From hype to reality: data science enabling personalized medicine

From genotype to phenotype in Arabidopsis thaliana: in-silico genome interpretation predicts 288 phenotypes from sequencing data

In many cases, the unprecedented availability of data provided by high-throughput sequencing has shifted the bottleneck from a data availability issue to a data interpretation issue, thus delaying the promised breakthroughs in genetics and precision medicine, for what concerns Human genetics, and phenotype prediction to improve plant adaptation to climate change and resistance to bioagressors, for what concerns plant sciences. In this paper, we propose a novel Genome Interpretation paradigm, which aims at directly modeling the genotype-to-phenotype relationship, and we focus on A. thaliana since it is the best studied model organism in plant genetics. Our model, called Galiana, is the first end-to-end Neural Network (NN) approach following the genomes in/phenotypes out paradigm and it is trained to predict 288 real-valued Arabidopsis thaliana phenotypes from Whole Genome sequencing data. We show that 75 of these phenotypes are predicted with a Pearson correlation ≥0.4, and are mostly related to flowering traits. We show that our end-to-end NN approach achieves better performances and larger phenotype coverage than models predicting single phenotypes from the GWAS-derived known associated genes. Galiana is also fully interpretable, thanks to the Saliency Maps gradient-based approaches. We followed this interpretation approach to identify 36 novel genes that are likely to be associated with flowering traits, finding evidence for 6 of them in the existing literature.

The perspective of IT decision makers on factors influencing adoption and implementation of AI-technologies in 40 German Hospitals: Descriptive Analysis (Preprint)

Background

New artificial intelligence (AI) tools are being developed at a high speed. However, strategies and practical experiences surrounding the adoption and implementation of AI in health care are lacking. This is likely because of the high implementation complexity of AI, legacy IT infrastructure, and unclear business cases, thus complicating AI adoption. Research has recently started to identify the factors influencing AI readiness of organizations.

Objective

This study aimed to investigate the factors influencing AI readiness as well as possible barriers to AI adoption and implementation in German hospitals. We also assessed the status quo regarding the dissemination of AI tools in hospitals. We focused on IT decision makers, a seldom studied but highly relevant group.

Methods

We created a web-based survey based on recent AI readiness and implementation literature. Participants were identified through a publicly accessible database and contacted via email or invitational leaflets sent by mail, in some cases accompanied by a telephonic prenotification. The survey responses were analyzed using descriptive statistics.

Results

We contacted 609 possible participants, and our database recorded 40 completed surveys. Most participants agreed or rather agreed with the statement that AI would be relevant in the future, both in Germany (37/40, 93%) and in their own hospital (36/40, 90%). Participants were asked whether their hospitals used or planned to use AI technologies. Of the 40 participants, 26 (65%) answered “yes.” Most AI technologies were used or planned for patient care, followed by biomedical research, administration, and logistics and central purchasing. The most important barriers to AI were lack of resources (staff, knowledge, and financial). Relevant possible opportunities for using AI were increase in efficiency owing to time-saving effects, competitive advantages, and increase in quality of care. Most AI tools in use or in planning have been developed with external partners.

Conclusions

Few tools have been implemented in routine care, and many hospitals do not use or plan to use AI in the future. This can likely be explained by missing or unclear business cases or the need for a modern IT infrastructure to integrate AI tools in a usable manner. These shortcomings complicate decision-making and resource attribution. As most AI technologies already in use were developed in cooperation with external partners, these relationships should be fostered. IT decision makers should assess their hospitals’ readiness for AI individually with a focus on resources. Further research should continue to monitor the dissemination of AI tools and readiness factors to determine whether improvements can be made over time. This monitoring is especially important with regard to government-supported investments in AI technologies that could alleviate financial burdens. Qualitative studies with hospital IT decision makers should be conducted to further explore the reasons for slow AI.

Machine Learning Consensus Clustering Approach for Patients with Lactic Acidosis in Intensive Care Units

BACKGROUND

Lactic acidosis is a heterogeneous condition with multiple underlying causes and associated outcomes. The use of multi-dimensional patient data to subtype lactic acidosis can personalize patient care. Machine learning consensus clustering may identify lactic acidosis subgroups with unique clinical profiles and outcomes.

METHODS

We used the Medical Information Mart for Intensive Care III database to abstract electronic medical record data from patients admitted to intensive care units (ICU) in a tertiary care hospital in the United States. We included patients who developed lactic acidosis (defined as serum lactate ≥ 4 mmol/L) within 48 h of ICU admission. We performed consensus clustering analysis based on patient characteristics, comorbidities, vital signs, organ supports, and laboratory data to identify clinically distinct lactic acidosis subgroups. We calculated standardized mean differences to show key subgroup features. We compared outcomes among subgroups.

RESULTS

We identified 1919 patients with lactic acidosis. The algorithm revealed three best unique lactic acidosis subgroups based on patient variables. Cluster 1 (n = 554) was characterized by old age, elective admission to cardiac surgery ICU, vasopressor use, mechanical ventilation use, and higher pH and serum bicarbonate. Cluster 2 (n = 815) was characterized by young age, admission to trauma/surgical ICU with higher blood pressure, lower comorbidity burden, lower severity index, and less vasopressor use. Cluster 3 (n = 550) was characterized by admission to medical ICU, history of liver disease and coagulopathy, acute kidney injury, lower blood pressure, higher comorbidity burden, higher severity index, higher serum lactate, and lower pH and serum bicarbonate. Cluster 3 had the worst outcomes, while cluster 1 had the most favorable outcomes in terms of persistent lactic acidosis and mortality.

CONCLUSIONS

Consensus clustering analysis synthesized the pattern of clinical and laboratory data to reveal clinically distinct lactic acidosis subgroups with different outcomes.

Machine Learning Prediction Models for Mortality in Intensive Care Unit Patients with Lactic Acidosis

Background: Lactic acidosis is the most common cause of anion gap metabolic acidosis in the intensive care unit (ICU), associated with poor outcomes including mortality. We sought to compare machine learning (ML) approaches versus logistic regression analysis for prediction of mortality in lactic acidosis patients admitted to the ICU. Methods: We used the Medical Information Mart for Intensive Care (MIMIC-III) database to identify ICU adult patients with lactic acidosis (serum lactate ≥4 mmol/L). The outcome of interest was hospital mortality. We developed prediction models using four ML approaches consisting of random forest (RF), decision tree (DT), extreme gradient boosting (XGBoost), artificial neural network (ANN), and statistical modeling with forward stepwise logistic regression using the testing dataset. We then assessed model performance using area under the receiver operating characteristic curve (AUROC), accuracy, precision, error rate, Matthews correlation coefficient (MCC), F1 score, and assessed model calibration using the Brier score, in the independent testing dataset. Results: Of 1919 lactic acidosis ICU patients, 1535 and 384 were included in the training and testing dataset, respectively. Hospital mortality was 30%. RF had the highest AUROC at 0.83, followed by logistic regression 0.81, XGBoost 0.81, ANN 0.79, and DT 0.71. In addition, RF also had the highest accuracy (0.79), MCC (0.45), F1 score (0.56), and lowest error rate (21.4%). The RF model was the most well-calibrated. The Brier score for RF, DT, XGBoost, ANN, and multivariable logistic regression was 0.15, 0.19, 0.18, 0.19, and 0.16, respectively. The RF model outperformed multivariable logistic regression model, SOFA score (AUROC 0.74), SAP II score (AUROC 0.77), and Charlson score (AUROC 0.69). Conclusion: The ML prediction model using RF algorithm provided the highest predictive performance for hospital mortality among ICU patient with lactic acidosis.

