Workflow-driven clinical decision support for personalized oncology

Use of Real-World FHIR Data Combined with Context-Sensitive Decision Modeling to Guide Sentinel Biopsy in Melanoma

Background: To support clinical decision-making at the point of care, the "best next step" based on Standard Operating Procedures (SOPs) and actual accurate patient data must be provided. To do this, textual SOPs have to be transformed into operable clinical algorithms and linked to the data of the patient being treated. For this linkage, we need to know exactly which data are needed by clinicians at a certain decision point and whether these data are available. These data might be identical to the data used within the SOP or might integrate a broader view. To address these concerns, we examined if the data used by the SOP is also complete from the point of view of physicians for contextual decision-making. Methods: We selected a cohort of 67 patients with stage III melanoma who had undergone adjuvant treatment and mainly had an indication for a sentinel biopsy. First, we performed a step-by-step simulation of the patient treatment along our clinical algorithm, which is based on a hospital-specific SOP, to validate the algorithm with the given Fast Healthcare Interoperability Resources (FHIR)-based data of our cohort. Second, we presented three different decision situations within our algorithm to 10 dermatooncologists, focusing on the concrete patient data used at this decision point. The results were conducted, analyzed, and compared with those of the pure algorithmic simulation. Results: The treatment paths of patients with melanoma could be retrospectively simulated along the clinical algorithm using data from the patients' electronic health records. The subsequent evaluation by dermatooncologists showed that the data used at the three decision points had a completeness between 84.6% and 100.0% compared with the data used by the SOP. At one decision point, data on "patient age (at primary diagnosis)" and "date of first diagnosis" were missing. Conclusions: The data needed for our decision points are available in the FHIR-based dataset. Furthermore, the data used at decision points by the SOP and hence the clinical algorithm are nearly complete compared with the data required by physicians in clinical practice. This is an important precondition for further research focusing on presenting decision points within a treatment process integrated with the patient data needed.

Cancer drug sensitivity estimation using modular deep Graph Neural Networks

Computational drug sensitivity models have the potential to improve therapeutic outcomes by identifying targeted drugs components that are tailored to the transcriptomic profile of a given primary tumor. The SMILES representation of molecules that is used by state-of-the-art drug-sensitivity models is not conducive for neural networks to generalize to new drugs, in part because the distance between atoms does not generally correspond to the distance between their representation in the SMILES strings. Graph-attention networks, on the other hand, are high-capacity models that require large training-data volumes which are not available for drug-sensitivity estimation. We develop a modular drug-sensitivity graph-attentional neural network. The modular architecture allows us to separately pre-train the graph encoder and graph-attentional pooling layer on related tasks for which more data are available. We observe that this model outperforms reference models for the use cases of precision oncology and drug discovery; in particular, it is better able to predict the specific interaction between drug and cell line that is not explained by the general cytotoxicity of the drug and the overall survivability of the cell line. The complete source code is available at https://zenodo.org/doi/10.5281/zenodo.8020945. All experiments are based on the publicly available GDSC data.

A Multidisciplinary Hyper-Modeling Scheme in Personalized In Silico Oncology: Coupling Cell Kinetics with Metabolism, Signaling Networks, and Biomechanics as Plug-In Component Models of a Cancer Digital Twin

The massive amount of human biological, imaging, and clinical data produced by multiple and diverse sources necessitates integrative modeling approaches able to summarize all this information into answers to specific clinical questions. In this paper, we present a hypermodeling scheme able to combine models of diverse cancer aspects regardless of their underlying method or scale. Describing tissue-scale cancer cell proliferation, biomechanical tumor growth, nutrient transport, genomic-scale aberrant cancer cell metabolism, and cell-signaling pathways that regulate the cellular response to therapy, the hypermodel integrates mutation, miRNA expression, imaging, and clinical data. The constituting hypomodels, as well as their orchestration and links, are described. Two specific cancer types, Wilms tumor (nephroblastoma) and non-small cell lung cancer, are addressed as proof-of-concept study cases. Personalized simulations of the actual anatomy of a patient have been conducted. The hypermodel has also been applied to predict tumor control after radiotherapy and the relationship between tumor proliferative activity and response to neoadjuvant chemotherapy. Our innovative hypermodel holds promise as a digital twin-based clinical decision support system and as the core of future in silico trial platforms, although additional retrospective adaptation and validation are necessary.

