Deep learning in systems medicine

A comprehensive approach for osteoporosis detection through chest CT analysis and bone turnover markers: harnessing radiomics and deep learning techniques

Purpose

The main objective of this study is to assess the possibility of using radiomics, deep learning, and transfer learning methods for the analysis of chest CT scans. An additional aim is to combine these techniques with bone turnover markers to identify and screen for osteoporosis in patients.

Method

A total of 488 patients who had undergone chest CT and bone turnover marker testing, and had known bone mineral density, were included in this study. ITK-SNAP software was used to delineate regions of interest, while radiomics features were extracted using Python. Multiple 2D and 3D deep learning models were trained to identify these regions of interest. The effectiveness of these techniques in screening for osteoporosis in patients was compared.

Result

Clinical models based on gender, age, and β-cross achieved an accuracy of 0.698 and an AUC of 0.665. Radiomics models, which utilized 14 selected radiomics features, achieved a maximum accuracy of 0.750 and an AUC of 0.739. The test group yielded promising results: the 2D Deep Learning model achieved an accuracy of 0.812 and an AUC of 0.855, while the 3D Deep Learning model performed even better with an accuracy of 0.854 and an AUC of 0.906. Similarly, the 2D Transfer Learning model achieved an accuracy of 0.854 and an AUC of 0.880, whereas the 3D Transfer Learning model exhibited an accuracy of 0.740 and an AUC of 0.737. Overall, the application of 3D deep learning and 2D transfer learning techniques on chest CT scans showed excellent screening performance in the context of osteoporosis.

Conclusion

Bone turnover markers may not be necessary for osteoporosis screening, as 3D deep learning and 2D transfer learning techniques utilizing chest CT scans proved to be equally effective alternatives.

Clinical knowledge-guided deep reinforcement learning for sepsis antibiotic dosing recommendations

Sepsis is the third leading cause of death worldwide. Antibiotics are an important component in the treatment of sepsis. The use of antibiotics is currently facing the challenge of increasing antibiotic resistance (Evans et al., 2021). Sepsis medication prediction can be modeled as a Markov decision process, but existing methods fail to integrate with medical knowledge, making the decision process potentially deviate from medical common sense and leading to underperformance. (Wang et al., 2021). In this paper, we use Deep Q-Network (DQN) to construct a Sepsis Anti-infection DQN (SAI-DQN) model to address the challenge of determining the optimal combination and duration of antibiotics in sepsis treatment. By setting sepsis clinical knowledge as reward functions to guide DQN complying with medical guidelines, we formed personalized treatment recommendations for antibiotic combinations. The results showed that our model had a higher average value for decision-making than clinical decisions. For the test set of patients, our model predicts that 79.07% of patients will achieve a favorable prognosis with the recommended combination of antibiotics. By statistically analyzing decision trajectories and drug action selection, our model was able to provide reasonable medication recommendations that comply with clinical practices. Our model was able to improve patient outcomes by recommending appropriate antibiotic combinations in line with certain clinical knowledge.

Deep Learning Prediction Model for Patient Survival Outcomes in Palliative Care Using Actigraphy Data and Clinical Information

(1) Background: Predicting the survival of patients in end-of-life care is crucial, and evaluating their performance status is a key factor in determining their likelihood of survival. However, the current traditional methods for predicting survival are limited due to their subjective nature. Wearable technology that provides continuous patient monitoring is a more favorable approach for predicting survival outcomes among palliative care patients. (2) Aims and objectives: In this study, we aimed to explore the potential of using deep learning (DL) model approaches to predict the survival outcomes of end-stage cancer patients. Furthermore, we also aimed to compare the accuracy of our proposed activity monitoring and survival prediction model with traditional prognostic tools, such as the Karnofsky Performance Scale (KPS) and the Palliative Performance Index (PPI). (3) Method: This study recruited 78 patients from the Taipei Medical University Hospital's palliative care unit, with 66 (39 male and 27 female) patients eventually being included in our DL model for predicting their survival outcomes. (4) Results: The KPS and PPI demonstrated an overall accuracy of 0.833 and 0.615, respectively. In comparison, the actigraphy data exhibited a higher accuracy at 0.893, while the accuracy of the wearable data combined with clinical information was even better, at 0.924. (5) Conclusion: Our study highlights the significance of incorporating clinical data alongside wearable sensors to predict prognosis. Our findings suggest that 48 h of data is sufficient for accurate predictions. The integration of wearable technology and the prediction model in palliative care has the potential to improve decision making for healthcare providers and can provide better support for patients and their families. The outcomes of this study can possibly contribute to the development of personalized and patient-centered end-of-life care plans in clinical practice.