Mitigating Burnout in an Oncological Unit: A Scoping Review

Objectives: The purpose of this study was to provide a scoping review on how to address and mitigate burnout in the profession of clinical oncology. Also, it examines how artificial intelligence (AI) can mitigate burnout in oncology. Methods: We searched Ovid Medline, PubMed, Scopus, and Web of Science, for articles that examine how to address burnout in oncology. Results: A total of 17 studies were found to examine how burnout in oncology can be mitigated. These interventions were either targeted at individuals (oncologists) or organizations where the oncologists work. The organizational interventions include educational (psychosocial and mindfulness-based course), art therapies and entertainment, team-based training, group meetings, motivational package and reward, effective leadership and policy change, and staff support. The individual interventions include equipping the oncologists with adequate training that include-communication skills, well-being and stress management, burnout education, financial independence, relaxation, self-efficacy, resilience, hobby adoption, and work-life balance for the oncologists. Similarly, AI is thought to be poised to offer the potential to mitigate burnout in oncology by enhancing the productivity and performance of the oncologists, reduce the workload and provide job satisfaction, and foster teamwork between the caregivers of patients with cancer. Discussion: Burnout is common among oncologists and can be elicited from different types of situations encountered in the process of caring for patients with cancer. Therefore, for these interventions to achieve the touted benefits, combinatorial strategies that combine other interventions may be viable for mitigating burnout in oncology. With the potential of AI to mitigate burnout, it is important for healthcare providers to facilitate its use in daily clinical practices. Conclusion: These combinatorial interventions can ensure job satisfaction, a supportive working environment, job retention for oncologists, and improved patient care. These interventions could be integrated systematically into routine cancer care for a positive impact on quality care, patient satisfaction, the overall success of the oncological ward, and the health organizations at large.

A Machine Learning Application to Predict Early Lung Involvement in Scleroderma: A Feasibility Evaluation

Introduction: Systemic sclerosis (SSc) is a systemic immune-mediated disease, featuring fibrosis of the skin and organs, and has the greatest mortality among rheumatic diseases. The nervous system involvement has recently been demonstrated, although actual lung involvement is considered the leading cause of death in SSc and, therefore, should be diagnosed early. Pulmonary function tests are not sensitive enough to be used for screening purposes, thus they should be flanked by other clinical examinations; however, this would lead to a risk of overtesting, with considerable costs for the health system and an unnecessary burden for the patients. To this extent, Machine Learning (ML) algorithms could represent a useful add-on to the current clinical practice for diagnostic purposes and could help retrieve the most useful exams to be carried out for diagnostic purposes. Method: Here, we retrospectively collected high resolution computed tomography, pulmonary function tests, esophageal pH impedance tests, esophageal manometry and reflux disease questionnaires of 38 patients with SSc, applying, with R, different supervised ML algorithms, including lasso, ridge, elastic net, classification and regression trees (CART) and random forest to estimate the most important predictors for pulmonary involvement from such data. Results: In terms of performance, the random forest algorithm outperformed the other classifiers, with an estimated root-mean-square error (RMSE) of 0.810. However, this algorithm was seen to be computationally intensive, leaving room for the usefulness of other classifiers when a shorter response time is needed. Conclusions: Despite the notably small sample size, that could have prevented obtaining fully reliable data, the powerful tools available for ML can be useful for predicting early lung involvement in SSc patients. The use of predictors coming from spirometry and pH impedentiometry together might perform optimally for predicting early lung involvement in SSc.

Machine Learning Consensus Clustering Approach for Hospitalized Patients with Phosphate Derangements

BACKGROUND

The goal of this study was to categorize patients with abnormal serum phosphate upon hospital admission into distinct clusters utilizing an unsupervised machine learning approach, and to assess the mortality risk associated with these clusters.

METHODS

We utilized the consensus clustering approach on demographic information, comorbidities, principal diagnoses, and laboratory data of hypophosphatemia (serum phosphate ≤ 2.4 mg/dL) and hyperphosphatemia cohorts (serum phosphate ≥ 4.6 mg/dL). The standardized mean difference was applied to determine each cluster's key features. We assessed the association of the clusters with mortality.

RESULTS

In the hypophosphatemia cohort (n = 3113), the consensus cluster analysis identified two clusters. The key features of patients in Cluster 2, compared with Cluster 1, included: older age; a higher comorbidity burden, particularly hypertension; diabetes mellitus; coronary artery disease; lower eGFR; and more acute kidney injury (AKI) at admission. Cluster 2 had a comparable hospital mortality (3.7% vs. 2.9%; p = 0.17), but a higher one-year mortality (26.8% vs. 14.0%; p < 0.001), and five-year mortality (20.2% vs. 44.3%; p < 0.001), compared to Cluster 1. In the hyperphosphatemia cohort (n = 7252), the analysis identified two clusters. The key features of patients in Cluster 2, compared with Cluster 1, included: older age; more primary admission for kidney disease; more history of hypertension; more end-stage kidney disease; more AKI at admission; and higher admission potassium, magnesium, and phosphate. Cluster 2 had a higher hospital (8.9% vs. 2.4%; p < 0.001) one-year mortality (32.9% vs. 14.8%; p < 0.001), and five-year mortality (24.5% vs. 51.1%; p < 0.001), compared with Cluster 1.

CONCLUSION

Our cluster analysis classified clinically distinct phenotypes with different mortality risks among hospitalized patients with serum phosphate derangements. Age, comorbidities, and kidney function were the key features that differentiated the phenotypes.

Fabrication approaches for high-throughput and biomimetic disease modeling

There is often a tradeoff between in vitro disease modeling platforms that capture pathophysiologic complexity and those that are amenable to high-throughput fabrication and analysis. However, this divide is closing through the application of a handful of fabrication approaches-parallel fabrication, automation, and flow-driven assembly-to design sophisticated cellular and biomaterial systems. The purpose of this review is to highlight methods for the fabrication of high-throughput biomaterial-based platforms and showcase examples that demonstrate their utility over a range of throughput and complexity. We conclude with a discussion of future considerations for the continued development of higher-throughput in vitro platforms that capture the appropriate level of biological complexity for the desired application. STATEMENT OF SIGNIFICANCE: There is a pressing need for new biomedical tools to study and understand disease. These platforms should mimic the complex properties of the body while also permitting investigation of many combinations of cells, extracellular cues, and/or therapeutics in high-throughput. This review summarizes emerging strategies to fabricate biomimetic disease models that bridge the gap between complex tissue-mimicking microenvironments and high-throughput screens for personalized medicine.

Data analysis with Shapley values for automatic subject selection in Alzheimer's disease data sets using interpretable machine learning

BACKGROUND

For the recruitment and monitoring of subjects for therapy studies, it is important to predict whether mild cognitive impaired (MCI) subjects will prospectively develop Alzheimer's disease (AD). Machine learning (ML) is suitable to improve early AD prediction. The etiology of AD is heterogeneous, which leads to high variability in disease patterns. Further variability originates from multicentric study designs, varying acquisition protocols, and errors in the preprocessing of magnetic resonance imaging (MRI) scans. The high variability makes the differentiation between signal and noise difficult and may lead to overfitting. This article examines whether an automatic and fair data valuation method based on Shapley values can identify the most informative subjects to improve ML classification.

METHODS

An ML workflow was developed and trained for a subset of the Alzheimer's Disease Neuroimaging Initiative (ADNI) cohort. The validation was executed for an independent ADNI test set and for the Australian Imaging, Biomarker and Lifestyle Flagship Study of Ageing (AIBL) cohort. The workflow included volumetric MRI feature extraction, feature selection, sample selection using Data Shapley, random forest (RF), and eXtreme Gradient Boosting (XGBoost) for model training as well as Kernel SHapley Additive exPlanations (SHAP) values for model interpretation.

