictive Models in Health Care Settings : A Simulation Study

BACKGROUND

Substantial effort has been directed toward demonstrating uses of predictive models in health care. However, implementation of these models into clinical practice may influence patient outcomes, which in turn are captured in electronic health record data. As a result, deployed models may affect the predictive ability of current and future models.

OBJECTIVE

To estimate changes in predictive model performance with use through 3 common scenarios: model retraining, sequentially implementing 1 model after another, and intervening in response to a model when 2 are simultaneously implemented.

DESIGN

Simulation of model implementation and use in critical care settings at various levels of intervention effectiveness and clinician adherence. Models were either trained or retrained after simulated implementation.

SETTING

Admissions to the intensive care unit (ICU) at Mount Sinai Health System (New York, New York) and Beth Israel Deaconess Medical Center (Boston, Massachusetts).

PATIENTS

130 000 critical care admissions across both health systems.

INTERVENTION

Across 3 scenarios, interventions were simulated at varying levels of clinician adherence and effectiveness.

MEASUREMENTS

Statistical measures of performance, including threshold-independent (area under the curve) and threshold-dependent measures.

RESULTS

At fixed 90% sensitivity, in scenario 1 a mortality prediction model lost 9% to 39% specificity after retraining once and in scenario 2 a mortality prediction model lost 8% to 15% specificity when created after the implementation of an acute kidney injury (AKI) prediction model; in scenario 3, models for AKI and mortality prediction implemented simultaneously, each led to reduced effective accuracy of the other by 1% to 28%.

LIMITATIONS

In real-world practice, the effectiveness of and adherence to model-based recommendations are rarely known in advance. Only binary classifiers for tabular ICU admissions data were simulated.

CONCLUSION

In simulated ICU settings, a universally effective model-updating approach for maintaining model performance does not seem to exist. Model use may have to be recorded to maintain viability of predictive modeling.

PRIMARY FUNDING SOURCE

National Center for Advancing Translational Sciences.

APPRAISE-AI Tool for Quantitative Evaluation of AI Studies for Clinical Decision Support

Importance

Artificial intelligence (AI) has gained considerable attention in health care, yet concerns have been raised around appropriate methods and fairness. Current AI reporting guidelines do not provide a means of quantifying overall quality of AI research, limiting their ability to compare models addressing the same clinical question.

Objective

To develop a tool (APPRAISE-AI) to evaluate the methodological and reporting quality of AI prediction models for clinical decision support.

Design, Setting, and Participants

This quality improvement study evaluated AI studies in the model development, silent, and clinical trial phases using the APPRAISE-AI tool, a quantitative method for evaluating quality of AI studies across 6 domains: clinical relevance, data quality, methodological conduct, robustness of results, reporting quality, and reproducibility. These domains included 24 items with a maximum overall score of 100 points. Points were assigned to each item, with higher points indicating stronger methodological or reporting quality. The tool was applied to a systematic review on machine learning to estimate sepsis that included articles published until September 13, 2019. Data analysis was performed from September to December 2022.

Main Outcomes and Measures

The primary outcomes were interrater and intrarater reliability and the correlation between APPRAISE-AI scores and expert scores, 3-year citation rate, number of Quality Assessment of Diagnostic Accuracy Studies (QUADAS-2) low risk-of-bias domains, and overall adherence to the Transparent Reporting of a Multivariable Prediction Model for Individual Prognosis or Diagnosis (TRIPOD) statement.

Results

A total of 28 studies were included. Overall APPRAISE-AI scores ranged from 33 (low quality) to 67 (high quality). Most studies were moderate quality. The 5 lowest scoring items included source of data, sample size calculation, bias assessment, error analysis, and transparency. Overall APPRAISE-AI scores were associated with expert scores (Spearman ρ, 0.82; 95% CI, 0.64-0.91; P < .001), 3-year citation rate (Spearman ρ, 0.69; 95% CI, 0.43-0.85; P < .001), number of QUADAS-2 low risk-of-bias domains (Spearman ρ, 0.56; 95% CI, 0.24-0.77; P = .002), and adherence to the TRIPOD statement (Spearman ρ, 0.87; 95% CI, 0.73-0.94; P < .001). Intraclass correlation coefficient ranges for interrater and intrarater reliability were 0.74 to 1.00 for individual items, 0.81 to 0.99 for individual domains, and 0.91 to 0.98 for overall scores.