Pre-Training on In Vitro and Fine-Tuning on Patient-Derived Data Improves Deep Neural Networks for Anti-Cancer Drug-Sensitivity Prediction

Large-scale databases that report the inhibitory capacities of many combinations of candidate drug compounds and cultivated cancer cell lines have driven the development of preclinical drug-sensitivity models based on machine learning. However, cultivated cell lines have devolved from human cancer cells over years or even decades under selective pressure in culture conditions. Moreover, models that have been trained on in vitro data cannot account for interactions with other types of cells. Drug-response data that are based on patient-derived cell cultures, xenografts, and organoids, on the other hand, are not available in the quantities that are needed to train high-capacity machine-learning models. We found that pre-training deep neural network models of drug sensitivity on in vitro drug-sensitivity databases before fine-tuning the model parameters on patient-derived data improves the models’ accuracy and improves the biological plausibility of the features, compared to training only on patient-derived data. From our experiments, we can conclude that pre-trained models outperform models that have been trained on the target domains in the vast majority of cases.

Learning dynamic treatment strategies for coronary heart diseases by artificial intelligence: real-world data-driven study

BACKGROUND

Coronary heart disease (CHD) has become the leading cause of death and one of the most serious epidemic diseases worldwide. CHD is characterized by urgency, danger and severity, and dynamic treatment strategies for CHD patients are needed. We aimed to build and validate an AI model for dynamic treatment recommendations for CHD patients with the goal of improving patient outcomes and learning best practices from clinicians to help clinical decision support for treating CHD patients.

METHODS

We formed the treatment strategy as a sequential decision problem, and applied an AI supervised reinforcement learning-long short-term memory (SRL-LSTM) framework that combined supervised learning (SL) and reinforcement learning (RL) with an LSTM network to track patients' states to learn a recommendation model that took a patient's diagnosis and evolving health status as input and provided a treatment recommendation in the form of whether to take specific drugs. The experiments were conducted by leveraging a real-world intensive care unit (ICU) database with 13,762 admitted patients diagnosed with CHD. We compared the performance of the applied SRL-LSTM model and several state-of-the-art SL and RL models in reducing the estimated in-hospital mortality and the Jaccard similarity with clinicians' decisions. We used a random forest algorithm to calculate the feature importance of both the clinician policy and the AI policy to illustrate the interpretability of the AI model.

RESULTS

Our experimental study demonstrated that the AI model could help reduce the estimated in-hospital mortality through its RL function and learn the best practice from clinicians through its SL function. The similarity between the clinician policy and the AI policy regarding the surviving patients was high, while for the expired patients, it was much lower. The dynamic treatment strategies made by the AI model were clinically interpretable and relied on sensible clinical features extracted according to monitoring indexes and risk factors for CHD patients.

CONCLUSIONS

We proposed a pipeline for constructing an AI model to learn dynamic treatment strategies for CHD patients that could improve patient outcomes and mimic the best practices of clinicians. And a lot of further studies and efforts are needed to make it practical.