RESULTS

The RF models, which excluded 134 of the 467 training subjects based on their RF Data Shapley values, outperformed the base models that reached a mean accuracy of 62.64% by 5.76% (3.61 percentage points) for the independent ADNI test set. The XGBoost base models reached a mean accuracy of 60.00% for the AIBL data set. The exclusion of those 133 subjects with the smallest RF Data Shapley values could improve the classification accuracy by 2.98% (1.79 percentage points). The cutoff values were calculated using an independent validation set.

CONCLUSION

The Data Shapley method was able to improve the mean accuracies for the test sets. The most informative subjects were associated with the number of ApolipoproteinE ε4 (ApoE ε4) alleles, cognitive test results, and volumetric MRI measurements.

Great future or greedy venture: Precision medicine needs philosophy

INTRODUCTION

Over the past decade, we have witnessed the initiation and implementation of precision medicine (PM), a discipline that promises to individualize and personalize medical management and treatment, rendering them ultimately more precise and effective. Despite of the continuing advances and numerous clinical applications, the potential of PM remains highly controversial, sparking heated debates about its future.

METHOD

The present article reviews the philosophical issues and practical challenges that are critical to the feasibility and implementation of PM.

OUTCOME

The explanation and argument about the relations between PM and computability, uncertainty as well as complexity, show that key foundational assumptions of PM might not be fully validated.

CONCLUSION

The present analysis suggests that our current understanding of PM is probably oversimplified and too superficial. More efforts are needed to realize the hope that PM has elicited, rather than make the term just as a hype.

Caution, "normal" BMI: health risks associated with potentially masked individual underweight-EPMA Position Paper 2021

An increasing interest in a healthy lifestyle raises questions about optimal body weight. Evidently, it should be clearly discriminated between the standardised "normal" body weight and individually optimal weight. To this end, the basic principle of personalised medicine "one size does not fit all" has to be applied. Contextually, "normal" but e.g. borderline body mass index might be optimal for one person but apparently suboptimal for another one strongly depending on the individual genetic predisposition, geographic origin, cultural and nutritional habits and relevant lifestyle parameters-all included into comprehensive individual patient profile. Even if only slightly deviant, both overweight and underweight are acknowledged risk factors for a shifted metabolism which, if being not optimised, may strongly contribute to the development and progression of severe pathologies. Development of innovative screening programmes is essential to promote population health by application of health risks assessment, individualised patient profiling and multi-parametric analysis, further used for cost-effective targeted prevention and treatments tailored to the person. The following healthcare areas are considered to be potentially strongly benefiting from the above proposed measures: suboptimal health conditions, sports medicine, stress overload and associated complications, planned pregnancies, periodontal health and dentistry, sleep medicine, eye health and disorders, inflammatory disorders, healing and pain management, metabolic disorders, cardiovascular disease, cancers, psychiatric and neurologic disorders, stroke of known and unknown aetiology, improved individual and population outcomes under pandemic conditions such as COVID-19. In a long-term way, a significantly improved healthcare economy is one of benefits of the proposed paradigm shift from reactive to Predictive, Preventive and Personalised Medicine (PPPM/3PM). A tight collaboration between all stakeholders including scientific community, healthcare givers, patient organisations, policy-makers and educators is essential for the smooth implementation of 3PM concepts in daily practice.

The promise of precision medicine in autism

Autism spectrum disorder (ASD) is a clinically and etiologically diverse developmental condition characterized by diminished social interactions, impaired communication, and repetitive and/or restrictive behaviors. Recent advances in ASD genetics pave the way for implementation of precision medicine in clinical management of autism.

Interpretable deep recommender system model for prediction of kinase inhibitor efficacy across cancer cell lines

Computational models for drug sensitivity prediction have the potential to significantly improve personalized cancer medicine. Drug sensitivity assays, combined with profiling of cancer cell lines and drugs become increasingly available for training such models. Multiple methods were proposed for predicting drug sensitivity from cancer cell line features, some in a multi-task fashion. So far, no such model leveraged drug inhibition profiles. Importantly, multi-task models require a tailored approach to model interpretability. In this work, we develop DEERS, a neural network recommender system for kinase inhibitor sensitivity prediction. The model utilizes molecular features of the cancer cell lines and kinase inhibition profiles of the drugs. DEERS incorporates two autoencoders to project cell line and drug features into 10-dimensional hidden representations and a feed-forward neural network to combine them into response prediction. We propose a novel interpretability approach, which in addition to the set of modeled features considers also the genes and processes outside of this set. Our approach outperforms simpler matrix factorization models, achieving R [Formula: see text] 0.82 correlation between true and predicted response for the unseen cell lines. The interpretability analysis identifies 67 biological processes that drive the cell line sensitivity to particular compounds. Detailed case studies are shown for PHA-793887, XMD14-99 and Dabrafenib.

Towards realizing the vision of precision medicine: AI based prediction of clinical drug response

Accurate and individualized prediction of response to therapies is central to precision medicine. However, because of the generally complex and multifaceted nature of clinical drug response, realizing this vision is highly challenging, requiring integrating different data types from the same individual into one prediction model. We used the anti-epileptic drug brivaracetam as a case study and combine a hybrid data/knowledge-driven feature extraction with machine learning to systematically integrate clinical and genetic data from a clinical discovery dataset (n = 235 patients). We constructed a model that successfully predicts clinical drug response [area under the curve (AUC) = 0.76] and show that even with limited sample size, integrating high-dimensional genetics data with clinical data can inform drug response prediction. After further validation on data collected from an independently conducted clinical study (AUC = 0.75), we extensively explore our model to gain insights into the determinants of drug response, and identify various clinical and genetic characteristics predisposing to poor response. Finally, we assess the potential impact of our model on clinical trial design and demonstrate that, by enriching for probable responders, significant reductions in clinical study sizes may be achieved. To our knowledge, our model represents the first retrospectively validated machine learning model linking drug mechanism of action and the genetic, clinical and demographic background in epilepsy patients to clinical drug response. Hence, it provides a blueprint for how machine learning-based multimodal data integration can act as a driver in achieving the goals of precision medicine in fields such as neurology.

Legal Challenges in Precision Medicine: What Duties Arising From Genetic and Genomic Testing Does a Physician Owe to Patients?

Precision medicine is increasingly incorporated into clinical practice via three primary data conduits: environmental, lifestyle, and genetic data. In this manuscript we take a closer look at the genetic tier of precision medicine. The volume and variety of data provides a more robust picture of health for individual patients and patient populations. However, this increased data may also have an adverse effect by muddling our understanding without the proper pedagogical tools. Patient genomic data can be challenging to work with. Physicians may encounter genetic results which are not fully understood. Genetic tests may also lead to the quandary of linking patients with diseases or disorders where there are no known treatments. Thus, physicians face a unique challenge of establishing the proper scope of their duty to patients when dealing with genomic data. Some of those scope of practice boundaries have been established as a result of litigation, while others remain an open question. In this paper, we map out some of the legal challenges facing the genomic component of precision medicine, both established and some questions requiring additional guidance. If physicians begin to perceive genomic data as falling short in overall benefit to their patients, it may detrimentally impact precision medicine as a whole. Helping to develop guidance for physicians working with patient genomic data can help avoid this fate of faltering confidence.