Improving therapeutic synergy score predictions with adverse effects using multi-task heterogeneous network learning

Drug combinations could trigger pharmacological therapeutic effects (TEs) and adverse effects (AEs). Many computational methods have been developed to predict TEs, e.g. the therapeutic synergy scores of anti-cancer drug combinations, or AEs from drug-drug interactions. However, most of the methods treated the AEs and TEs predictions as two separate tasks, ignoring the potential mechanistic commonalities shared between them. Based on previous clinical observations, we hypothesized that by learning the shared mechanistic commonalities between AEs and TEs, we could learn the underlying MoAs (mechanisms of actions) and ultimately improve the accuracy of TE predictions. To test our hypothesis, we formulated the TE prediction problem as a multi-task heterogeneous network learning problem that performed TE and AE learning tasks simultaneously. To solve this problem, we proposed Muthene (multi-task heterogeneous network embedding) and evaluated it on our collected drug-drug interaction dataset with both TEs and AEs indications. Our experimental results showed that, by including the AE prediction as an auxiliary task, Muthene generated more accurate TE predictions than standard single-task learning methods, which supports our hypothesis. Using a drug pair Vincristine-Dasatinib as a case study, we demonstrated that our method not only provides a novel way of TE predictions but also helps us gain a deeper understanding of the MoAs of drug combinations.

Immune subtype identification and multi-layer perceptron classifier construction for breast cancer

Introduction

Breast cancer is a heterogeneous tumor. Tumor microenvironment (TME) has an important effect on the proliferation, metastasis, treatment, and prognosis of breast cancer.

Methods

In this study, we calculated the relative proportion of tumor infiltrating immune cells (TIICs) in the breast cancer TME, and used the consensus clustering algorithm to cluster the breast cancer subtypes. We also developed a multi-layer perceptron (MLP) classifier based on a deep learning framework to detect breast cancer subtypes, which 70% of the breast cancer research cohort was used for the model training and 30% for validation.

Results

By performing the K-means clustering algorithm, the research cohort was clustered into two subtypes. The Kaplan-Meier survival estimate analysis showed significant differences in the overall survival (OS) between the two identified subtypes. Estimating the difference in the relative proportion of TIICs showed that the two subtypes had significant differences in multiple immune cells, such as CD8, CD4, and regulatory T cells. Further, the expression level of immune checkpoint molecules (PDL1, CTLA4, LAG3, TIGIT, CD27, IDO1, ICOS) and tumor mutational burden (TMB) also showed significant differences between the two subtypes, indicating the clinical value of the two subtypes. Finally, we identified a 38-gene signature and developed a multilayer perceptron (MLP) classifier that combined multi-gene signature to identify breast cancer subtypes. The results showed that the classifier had an accuracy rate of 93.56% and can be robustly used for the breast cancer subtype diagnosis.

Conclusion

Identification of breast cancer subtypes based on the immune signature in the tumor microenvironment can assist clinicians to effectively and accurately assess the progression of breast cancer and formulate different treatment strategies for different subtypes.

Towards a Virtual "Global Academia of Surgeons"

OBJECTIVE

To explore the prospects of academic e-learning by evaluating our long-standing internet-based surgical learning program and to assess the impact of training on the presentation skills of our residents. The eventual goal is to search whether such models could be further developed by the European Surgical Association (ESA).

BACKGROUND

E-learning has become a major educational trend particularly during the COVID-19 pandemic. For more than a decade, our academic tertiary center has released weekly video-lectures covering the entire abdominal-surgical curriculum for residents. All lessons were prepared under the supervision of specialized experts and recorded and edited by a professional film team before being released on a dedicated YouTube channel ( https://www.usz.ch/surgical-resident-lectures ).

METHODS

To date, our channel includes 120 presentations with more than 619,000 views. We conducted a survey among online users with a medical background and tested the benefits and potential for improvements of local stakeholders to collect individual reviews.

RESULTS

A total of 708 users from 106 countries participated in the survey. Continuing medical education (49%), specific questions (38%), and exam preparation (33%) were the main motivations for video viewing. The preferred topics were current guidelines (69%), latest research topics (59%), and complex surgical conditions (52%). Ninety-four percent of our local audience reported a positive learning experience.

CONCLUSION

E-learning can improve local academic training and promote the global visibility of strong academic centers. Providing free and unrestricted expertise via social media is a novel and groundbreaking opportunity that fills a global education gap by dissemination of surgical education on an unprecedented scale. Expert associations such as the ESA may adopt similar formats and foster their perception as true beacons of knowledge.