Conclusions and Relevance

In this quality improvement study, APPRAISE-AI demonstrated strong interrater and intrarater reliability and correlated well with several study quality measures. This tool may provide a quantitative approach for investigators, reviewers, editors, and funding organizations to compare the research quality across AI studies for clinical decision support.

Evidence of questionable research practices in clinical prediction models

BACKGROUND

Clinical prediction models are widely used in health and medical research. The area under the receiver operating characteristic curve (AUC) is a frequently used estimate to describe the discriminatory ability of a clinical prediction model. The AUC is often interpreted relative to thresholds, with "good" or "excellent" models defined at 0.7, 0.8 or 0.9. These thresholds may create targets that result in "hacking", where researchers are motivated to re-analyse their data until they achieve a "good" result.

METHODS

We extracted AUC values from PubMed abstracts to look for evidence of hacking. We used histograms of the AUC values in bins of size 0.01 and compared the observed distribution to a smooth distribution from a spline.

RESULTS

The distribution of 306,888 AUC values showed clear excesses above the thresholds of 0.7, 0.8 and 0.9 and shortfalls below the thresholds.

CONCLUSIONS

The AUCs for some models are over-inflated, which risks exposing patients to sub-optimal clinical decision-making. Greater modelling transparency is needed, including published protocols, and data and code sharing.

AI and machine learning in resuscitation: Ongoing research, new concepts, and key challenges

Aim

Artificial intelligence (AI) and machine learning (ML) are important areas of computer science that have recently attracted attention for their application to medicine. However, as techniques continue to advance and become more complex, it is increasingly challenging for clinicians to stay abreast of the latest research. This overview aims to translate research concepts and potential concerns to healthcare professionals interested in applying AI and ML to resuscitation research but who are not experts in the field.

Main text

We present various research including prediction models using structured and unstructured data, exploring treatment heterogeneity, reinforcement learning, language processing, and large-scale language models. These studies potentially offer valuable insights for optimizing treatment strategies and clinical workflows. However, implementing AI and ML in clinical settings presents its own set of challenges. The availability of high-quality and reliable data is crucial for developing accurate ML models. A rigorous validation process and the integration of ML into clinical practice is essential for practical implementation. We furthermore highlight the potential risks associated with self-fulfilling prophecies and feedback loops, emphasizing the importance of transparency, interpretability, and trustworthiness in AI and ML models. These issues need to be addressed in order to establish reliable and trustworthy AI and ML models.

Conclusion

In this article, we overview concepts and examples of AI and ML research in the resuscitation field. Moving forward, appropriate understanding of ML and collaboration with relevant experts will be essential for researchers and clinicians to overcome the challenges and harness the full potential of AI and ML in resuscitation.

Morphometry-based radiomics for predicting therapeutic response in patients with gliomas following radiotherapy

Introduction

Gliomas are still considered as challenging in oncologic management despite the developments in treatment approaches. The complete elimination of a glioma might not be possible even after a treatment and assessment of therapeutic response is important to determine the future course of actions for patients with such cancers. In the recent years radiomics has emerged as a promising solution with potential applications including prediction of therapeutic response. Hence, this study was focused on investigating whether morphometry-based radiomics signature could be used to predict therapeutic response in patients with gliomas following radiotherapy.

Methods

105 magnetic resonance (MR) images including segmented and non-segmented images were used to extract morphometric features and develop a morphometry-based radiomics signature. After determining the appropriate machine learning algorithm, a prediction model was developed to predict the therapeutic response eliminating the highly correlated features as well as without eliminating the highly correlated features. Then the model performance was evaluated.