Modeling and Predicting the Cell Migration Properties from Scratch Wound Healing Assay on Cisplatin-Resistant Ovarian Cancer Cell Lines Using Artificial Neural Network

The study of artificial neural networks (ANN) has undergone a tremendous revolution in recent years, boosted by deep learning tools. The presence of a greater number of learning tools and their applications, in particular, favors this revolution. However, there is a significant need to deal with the issue of implementing a systematic method during the development phase of the ANN to increase its performance. A multilayer feedforward neural network (FNN) was proposed in this paper to predict the cell migration assay on cisplatin-sensitive and cisplatin-resistant (CisR) ovarian cancer (OC) cell lines via scratch wound healing assay. An FNN training algorithm model was generated using the MATLAB fitting function in a MATLAB script to accomplish this task. The input parameters were types of cell lines, times, and wound area, and outputs were relative wound area, percentage of wound closure, and wound healing speed. In addition, we tested and compared the initial accuracy of various supervised learning classifier and support vector regression (SVR) algorithms. The proposed ANN model achieved good agreement with the experimental data and minimized error between the estimated and experimental values. The conclusions drawn demonstrate that the developed ANN model is a useful, accurate, fast, and inexpensive method to predict cancerous cell migration characteristics evaluated via scratch wound healing assay.

‘It’s complicated’: Professional opacity, duality, and ambiguity—A response to Noordegraaf (2020)

In this comment to Noordegraaf’s ‘Protective or connective professionalism? How connected professionals can (still) act as autonomous and authoritative experts’, we argue that Noordegraaf has contributed significant insights into the development of contemporary professionalism. However, we argue for a less binary and more complex view of forms of professionalism, and for finding ways of understanding professionalism grounded in a relational view of everyday professional work. The first section (by Johan Alvehus) suggests that Noordegraaf’s ‘connective professionalism’ is primarily about new ways of strengthening professionalism’s protective shields by maintaining functional ambiguity and transparent opacity around professional jurisdictions. The second section (by Amalya Oliver and Netta Avnoon) argues for viewing professionalism on a range of protection–connection and offers an approach for understanding how connective and protective models co-occur. Both commentaries thus take a relational, dynamic, and somewhat skeptical view on the reproduction and maintenance of professionalism.

What Is the Persistence to Methotrexate in Rheumatoid Arthritis, and Does Machine Learning Outperform Hypothesis-Based Approaches to Its Prediction?

OBJECTIVE

The objectives of this study were to assess the 1-year persistence to methotrexate (MTX) initiated as the first ever conventional synthetic disease-modifying antirheumatic drug in new-onset rheumatoid arthritis (RA) and to investigate the marginal gains and robustness of the results by increasing the number and nature of covariates and by using data-driven, instead of hypothesis-based, methods to predict this persistence.

METHODS

Through the Swedish Rheumatology Quality Register, linked to other data sources, we identified a cohort of 5475 patients with new-onset RA in 2006-2016 who were starting MTX monotherapy as their first disease-modifying antirheumatic drug. Data on phenotype at diagnosis and demographics were combined with increasingly detailed data on medical disease history and medication use in four increasingly complex data sets (48-4162 covariates). We performed manual model building using logistic regression. We also performed five different machine learning (ML) methods and combined the ML results into an ensemble model. We calculated the area under the receiver operating characteristic curve (AUROC) and made calibration plots. We trained on 90% of the data, and tested the models on a holdout data set.

RESULTS

Of the 5475 patients, 3834 (70%) remained on MTX monotherapy 1 year after treatment start. Clinical RA disease activity and baseline characteristics were most strongly associated with the outcome. The best manual model had an AUROC of 0.66 (95% confidence interval [CI] 0.60-0.71). For the ML methods, Lasso regression performed best (AUROC = 0.67; 95% CI 0.62-0.71).

CONCLUSION

Approximately two thirds of patients with early RA who start MTX remain on this therapy 1 year later. Predicting this persistence remains a challenge, whether using hypothesis-based or ML models, and may yet require additional types of data.

Evolutionary genetic algorithm identifies IL2RB as a potential predictive biomarker for immune-checkpoint therapy in colorectal cancer

Identifying robust predictive biomarkers to stratify colorectal cancer (CRC) patients based on their response to immune-checkpoint therapy is an area of unmet clinical need. Our evolutionary algorithm Atlas Correlation Explorer (ACE) represents a novel approach for mining The Cancer Genome Atlas (TCGA) data for clinically relevant associations. We deployed ACE to identify candidate predictive biomarkers of response to immune-checkpoint therapy in CRC. We interrogated the colon adenocarcinoma (COAD) gene expression data across nine immune-checkpoints (PDL1, PDCD1, CTLA4, LAG3, TIM3, TIGIT, ICOS, IDO1 and BTLA). IL2RB was identified as the most common gene associated with immune-checkpoint genes in CRC. Using human/murine single-cell RNA-seq data, we demonstrated that IL2RB was expressed predominantly in a subset of T-cells associated with increased immune-checkpoint expression (P < 0.0001). Confirmatory IL2RB immunohistochemistry (IHC) analysis in a large MSI-H colon cancer tissue microarray (TMA; n = 115) revealed sensitive, specific staining of a subset of lymphocytes and a strong association with FOXP3+ lymphocytes (P < 0.0001). IL2RB mRNA positively correlated with three previously-published gene signatures of response to immune-checkpoint therapy (P < 0.0001). Our evolutionary algorithm has identified IL2RB to be extensively linked to immune-checkpoints in CRC; its expression should be investigated for clinical utility as a potential predictive biomarker for CRC patients receiving immune-checkpoint blockade.

An Explainable Multimodal Neural Network Architecture for Predicting Epilepsy Comorbidities Based on Administrative Claims Data

Epilepsy is a complex brain disorder characterized by repetitive seizure events. Epilepsy patients often suffer from various and severe physical and psychological comorbidities (e.g., anxiety, migraine, and stroke). While general comorbidity prevalences and incidences can be estimated from epidemiological data, such an approach does not take into account that actual patient-specific risks can depend on various individual factors, including medication. This motivates to develop a machine learning approach for predicting risks of future comorbidities for individual epilepsy patients. In this work, we use inpatient and outpatient administrative health claims data of around 19,500 U.S. epilepsy patients. We suggest a dedicated multimodal neural network architecture (Deep personalized LOngitudinal convolutional RIsk model-DeepLORI) to predict the time-dependent risk of six common comorbidities of epilepsy patients. We demonstrate superior performance of DeepLORI in a comparison with several existing methods. Moreover, we show that DeepLORI-based predictions can be interpreted on the level of individual patients. Using a game theoretic approach, we identify relevant features in DeepLORI models and demonstrate that model predictions are explainable in light of existing knowledge about the disease. Finally, we validate the model on independent data from around 97,000 patients, showing good generalization and stable prediction performance over time.

Rise of Clinical Studies in the Field of Machine Learning: A Review of Data Registered in ClinicalTrials.gov

Although advances in machine-learning healthcare applications promise great potential for innovative medical care, few data are available on the translational status of these new technologies. We aimed to provide a comprehensive characterization of the development and status quo of clinical studies in the field of machine learning. For this purpose, we performed a registry-based analysis of machine-learning-related studies that were published and first available in the ClinicalTrials.gov database until 2020, using the database's study classification. In total, n = 358 eligible studies could be included in the analysis. Of these, 82% were initiated by academic institutions/university (hospitals) and 18% by industry sponsors. A total of 96% were national and 4% international. About half of the studies (47%) had at least one recruiting location in a country in North America, followed by Europe (37%) and Asia (15%). Most of the studies reported were initiated in the medical field of imaging (12%), followed by cardiology, psychiatry, anesthesia/intensive care medicine (all 11%) and neurology (10%). Although the majority of the clinical studies were still initiated in an academic research context, the first industry-financed projects on machine-learning-based algorithms are becoming visible. The number of clinical studies with machine-learning-related applications and the variety of medical challenges addressed serve to indicate their increasing importance in future clinical care. Finally, they also set a time frame for the adjustment of medical device-related regulation and governance.