Deconstruction of Risk Prediction of Ischemic Cardiovascular and Cerebrovascular Diseases Based on Deep Learning

Over the years, with the widespread use of computer technology and the dramatic increase in electronic medical data, data-driven approaches to medical data analysis have emerged. However, the analysis of medical data remains challenging due to the mixed nature of the data, the incompleteness of many records, and the high level of noise. This paper proposes an improved neural network DBN-LSTM that combines a deep belief network (DBN) with a long short-term memory (LSTM) network. The subset of feature attributes processed by CFS-EGA is used for training, and the optimal selection test of the number of hidden layers is performed on the upper DBN in the process of training DBN-LSTM. At the same time, the validation set is combined to determine the hyperparameters of the LSTM. Construct the DNN, CNN, and long short-term memory (LSTM) network for comparative analysis with DBN-LSTM. Use the classification method to compare the average of the final results of the two experiments. The results show that the prediction accuracy of DBN-LSTM for cardiovascular and cerebrovascular diseases reaches 95.61%, which is higher than the three traditional neural networks.

Artificial intelligence and liver transplantation: Looking for the best donor-recipient pairing

Decision-making based on artificial intelligence (AI) methodology is increasingly present in all areas of modern medicine. In recent years, models based on deep-learning have begun to be used in organ transplantation. Taking into account the huge number of factors and variables involved in donor-recipient (D-R) matching, AI models may be well suited to improve organ allocation. AI-based models should provide two solutions: complement decision-making with current metrics based on logistic regression and improve their predictability. Hundreds of classifiers could be used to address this problem. However, not all of them are really useful for D-R pairing. Basically, in the decision to assign a given donor to a candidate in waiting list, a multitude of variables are handled, including donor, recipient, logistic and perioperative variables. Of these last two, some of them can be inferred indirectly from the team's previous experience. Two groups of AI models have been used in the D-R matching: artificial neural networks (ANN) and random forest (RF). The former mimics the functional architecture of neurons, with input layers and output layers. The algorithms can be uni- or multi-objective. In general, ANNs can be used with large databases, where their generalizability is improved. However, they are models that are very sensitive to the quality of the databases and, in essence, they are black-box models in which all variables are important. Unfortunately, these models do not allow to know safely the weight of each variable. On the other hand, RF builds decision trees and works well with small cohorts. In addition, they can select top variables as with logistic regression. However, they are not useful with large databases, due to the extreme number of decision trees that they would generate, making them impractical. Both ANN and RF allow a successful donor allocation in over 80% of D-R pairing, a number much higher than that obtained with the best statistical metrics such as model for end-stage liver disease, balance of risk score, and survival outcomes following liver transplantation scores. Many barriers need to be overcome before these deep-learning-based models can be included for D-R matching. The main one of them is the resistance of the clinicians to leave their own decision to autonomous computational models.

Optimization of Complete Rat Heart Decellularization Using Artificial Neural Networks

Whole organ decellularization techniques have facilitated the fabrication of extracellular matrices (ECMs) for engineering new organs. Unfortunately, there is no objective gold standard evaluation of the scaffold without applying a destructive method such as histological analysis or DNA removal quantification of the dry tissue. Our proposal is a software application using deep convolutional neural networks (DCNN) to distinguish between different stages of decellularization, determining the exact moment of completion. Hearts from male Sprague Dawley rats (n = 10) were decellularized using 1% sodium dodecyl sulfate (SDS) in a modified Langendorff device in the presence of an alternating rectangular electric field. Spectrophotometric measurements of deoxyribonucleic acid (DNA) and total proteins concentration from the decellularization solution were taken every 30 min. A monitoring system supervised the sessions, collecting a large number of photos saved in corresponding folders. This system aimed to prove a strong correlation between the data gathered by spectrophotometry and the state of the heart that could be visualized with an OpenCV-based spectrometer. A decellularization completion metric was built using a DCNN based classifier model trained using an image set comprising thousands of photos. Optimizing the decellularization process using a machine learning approach launches exponential progress in tissue bioengineering research.

Defining Blood Plasma and Serum Metabolome by GC-MS

Metabolomics uses advanced analytical chemistry methods to analyze metabolites in biological samples. The most intensively studied samples are blood and its liquid components: plasma and serum. Armed with advanced equipment and progressive software solutions, the scientific community has shown that small molecules’ roles in living systems are not limited to traditional “building blocks” or “just fuel” for cellular energy. As a result, the conclusions based on studying the metabolome are finding practical reflection in molecular medicine and a better understanding of fundamental biochemical processes in living systems. This review is not a detailed protocol of metabolomic analysis. However, it should support the reader with information about the achievements in the whole process of metabolic exploration of human plasma and serum using mass spectrometry combined with gas chromatography.