Results

Tumor grade had the highest contribution to develop the morphometry-based signature. Random forest provided the highest accuracy to train the prediction model derived from the morphometry-based radiomics signature. An accuracy of 86% and area under the curve (AUC) value of 0.91 were achieved for the prediction model evaluated without eliminating the highly correlated features whereas accuracy and AUC value were 84% and 0.92 respectively for the prediction model evaluated after eliminating the highly correlated features.

Discussion

Nonetheless, the developed morphometry-based radiomics signature could be utilized as a noninvasive biomarker for therapeutic response in patients with gliomas following radiotherapy.

Clinical Validity of a Machine Learning Decision Support System for Early Detection of Hepatitis B Virus: A Binational External Validation Study

HepB LiveTest is a machine learning decision support system developed for the early detection of hepatitis B virus (HBV). However, there is a lack of evidence on its generalisability. In this study, we aimed to externally assess the clinical validity and portability of HepB LiveTest in predicting HBV infection among independent patient cohorts from Nigeria and Australia. The performance of HepB LiveTest was evaluated by constructing receiver operating characteristic curves and estimating the area under the curve. Delong's method was used to estimate the 95% confidence interval (CI) of the area under the receiver-operating characteristic curve (AUROC). Compared to the Australian cohort, patients in the derivation cohort of HepB LiveTest and the hospital-based Nigerian cohort were younger (mean age, 45.5 years vs. 38.8 years vs. 40.8 years, respectively; p < 0.001) and had a higher incidence of HBV infection (1.9% vs. 69.4% vs. 57.3%). In the hospital-based Nigerian cohort, HepB LiveTest performed optimally with an AUROC of 0.94 (95% CI, 0.91-0.97). The model provided tailored predictions that ensured most cases of HBV infection did not go undetected. However, its discriminatory measure dropped to 0.60 (95% CI, 0.56-0.64) in the Australian cohort. These findings indicate that HepB LiveTest exhibits adequate cross-site transportability and clinical validity in the hospital-based Nigerian patient cohort but shows limited performance in the Australian cohort. Whilst HepB LiveTest holds promise for reducing HBV prevalence in underserved populations, caution is warranted when implementing the model in older populations, particularly in regions with low incidence of HBV infection.

Identifying older adults at increased risk of medication-related readmission to hospital within 30 days of discharge: development and validation of a risk assessment tool

OBJECTIVE

Developing and validating a risk assessment tool aiming to identify older adults (≥65 years) at increased risk of possibly medication-related readmission to hospital within 30 days of discharge.

DESIGN

Retrospective cohort study.

SETTING

The risk score was developed using data from a hospital in southern Sweden and validated using data from four hospitals in the mid-eastern part of Sweden.

PARTICIPANTS

The development cohort (n=720) was admitted to hospital during 2017, whereas the validation cohort (n=892) was admitted during 2017-2018.

MEASURES

The risk assessment tool aims to predict possibly medication-related readmission to hospital within 30 days of discharge. Variables known at first admission and individually associated with possibly medication-related readmission were used in development. The included variables were assigned points, and Youden's index was used to decide a threshold score. The risk score was calculated for all individuals in both cohorts. Area under the receiver operating characteristic (ROC) curve (c-index) was used to measure the discrimination of the developed risk score. Sensitivity, specificity and positive and negative predictive values were calculated using cross-tabulation.

RESULTS

The developed risk assessment tool, the Hospitalisations, Own home, Medications, and Emergency admission (HOME) Score, had a c-index of 0.69 in the development cohort and 0.65 in the validation cohort. It showed sensitivity 76%, specificity 54%, positive predictive value 29% and negative predictive value 90% at the threshold score in the development cohort.

CONCLUSION

The HOME Score can be used to identify older adults at increased risk of possibly medication-related readmission within 30 days of discharge. The tool is easy to use and includes variables available in electronic health records at admission, thus making it possible to implement risk-reducing activities during the hospital stay as well as at discharge and in transitions of care. Further studies are needed to investigate the clinical usefulness of the HOME Score as well as the benefits of implemented activities.