CLEP: A Hybrid Data- and Knowledge- Driven Framework for Generating Patient Representations

Summary

As machine learning and artificial intelligence increasingly attain a larger number of applications in the biomedical domain, at their core, their utility depends on the data used to train them. Due to the complexity and high dimensionality of biomedical data, there is a need for approaches that combine prior knowledge around known biological interactions with patient data. Here, we present CLinical Embedding of Patients (CLEP), a novel approach that generates new patient representations by leveraging both prior knowledge and patient-level data. First, given a patient-level dataset and a knowledge graph containing relations across features that can be mapped to the dataset, CLEP incorporates patients into the knowledge graph as new nodes connected to their most characteristic features. Next, CLEP employs knowledge graph embedding models to generate new patient representations that can ultimately be used for a variety of downstream tasks, ranging from clustering to classification. We demonstrate how using new patient representations generated by CLEP significantly improves performance in classifying between patients and healthy controls for a variety of machine learning models, as compared to the use of the original transcriptomics data. Furthermore, we also show how incorporating patients into a knowledge graph can foster the interpretation and identification of biological features characteristic of a specific disease or patient subgroup. Finally, we released CLEP as an open source Python package together with examples and documentation.

Availability and implementation

CLEP is available to the bioinformatics community as an open source Python package at https://github.com/hybrid-kg/clep under the Apache 2.0 License.

Supplementary information

Supplementary data are available at Bioinformatics online.

Data-driven Derivation and Validation of Novel Phenotypes for Acute Kidney Transplant Rejection using Semi-supervised Clustering

BACKGROUND

Over the past decades, an international group of experts iteratively developed a consensus classification of kidney transplant rejection phenotypes, known as the Banff classification. Data-driven clustering of kidney transplant histologic data could simplify the complex and discretionary rules of the Banff classification, while improving the association with graft failure.

METHODS

The data consisted of a training set of 3510 kidney-transplant biopsies from an observational cohort of 936 recipients. Independent validation of the results was performed on an external set of 3835 biopsies from 1989 patients. On the basis of acute histologic lesion scores and the presence of donor-specific HLA antibodies, stable clustering was achieved on the basis of a consensus of 400 different clustering partitions. Additional information on kidney-transplant failure was introduced with a weighted Euclidean distance.

RESULTS

Based on the proportion of ambiguous clustering, six clinically meaningful cluster phenotypes were identified. There was significant overlap with the existing Banff classification (adjusted rand index, 0.48). However, the data-driven approach eliminated intermediate and mixed phenotypes and created acute rejection clusters that are each significantly associated with graft failure. Finally, a novel visualization tool presents disease phenotypes and severity in a continuous manner, as a complement to the discrete clusters.

CONCLUSIONS

A semisupervised clustering approach for the identification of clinically meaningful novel phenotypes of kidney transplant rejection has been developed and validated. The approach has the potential to offer a more quantitative evaluation of rejection subtypes and severity, especially in situations in which the current histologic categorization is ambiguous.

A precision medicine framework for personalized simulation of hemodynamics in cerebrovascular disease

BACKGROUND

Cerebrovascular disease, in particular stroke, is a major public health challenge. An important biomarker is cerebral hemodynamics. To measure and quantify cerebral hemodynamics, however, only invasive, potentially harmful or time-to-treatment prolonging methods are available.

RESULTS

We present a simulation-based approach which allows calculation of cerebral hemodynamics based on the patient-individual vessel configuration derived from structural vessel imaging. For this, we implemented a framework allowing segmentation and annotation of brain vessels from structural imaging followed by 0-dimensional lumped simulation modeling of cerebral hemodynamics. For annotation, a 3D-graphical user interface was implemented. For 0D-simulation, we used a modified nodal analysis, which was adapted for easy implementation by code. The simulation enables identification of areas vulnerable to stroke and simulation of changes due to different systemic blood pressures. Moreover, sensitivity analysis was implemented allowing the live simulation of changes to simulate procedures and disease progression. Beyond presentation of the framework, we demonstrated in an exploratory analysis in 67 patients that the simulation has a high specificity and low-to-moderate sensitivity to detect perfusion changes in classic perfusion imaging.

CONCLUSIONS

The presented precision medicine approach using novel biomarkers has the potential to make the application of harmful and complex perfusion methods obsolete.

Advances in the application of artificial intelligence in solid tumor imaging

Early diagnosis and timely treatment are crucial in reducing cancer-related mortality. Artificial intelligence (AI) has greatly relieved clinical workloads and changed the current medical workflows. We searched for recent studies, reports and reviews referring to AI and solid tumors; many reviews have summarized AI applications in the diagnosis and treatment of a single tumor type. We herein systematically review the advances of AI application in multiple solid tumors including esophagus, stomach, intestine, breast, thyroid, prostate, lung, liver, cervix, pancreas and kidney with a specific focus on the continual improvement on model performance in imaging practice.

Artificial Intelligence in Bulk and Single-Cell RNA-Sequencing Data to Foster Precision Oncology

Artificial intelligence, or the discipline of developing computational algorithms able to perform tasks that requires human intelligence, offers the opportunity to improve our idea and delivery of precision medicine. Here, we provide an overview of artificial intelligence approaches for the analysis of large-scale RNA-sequencing datasets in cancer. We present the major solutions to disentangle inter- and intra-tumor heterogeneity of transcriptome profiles for an effective improvement of patient management. We outline the contributions of learning algorithms to the needs of cancer genomics, from identifying rare cancer subtypes to personalizing therapeutic treatments.

Economic evaluations of big data analytics for clinical decision-making: a scoping review

OBJECTIVE

Much has been invested in big data analytics to improve health and reduce costs. However, it is unknown whether these investments have achieved the desired goals. We performed a scoping review to determine the health and economic impact of big data analytics for clinical decision-making.

MATERIALS AND METHODS

We searched Medline, Embase, Web of Science and the National Health Services Economic Evaluations Database for relevant articles. We included peer-reviewed papers that report the health economic impact of analytics that assist clinical decision-making. We extracted the economic methods and estimated impact and also assessed the quality of the methods used. In addition, we estimated how many studies assessed "big data analytics" based on a broad definition of this term.

RESULTS

The search yielded 12 133 papers but only 71 studies fulfilled all eligibility criteria. Only a few papers were full economic evaluations; many were performed during development. Papers frequently reported savings for healthcare payers but only 20% also included costs of analytics. Twenty studies examined "big data analytics" and only 7 reported both cost-savings and better outcomes.

DISCUSSION

The promised potential of big data is not yet reflected in the literature, partly since only a few full and properly performed economic evaluations have been published. This and the lack of a clear definition of "big data" limit policy makers and healthcare professionals from determining which big data initiatives are worth implementing.

The continuum of disrupted metabolic tempo, mitochondrial substrate congestion, and metabolic gridlock toward the development of non-communicable diseases

Non-communicable diseases (NCD) are the slow-motion disasters with imminent global health care burden. The current dietary management for NCD is dominated by the calorie balance model. Apart from the quantitative balance of calorie, healthy bioenergetics requires temporal eating and fasting rhythms, and the subsequent switching for different metabolic fuels. We herein term these three bioenergetic attributes, i.e., caloric balance, diurnal eating-fasting rhythm, and metabolic flexibility, as the metabolic tempo. These three attributes are intertwined with each other; alteration of one attribute affects one or more other attributes. Lifestyle-induced disrupted metabolic tempo presents a high flux of mixed carbon substrates to mitochondria, with the resulting congestion and indecisiveness of metabolic switches. Such indecisiveness impairs metabolic flexibility, promotes anabolism, and accumulates the energy storage pools. The triggers from hypoxic inducible factor expression could further promote the metabolic gridlock and adipocyte maladaptation. The maladaptive adipocytes lead to ectopic fat deposition, increased circulating lipid levels, insulin resistance, and chronic systemic inflammation. These continuum set stages for clinical NCDs. We propose that the restoration of all tempo attributes through the combined diet-, time-, and calorie-restricted interventions could be the preferred strategy for NCD management.