Deep Learning for Human Disease Detection, Subtype Classification, and Treatment Response Prediction Using Epigenomic Data

Deep learning (DL) is a distinct class of machine learning that has achieved first-class performance in many fields of study. For epigenomics, the application of DL to assist physicians and scientists in human disease-relevant prediction tasks has been relatively unexplored until very recently. In this article, we critically review published studies that employed DL models to predict disease detection, subtype classification, and treatment responses, using epigenomic data. A comprehensive search on PubMed, Scopus, Web of Science, Google Scholar, and arXiv.org was performed following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines. Among 1140 initially identified publications, we included 22 articles in our review. DNA methylation and RNA-sequencing data are most frequently used to train the predictive models. The reviewed models achieved a high accuracy ranged from 88.3% to 100.0% for disease detection tasks, from 69.5% to 97.8% for subtype classification tasks, and from 80.0% to 93.0% for treatment response prediction tasks. We generated a workflow to develop a predictive model that encompasses all steps from first defining human disease-related tasks to finally evaluating model performance. DL holds promise for transforming epigenomic big data into valuable knowledge that will enhance the development of translational epigenomics.

Role of Deep Learning in Predicting Aging-Related Diseases: A Scoping Review

Aging refers to progressive physiological changes in a cell, an organ, or the whole body of an individual, over time. Aging-related diseases are highly prevalent and could impact an individual’s physical health. Recently, artificial intelligence (AI) methods have been used to predict aging-related diseases and issues, aiding clinical providers in decision-making based on patient’s medical records. Deep learning (DL), as one of the most recent generations of AI technologies, has embraced rapid progress in the early prediction and classification of aging-related issues. In this paper, a scoping review of publications using DL approaches to predict common aging-related diseases (such as age-related macular degeneration, cardiovascular and respiratory diseases, arthritis, Alzheimer’s and lifestyle patterns related to disease progression), was performed. Google Scholar, IEEE and PubMed are used to search DL papers on common aging-related issues published between January 2017 and August 2021. These papers were reviewed, evaluated, and the findings were summarized. Overall, 34 studies met the inclusion criteria. These studies indicate that DL could help clinicians in diagnosing disease at its early stages by mapping diagnostic predictions into observable clinical presentations; and achieving high predictive performance (e.g., more than 90% accurate predictions of diseases in aging).

A Vision of Future Healthcare: Potential Opportunities and Risks of Systems Medicine from a Citizen and Patient Perspective-Results of a Qualitative Study

Advances in (bio)medicine and technological innovations make it possible to combine high-dimensional, heterogeneous health data to better understand causes of diseases and make them usable for predictive, preventive, and precision medicine. This study aimed to determine views on and expectations of “systems medicine” from the perspective of citizens and patients in six focus group interviews, all transcribed verbatim and content analyzed. A future vision of the use of systems medicine in healthcare served as a stimulus for the discussion. The results show that although certain aspects of systems medicine were seen positive (e.g., use of smart technology, digitalization, and networking in healthcare), the perceived risks dominated. The high degree of technification was perceived as emotionally burdensome (e.g., reduction of people to their data, loss of control, dehumanization). The risk-benefit balance for the use of risk-prediction models for disease events and trajectories was rated as rather negative. There were normative and ethical concerns about unwanted data use, discrimination, and restriction of fundamental rights. These concerns and needs of citizens and patients must be addressed in policy frameworks and health policy implementation strategies to reduce negative emotions and attitudes toward systems medicine and to take advantage of its opportunities.

DeepFeature: feature selection in nonimage data using convolutional neural network

Artificial intelligence methods offer exciting new capabilities for the discovery of biological mechanisms from raw data because they are able to detect vastly more complex patterns of association that cannot be captured by classical statistical tests. Among these methods, deep neural networks are currently among the most advanced approaches and, in particular, convolutional neural networks (CNNs) have been shown to perform excellently for a variety of difficult tasks. Despite that applications of this type of networks to high-dimensional omics data and, most importantly, meaningful interpretation of the results returned from such models in a biomedical context remains an open problem. Here we present, an approach applying a CNN to nonimage data for feature selection. Our pipeline, DeepFeature, can both successfully transform omics data into a form that is optimal for fitting a CNN model and can also return sets of the most important genes used internally for computing predictions. Within the framework, the Snowfall compression algorithm is introduced to enable more elements in the fixed pixel framework, and region accumulation and element decoder is developed to find elements or genes from the class activation maps. In comparative tests for cancer type prediction task, DeepFeature simultaneously achieved superior predictive performance and better ability to discover key pathways and biological processes meaningful for this context. Capabilities offered by the proposed framework can enable the effective use of powerful deep learning methods to facilitate the discovery of causal mechanisms in high-dimensional biomedical data.