Matching anticancer compounds and tumor cell lines by neural networks with ranking loss

Computational drug sensitivity models have the potential to improve therapeutic outcomes by identifying targeted drug components that are likely to achieve the highest efficacy for a cancer cell line at hand at a therapeutic dose. State of the art drug sensitivity models use regression techniques to predict the inhibitory concentration of a drug for a tumor cell line. This regression objective is not directly aligned with either of these principal goals of drug sensitivity models: We argue that drug sensitivity modeling should be seen as a ranking problem with an optimization criterion that quantifies a drug's inhibitory capacity for the cancer cell line at hand relative to its toxicity for healthy cells. We derive an extension to the well-established drug sensitivity regression model PaccMann that employs a ranking loss and focuses on the ratio of inhibitory concentration and therapeutic dosage range. We find that the ranking extension significantly enhances the model's capability to identify the most effective anticancer drugs for unseen tumor cell profiles based in on in-vitro data.

Fostering Palliative Care Through Digital Intervention: A Platform for Adult Patients With Hematologic Malignancies

Patient-reported outcomes (PROs) are an emerging paradigm in clinical research and healthcare, aiming to capture the patient's self-assessed health status in order to gauge efficacy of treatment from their perspective. As these patient-generated health data provide insights into the effects of healthcare processes in real-life settings beyond the clinical setting, they can also be viewed as a resolution beyond what can be gleaned directly by the clinician. To this end, patients are identified as a key stakeholder of the healthcare decision making process, instead of passively following their doctor's guidance. As this joint decision-making process requires constant and high-quality communication between the patient and his/her healthcare providers, novel methodologies and tools have been proposed to promote richer and preemptive communication to facilitate earlier recognition of potential complications. To this end, as PROs can be used to quantify the patient impact (especially important for chronic conditions such as cancer), they can play a prominent role in providing patient-centric care. In this paper, we introduce the MyPal platform that aims to support adults suffering from hematologic malignancies, focusing on the technical design and highlighting the respective challenges. MyPal is a Horizon 2020 European project aiming to support palliative care for cancer patients via the electronic PROs (ePROs) paradigm, building upon modern eHealth technologies. To this end, MyPal project evaluate the proposed eHealth intervention via clinical studies and assess its potential impact on the provided palliative care. More specifically, MyPal platform provides specialized applications supporting the regular answering of well-defined and standardized questionnaires, spontaneous symptoms reporting, educational material provision, notifications etc. The presented platform has been validated by end-users and is currently in the phase of pilot testing in a clinical study to evaluate its feasibility and its potential impact on the quality of life of palliative care patients with hematologic malignancies.

Navigating Multi-Scale Cancer Systems Biology Towards Model-Driven Clinical Oncology and Its Applications in Personalized Therapeutics

Rapid advancements in high-throughput omics technologies and experimental protocols have led to the generation of vast amounts of scale-specific biomolecular data on cancer that now populates several online databases and resources. Cancer systems biology models built using this data have the potential to provide specific insights into complex multifactorial aberrations underpinning tumor initiation, development, and metastasis. Furthermore, the annotation of these single- and multi-scale models with patient data can additionally assist in designing personalized therapeutic interventions as well as aid in clinical decision-making. Here, we have systematically reviewed the emergence and evolution of (i) repositories with scale-specific and multi-scale biomolecular cancer data, (ii) systems biology models developed using this data, (iii) associated simulation software for the development of personalized cancer therapeutics, and (iv) translational attempts to pipeline multi-scale panomics data for data-driven in silico clinical oncology. The review concludes that the absence of a generic, zero-code, panomics-based multi-scale modeling pipeline and associated software framework, impedes the development and seamless deployment of personalized in silico multi-scale models in clinical settings.