Variational Autoencoder Modular Bayesian Networks for Simulation of Heterogeneous Clinical Study Data

In the area of Big Data, one of the major obstacles for the progress of biomedical research is the existence of data “silos” because legal and ethical constraints often do not allow for sharing sensitive patient data from clinical studies across institutions. While federated machine learning now allows for building models from scattered data of the same format, there is still the need to investigate, mine, and understand data of separate and very differently designed clinical studies that can only be accessed within each of the data-hosting organizations. Simulation of sufficiently realistic virtual patients based on the data within each individual organization could be a way to fill this gap. In this work, we propose a new machine learning approach [Variational Autoencoder Modular Bayesian Network (VAMBN)] to learn a generative model of longitudinal clinical study data. VAMBN considers typical key aspects of such data, namely limited sample size coupled with comparable many variables of different numerical scales and statistical properties, and many missing values. We show that with VAMBN, we can simulate virtual patients in a sufficiently realistic manner while making theoretical guarantees on data privacy. In addition, VAMBN allows for simulating counterfactual scenarios. Hence, VAMBN could facilitate data sharing as well as design of clinical trials.

Future Medical Artificial Intelligence Application Requirements and Expectations of Physicians in German University Hospitals: Web-Based Survey

BACKGROUND

The increasing development of artificial intelligence (AI) systems in medicine driven by researchers and entrepreneurs goes along with enormous expectations for medical care advancement. AI might change the clinical practice of physicians from almost all medical disciplines and in most areas of health care. While expectations for AI in medicine are high, practical implementations of AI for clinical practice are still scarce in Germany. Moreover, physicians' requirements and expectations of AI in medicine and their opinion on the usage of anonymized patient data for clinical and biomedical research have not been investigated widely in German university hospitals.

OBJECTIVE

This study aimed to evaluate physicians' requirements and expectations of AI in medicine and their opinion on the secondary usage of patient data for (bio)medical research (eg, for the development of machine learning algorithms) in university hospitals in Germany.

METHODS

A web-based survey was conducted addressing physicians of all medical disciplines in 8 German university hospitals. Answers were given using Likert scales and general demographic responses. Physicians were asked to participate locally via email in the respective hospitals.

RESULTS

The online survey was completed by 303 physicians (female: 121/303, 39.9%; male: 173/303, 57.1%; no response: 9/303, 3.0%) from a wide range of medical disciplines and work experience levels. Most respondents either had a positive (130/303, 42.9%) or a very positive attitude (82/303, 27.1%) towards AI in medicine. There was a significant association between the personal rating of AI in medicine and the self-reported technical affinity level (H4=48.3, P<.001). A vast majority of physicians expected the future of medicine to be a mix of human and artificial intelligence (273/303, 90.1%) but also requested a scientific evaluation before the routine implementation of AI-based systems (276/303, 91.1%). Physicians were most optimistic that AI applications would identify drug interactions (280/303, 92.4%) to improve patient care substantially but were quite reserved regarding AI-supported diagnosis of psychiatric diseases (62/303, 20.5%). Of the respondents, 82.5% (250/303) agreed that there should be open access to anonymized patient databases for medical and biomedical research.

CONCLUSIONS

Physicians in stationary patient care in German university hospitals show a generally positive attitude towards using most AI applications in medicine. Along with this optimism comes several expectations and hopes that AI will assist physicians in clinical decision making. Especially in fields of medicine where huge amounts of data are processed (eg, imaging procedures in radiology and pathology) or data are collected continuously (eg, cardiology and intensive care medicine), physicians' expectations of AI to substantially improve future patient care are high. In the study, the greatest potential was seen in the application of AI for the identification of drug interactions, assumedly due to the rising complexity of drug administration to polymorbid, polypharmacy patients. However, for the practical usage of AI in health care, regulatory and organizational challenges still have to be mastered.

AI applications to medical images: From machine learning to deep learning

PURPOSE

Artificial intelligence (AI) models are playing an increasing role in biomedical research and healthcare services. This review focuses on challenges points to be clarified about how to develop AI applications as clinical decision support systems in the real-world context.

METHODS

A narrative review has been performed including a critical assessment of articles published between 1989 and 2021 that guided challenging sections.

RESULTS

We first illustrate the architectural characteristics of machine learning (ML)/radiomics and deep learning (DL) approaches. For ML/radiomics, the phases of feature selection and of training, validation, and testing are described. DL models are presented as multi-layered artificial/convolutional neural networks, allowing us to directly process images. The data curation section includes technical steps such as image labelling, image annotation (with segmentation as a crucial step in radiomics), data harmonization (enabling compensation for differences in imaging protocols that typically generate noise in non-AI imaging studies) and federated learning. Thereafter, we dedicate specific sections to: sample size calculation, considering multiple testing in AI approaches; procedures for data augmentation to work with limited and unbalanced datasets; and the interpretability of AI models (the so-called black box issue). Pros and cons for choosing ML versus DL to implement AI applications to medical imaging are finally presented in a synoptic way.

CONCLUSIONS

Biomedicine and healthcare systems are one of the most important fields for AI applications and medical imaging is probably the most suitable and promising domain. Clarification of specific challenging points facilitates the development of such systems and their translation to clinical practice.

Driving success in personalized medicine through AI-enabled computational modeling

The development of successful drugs is expensive and time-consuming because of high clinical attrition rates. This is caused partially by the rupture seen in the translatability of the drug from the bench to the clinic in the context of personalized medicine. Artificial intelligence (AI)-driven platforms integrated with mechanistic modeling have become instrumental in accelerating the drug development process by leveraging data ubiquitously across the various phases. AI can counter the deficiencies and ambiguities that arise during the classical drug development process while reducing human intervention and bridging the translational gap in discovering the connections between drugs and diseases.

Systematic literature review of machine learning methods used in the analysis of real-world data for patient-provider decision making

BACKGROUND

Machine learning is a broad term encompassing a number of methods that allow the investigator to learn from the data. These methods may permit large real-world databases to be more rapidly translated to applications to inform patient-provider decision making.

METHODS

This systematic literature review was conducted to identify published observational research of employed machine learning to inform decision making at the patient-provider level. The search strategy was implemented and studies meeting eligibility criteria were evaluated by two independent reviewers. Relevant data related to study design, statistical methods and strengths and limitations were identified; study quality was assessed using a modified version of the Luo checklist.

RESULTS

A total of 34 publications from January 2014 to September 2020 were identified and evaluated for this review. There were diverse methods, statistical packages and approaches used across identified studies. The most common methods included decision tree and random forest approaches. Most studies applied internal validation but only two conducted external validation. Most studies utilized one algorithm, and only eight studies applied multiple machine learning algorithms to the data. Seven items on the Luo checklist failed to be met by more than 50% of published studies.

CONCLUSIONS

A wide variety of approaches, algorithms, statistical software, and validation strategies were employed in the application of machine learning methods to inform patient-provider decision making. There is a need to ensure that multiple machine learning approaches are used, the model selection strategy is clearly defined, and both internal and external validation are necessary to be sure that decisions for patient care are being made with the highest quality evidence. Future work should routinely employ ensemble methods incorporating multiple machine learning algorithms.

AI and Big Data in Healthcare: Towards a More Comprehensive Research Framework for Multimorbidity

Multimorbidity refers to the coexistence of two or more chronic diseases in one person. Therefore, patients with multimorbidity have multiple and special care needs. However, in practice it is difficult to meet these needs because the organizational processes of current healthcare systems tend to be tailored to a single disease. To improve clinical decision making and patient care in multimorbidity, a radical change in the problem-solving approach to medical research and treatment is needed. In addition to the traditional reductionist approach, we propose interactive research supported by artificial intelligence (AI) and advanced big data analytics. Such research approach, when applied to data routinely collected in healthcare settings, provides an integrated platform for research tasks related to multimorbidity. This may include, for example, prediction, correlation, and classification problems based on multiple interaction factors. However, to realize the idea of this paradigm shift in multimorbidity research, the optimization, standardization, and most importantly, the integration of electronic health data into a common national and international research infrastructure is needed. Ultimately, there is a need for the integration and implementation of efficient AI approaches, particularly deep learning, into clinical routine directly within the workflows of the medical professionals.

Blind-sided by privacy? Digital contact tracing, the Apple/Google API and big tech's newfound role as global health policy makers

Since the outbreak of COVID-19, governments have turned their attention to digital contact tracing. In many countries, public debate has focused on the risks this technology poses to privacy, with advocates and experts sounding alarm bells about surveillance and mission creep reminiscent of the post 9/11 era. Yet, when Apple and Google launched their contact tracing API in April 2020, some of the world's leading privacy experts applauded this initiative for its privacy-preserving technical specifications. In an interesting twist, the tech giants came to be portrayed as greater champions of privacy than some democratic governments. This article proposes to view the Apple/Google API in terms of a broader phenomenon whereby tech corporations are encroaching into ever new spheres of social life. From this perspective, the (legitimate) advantage these actors have accrued in the sphere of the production of digital goods provides them with (illegitimate) access to the spheres of health and medicine, and more worrisome, to the sphere of politics. These sphere transgressions raise numerous risks that are not captured by the focus on privacy harms. Namely, a crowding out of essential spherical expertise, new dependencies on corporate actors for the delivery of essential, public goods, the shaping of (global) public policy by non-representative, private actors and ultimately, the accumulation of decision-making power across multiple spheres. While privacy is certainly an important value, its centrality in the debate on digital contact tracing may blind us to these broader societal harms and unwittingly pave the way for ever more sphere transgressions.

ANMerge: A Comprehensive and Accessible Alzheimer's Disease Patient-Level Dataset

BACKGROUND

Accessible datasets are of fundamental importance to the advancement of Alzheimer's disease (AD) research. The AddNeuroMed consortium conducted a longitudinal observational cohort study with the aim to discover AD biomarkers. During this study, a broad selection of data modalities was measured including clinical assessments, magnetic resonance imaging, genotyping, transcriptomic profiling, and blood plasma proteomics. Some of the collected data were shared with third-party researchers. However, this data was incomplete, erroneous, and lacking in interoperability.

OBJECTIVE

To provide the research community with an accessible, multimodal, patient-level AD cohort dataset.

METHODS

We systematically addressed several limitations of the originally shared resources and provided additional unreleased data to enhance the dataset.

RESULTS

In this work, we publish and describe ANMerge, a new version of the AddNeuroMed dataset. ANMerge includes multimodal data from 1,702 study participants and is accessible to the research community via a centralized portal.

CONCLUSION

ANMerge is an information rich patient-level data resource that can serve as a discovery and validation cohort for data-driven AD research, such as, for example, machine learning and artificial intelligence approaches.

Digital Twins, Internet of Things and Mobile Medicine: A Review of Current Platforms to Support Smart Healthcare

As the population grows, the need for higher-quality medical services increases, as well as the demand for information technology in medicine. The Smart Healthcare concept brings various approaches to address the acute problems encountered in modern healthcare. In this paper, we review the main problems of modern healthcare and analyze existing approaches and technologies in digital twins, the Internet of Things, and mobile medicine. We will also analyze the key features of modern platforms that support Mobile Health Applications. Finally, based on our analysis, we will propose the concept of Smart Healthcare Platform, focused on solving tasks related to supporting the development of Mobile Health Applications, including organizing access, management, and sharing of user data.

hiPSCs for predictive modelling of neurodegenerative diseases: dreaming the possible

Human induced pluripotent stem cells (hiPSCs) were first generated in 2007, but the full translational potential of this valuable tool has yet to be realized. The potential applications of hiPSCs are especially relevant to neurology, as brain cells from patients are rarely available for research. hiPSCs from individuals with neuropsychiatric or neurodegenerative diseases have facilitated biological and multi-omics studies as well as large-scale screening of chemical libraries. However, researchers are struggling to improve the scalability, reproducibility and quality of this descriptive disease modelling. Addressing these limitations will be the first step towards a new era in hiPSC research - that of predictive disease modelling - involving the correlation and integration of in vitro experimental data with longitudinal clinical data. This approach is a key element of the emerging precision medicine paradigm, in which hiPSCs could become a powerful diagnostic and prognostic tool. Here, we consider the steps necessary to achieve predictive modelling of neurodegenerative disease with hiPSCs, using Huntington disease as an example.

Cancer survival statistics for patients and healthcare professionals - a tutorial of real-world data analysis

Monitoring survival of cancer patients using data collected by population-based cancer registries is an important component of cancer control. In this setting, patient survival is often summarized using net survival, that is survival from cancer if there were no other possible causes of death. Although net survival is the gold standard for comparing survival between groups or over time, it is less relevant for understanding the anticipated real-world prognosis of patients. In this review, we explain statistical concepts targeted towards patients, clinicians and healthcare professionals that summarize cancer patient survival under the assumption that other causes of death exist. Specifically, we explain the appropriate use, interpretation and assumptions behind statistical methods for competing risks, loss in life expectancy due to cancer and conditional survival. These concepts are relevant when producing statistics for risk communication between physicians and patients, planning for use of healthcare resources, or other applications when consideration of both cancer outcomes and the competing risks of death is required. To reinforce the concepts, we use Swedish population-based data of patients diagnosed with cancer of the breast, prostate, colon and chronic myeloid leukaemia. We conclude that when choosing between summary measures of survival it is critical to characterize the purpose of the study and to determine the nature of the hypothesis under investigation. The choice of terminology and style of reporting should be carefully adapted to the target audience and may range from summaries for specialist readers of scientific publications to interactive online tools aimed towards lay persons.

Real-time imputation of missing predictor values in clinical practice

Aims

Use of prediction models is widely recommended by clinical guidelines, but usually requires complete information on all predictors, which is not always available in daily practice. We aim to describe two methods for real-time handling of missing predictor values when using prediction models in practice.

Methods and results

We compare the widely used method of mean imputation (M-imp) to a method that personalizes the imputations by taking advantage of the observed patient characteristics. These characteristics may include both prediction model variables and other characteristics (auxiliary variables). The method was implemented using imputation from a joint multivariate normal model of the patient characteristics (joint modelling imputation; JMI). Data from two different cardiovascular cohorts with cardiovascular predictors and outcome were used to evaluate the real-time imputation methods. We quantified the prediction model's overall performance [mean squared error (MSE) of linear predictor], discrimination (c-index), calibration (intercept and slope), and net benefit (decision curve analysis). When compared with mean imputation, JMI substantially improved the MSE (0.10 vs. 0.13), c-index (0.70 vs. 0.68), and calibration (calibration-in-the-large: 0.04 vs. 0.06; calibration slope: 1.01 vs. 0.92), especially when incorporating auxiliary variables. When the imputation method was based on an external cohort, calibration deteriorated, but discrimination remained similar.