Oncology Information System: A Qualitative Study to Identify Cancer Patient Care Workflows

Oncology information systems provide solutions for managing the information of cancer patients and enable monitoring of different aspects of cancer patient care. Since the use of oncology information systems enhances the quality of care, improves documentation, optimizes resource allocation, and increases the cost-effectiveness of care services, attention to these systems' performance and their adaptation to workflows seems necessary. The purpose of this study was to identify cancer patient care workflows to design an oncology information system for Iran. This study employed a qualitative design and was conducted in 2019. Semi-structured interviews were conducted with 25 experts to determine their views on identifying workflows for cancer patients' care. The participants were clinical and non-clinical staff at six university hospitals equipped with oncology wards. The method of data analysis was framework analysis. The cancer patient care workflows consisted of two categories, including cancer diagnosis workflows and cancer treatment workflows. Cancer diagnosis workflows fall into three subcategories, i.e., the patient's referral to the clinic, an examination of the patient's condition, and pathology workflows. On the other hand, cancer treatment workflows are divided into various treatments offered to cancer patients and workflows in the chemotherapy and radiotherapy wards. Given the variety of services and the complexity of caring for cancer patients as well as the involvement of various specialists in the process of care, identifying and optimizing workflows in the oncology information system reduces errors, enhances data accuracy, eliminates unnecessary steps, and ultimately improve the service delivery to cancer patients.

Integration of mathematical model predictions into routine workflows to support clinical decision making in haematology

Background

Individualization and patient-specific optimization of treatment is a major goal of modern health care. One way to achieve this goal is the application of high-resolution diagnostics together with the application of targeted therapies. However, the rising number of different treatment modalities also induces new challenges: Whereas randomized clinical trials focus on proving average treatment effects in specific groups of patients, direct conclusions at the individual patient level are problematic. Thus, the identification of the best patient-specific treatment options remains an open question. Systems medicine, specifically mechanistic mathematical models, can substantially support individual treatment optimization. In addition to providing a better general understanding of disease mechanisms and treatment effects, these models allow for an identification of patient-specific parameterizations and, therefore, provide individualized predictions for the effect of different treatment modalities.

Results

In the following we describe a software framework that facilitates the integration of mathematical models and computer simulations into routine clinical processes to support decision-making. This is achieved by combining standard data management and data exploration tools, with the generation and visualization of mathematical model predictions for treatment options at an individual patient level.

Conclusions

By integrating model results in an audit trail compatible manner into established clinical workflows, our framework has the potential to foster the use of systems-medical approaches in clinical practice. We illustrate the framework application by two use cases from the field of haematological oncology.

Technical, Biological, and Systems Barriers for Molecular Clinical Decision Support

Genome-enabled or molecular clinical decision support (CDS) systems provide unique advantages for the clinical use of genomic data; however, their implementation is complicated by technical, biological, and systemic barriers. This article reviews the substantial technical progress that has been made in the past decade and finds that the underlying biological limitations of genomics as well as systemic barriers to adoption of molecular CDS have been comparatively underestimated. A hybrid consultative CDS system, which integrates a genomics consultant into an active CDS system, may provide an interim path forward.

A study on the predictability of acute lymphoblastic leukaemia response to treatment using a hybrid oncosimulator

Efficient use of Virtual Physiological Human (VPH)-type models for personalized treatment response prediction purposes requires a precise model parameterization. In the case where the available personalized data are not sufficient to fully determine the parameter values, an appropriate prediction task may be followed. This study, a hybrid combination of computational optimization and machine learning methods with an already developed mechanistic model called the acute lymphoblastic leukaemia (ALL) Oncosimulator which simulates ALL progression and treatment response is presented. These methods are used in order for the parameters of the model to be estimated for retrospective cases and to be predicted for prospective ones. The parameter value prediction is based on a regression model trained on retrospective cases. The proposed Hybrid ALL Oncosimulator system has been evaluated when predicting the pre-phase treatment outcome in ALL. This has been correctly achieved for a significant percentage of patient cases tested (approx. 70% of patients). Moreover, the system is capable of denying the classification of cases for which the results are not trustworthy enough. In that case, potentially misleading predictions for a number of patients are avoided, while the classification accuracy for the remaining patient cases further increases. The results obtained are particularly encouraging regarding the soundness of the proposed methodologies and their relevance to the process of achieving clinical applicability of the proposed Hybrid ALL Oncosimulator system and VPH models in general.