Conclusions

We recommend JMI with auxiliary variables for real-time imputation of missing values, and to update imputation models when implementing them in new settings or (sub)populations.

Evaluating the Alzheimer's disease data landscape

INTRODUCTION

Numerous studies have collected Alzheimer's disease (AD) cohort data sets. To achieve reproducible, robust results in data-driven approaches, an evaluation of the present data landscape is vital.

METHODS

Previous efforts relied exclusively on metadata and literature. Here, we evaluate the data landscape by directly investigating nine patient-level data sets generated in major clinical cohort studies.

RESULTS

The investigated cohorts differ in key characteristics, such as demographics and distributions of AD biomarkers. Analyzing the ethnoracial diversity revealed a strong bias toward White/Caucasian individuals. We described and compared the measured data modalities. Finally, the available longitudinal data for important AD biomarkers was evaluated. All results are explorable through our web application ADataViewer (https://adata.scai.fraunhofer.de).

DISCUSSION

Our evaluation exposed critical limitations in the AD data landscape that impede comparative approaches across multiple data sets. Comparison of our results to those gained by metadata-based approaches highlights that thorough investigation of real patient-level data is imperative to assess a data landscape.

A research agenda for ageing in China in the 21st century (2nd edition): Focusing on basic and translational research, long-term care, policy and social networks

One of the key issues facing public healthcare is the global trend of an increasingly ageing society which continues to present policy makers and caregivers with formidable healthcare and socio-economic challenges. Ageing is the primary contributor to a broad spectrum of chronic disorders all associated with a lower quality of life in the elderly. In 2019, the Chinese population constituted 18 % of the world population, with 164.5 million Chinese citizens aged 65 and above (65+), and 26 million aged 80 or above (80+). China has become an ageing society, and as it continues to age it will continue to exacerbate the burden borne by current family and public healthcare systems. Major healthcare challenges involved with caring for the elderly in China include the management of chronic non-communicable diseases (CNCDs), physical frailty, neurodegenerative diseases, cardiovascular diseases, with emerging challenges such as providing sufficient dental care, combating the rising prevalence of sexually transmitted diseases among nursing home communities, providing support for increased incidences of immune diseases, and the growing necessity to provide palliative care for the elderly. At the governmental level, it is necessary to make long-term strategic plans to respond to the pressures of an ageing society, especially to establish a nationwide, affordable, annual health check system to facilitate early diagnosis and provide access to affordable treatments. China has begun work on several activities to address these issues including the recent completion of the of the Ten-year Health-Care Reform project, the implementation of the Healthy China 2030 Action Plan, and the opening of the National Clinical Research Center for Geriatric Disorders. There are also societal challenges, namely the shift from an extended family system in which the younger provide home care for their elderly family members, to the current trend in which young people are increasingly migrating towards major cities for work, increasing reliance on nursing homes to compensate, especially following the outcomes of the 'one child policy' and the 'empty-nest elderly' phenomenon. At the individual level, it is important to provide avenues for people to seek and improve their own knowledge of health and disease, to encourage them to seek medical check-ups to prevent/manage illness, and to find ways to promote modifiable health-related behaviors (social activity, exercise, healthy diets, reasonable diet supplements) to enable healthier, happier, longer, and more productive lives in the elderly. Finally, at the technological or treatment level, there is a focus on modern technologies to counteract the negative effects of ageing. Researchers are striving to produce drugs that can mimic the effects of 'exercising more, eating less', while other anti-ageing molecules from molecular gerontologists could help to improve 'healthspan' in the elderly. Machine learning, 'Big Data', and other novel technologies can also be used to monitor disease patterns at the population level and may be used to inform policy design in the future. Collectively, synergies across disciplines on policies, geriatric care, drug development, personal awareness, the use of big data, machine learning and personalized medicine will transform China into a country that enables the most for its elderly, maximizing and celebrating their longevity in the coming decades. This is the 2nd edition of the review paper (Fang EF et al., Ageing Re. Rev. 2015).

Interrogating the microenvironmental landscape of tumors with computational image analysis approaches

The tumor microenvironment is an interacting heterogeneous collection of cancer cells, resident as well as infiltrating host cells, secreted factors, and extracellular matrix proteins. With the growing importance of immunotherapies, it has become crucial to be able to characterize the composition and the functional orientation of the microenvironment. The development of novel computational image analysis methodologies may enable the robust quantification and localization of immune and related biomarker-expressing cells within the microenvironment. The aim of the review is to concisely highlight a selection of current and significant contributions pertinent to methodological advances coupled with biomedical or translational applications. A further aim is to concisely present computational advances that, to our knowledge, have currently very limited use for the assessment of the microenvironment but have the potential to enhance image analysis pipelines; on this basis, an example is shown for the detection and segmentation of cells of the microenvironment using a published pipeline and a public dataset. Finally, a general proposal is presented on the conceptual design of automation-optimized computational image analysis workflows in the biomedical and clinical domain.

Clustering of Alzheimer's and Parkinson's disease based on genetic burden of shared molecular mechanisms

One of the visions of precision medicine has been to re-define disease taxonomies based on molecular characteristics rather than on phenotypic evidence. However, achieving this goal is highly challenging, specifically in neurology. Our contribution is a machine-learning based joint molecular subtyping of Alzheimer's (AD) and Parkinson's Disease (PD), based on the genetic burden of 15 molecular mechanisms comprising 27 proteins (e.g. APOE) that have been described in both diseases. We demonstrate that our joint AD/PD clustering using a combination of sparse autoencoders and sparse non-negative matrix factorization is reproducible and can be associated with significant differences of AD and PD patient subgroups on a clinical, pathophysiological and molecular level. Hence, clusters are disease-associated. To our knowledge this work is the first demonstration of a mechanism based stratification in the field of neurodegenerative diseases. Overall, we thus see this work as an important step towards a molecular mechanism-based taxonomy of neurological disorders, which could help in developing better targeted therapies in the future by going beyond classical phenotype based disease definitions.

The immune phenotype of tongue squamous cell carcinoma predicts early relapse and poor prognosis

BACKGROUND

In patients with squamous cell carcinoma of the oral tongue (OTSCC), current tumor node metastasis staging system fails to identify at-risk patients associated with early relapse and poor prognosis despite complete surgical resection. Given the importance of tumor-infiltrating lymphocytes (TILs) in the development of cancers, here we investigated the prognostic significance of the immune phenotype in OTSCC.

METHODS

Hematoxylin-eosin stained sections of OTSCCs from 211 patients were evaluated. Cancers were classified as (a) immune-inflamed when TILs were found next to tumor cell nests; (b) immune-excluded when TILs were found in the stroma, outside the tumor; and (c) immune-desert for tumors lacking lymphocyte infiltrate. The prognostic significance of these immune phenotypes classes was investigated. Data were further validated on an independent cohort from The Cancer Genome Atlas database.

RESULTS

Immune-desert phenotype was the least represented group of OTSCCs in our cohort (11.8%) and served as an independent prognostic factor. Patients with immune-desert tumors exhibited worse disease-specific survival (HR = 2.673; [CI: 95% 1.497-4.773]; P = .001), overall survival (HR = 2.591; [CI: 95% 1.468-4.572]; P = .001), and disease-free survival (HR = 2.313; [CI: 95% 1.118-4.786]; P = .024) at multivariate analysis.

CONCLUSIONS

We identified a specific subgroup of OTSCCs with poor prognosis. Tumor-infiltrating lymphocytes density and localization could serve as an integrative parameter to the current staging system and inform the selection of most appropriate treatments. In particular, the tumor immune phenotype could improve the stratification of patients with more aggressive disease.