A machine learning approach for predicting high risk hospitalized patients with COVID-19 SARS-Cov-2.

BACKGROUND: This study aimed to explore whether explainable Artificial Intelligence methods can be fruitfully used to improve the medical management of patients suffering from complex diseases, and in particular to predict the death risk in hospitalized patients with SARS-Cov-2 based on admission data. METHODS: This work is based on an observational ambispective study that comprised patients older than 18 years with a positive SARS-Cov-2 diagnosis that were admitted to the hospital Azienda Ospedaliera "SS Antonio e Biagio e Cesare Arrigo", Alessandria, Italy from February, 24 2020 to May, 31 2021, and that completed the disease treatment inside this structure. The patients'medical history, demographic, epidemiologic and clinical data were collected from the electronic medical records system and paper based medical records, entered and managed by the Clinical Study Coordinators using the REDCap electronic data capture tool patient chart. The dataset was used to train and to evaluate predictive ML models. RESULTS: We overall trained, analysed and evaluated 19 predictive models (both supervised and unsupervised) on data from 824 patients described by 43 features. We focused our attention on models that provide an explanation that is understandable and directly usable by domain experts, and compared the results against other classical machine learning approaches. Among the former, JRIP showed the best performance in 10-fold cross validation, and the best average performance in a further validation test using a different patient dataset from the beginning of the third COVID-19 wave. Moreover, JRIP showed comparable performances with other approaches that do not provide a clear and/or understandable explanation. CONCLUSIONS: The ML supervised models showed to correctly discern between low-risk and high-risk patients, even when the medical disease context is complex and the list of features is limited to information available at admission time. Furthermore, the models demonstrated to reasonably perform on a dataset from the third COVID-19 wave that was not used in the training phase. Overall, these results are remarkable: (i) from a medical point of view, these models evaluate good predictions despite the possible differences entitled with different care protocols and the possible influence of other viral variants (i.e. delta variant); (ii) from the organizational point of view, they could be used to optimize the management of health-care path at the admission time.

Supervised machine learning enables non-invasive lesion characterization in primary prostate cancer with [68Ga]Ga-PSMA-11 PET/MRI.

PURPOSE: Risk classification of primary prostate cancer in clinical routine is mainly based on prostate-specific antigen (PSA) levels, Gleason scores from biopsy samples, and tumor-nodes-metastasis (TNM) staging. This study aimed to investigate the diagnostic performance of positron emission tomography/magnetic resonance imaging (PET/MRI) in vivo models for predicting low-vs-high lesion risk (LH) as well as biochemical recurrence (BCR) and overall patient risk (OPR) with machine learning. METHODS: Fifty-two patients who underwent multi-parametric dual-tracer [18F]FMC and [68Ga]Ga-PSMA-11 PET/MRI as well as radical prostatectomy between 2014 and 2015 were included as part of a single-center pilot to a randomized prospective trial (NCT02659527). Radiomics in combination with ensemble machine learning was applied including the [68Ga]Ga-PSMA-11 PET, the apparent diffusion coefficient, and the transverse relaxation time-weighted MRI scans of each patient to establish a low-vs-high risk lesion prediction model (MLH). Furthermore, MBCR and MOPR predictive model schemes were built by combining MLH, PSA, and clinical stage values of patients. Performance evaluation of the established models was performed with 1000-fold Monte Carlo (MC) cross-validation. Results were additionally compared to conventional [68Ga]Ga-PSMA-11 standardized uptake value (SUV) analyses. RESULTS: The area under the receiver operator characteristic curve (AUC) of the MLH model (0.86) was higher than the AUC of the [68Ga]Ga-PSMA-11 SUVmax analysis (0.80). MC cross-validation revealed 89% and 91% accuracies with 0.90 and 0.94 AUCs for the MBCR and MOPR models respectively, while standard routine analysis based on PSA, biopsy Gleason score, and TNM staging resulted in 69% and 70% accuracies to predict BCR and OPR respectively. CONCLUSION: Our results demonstrate the potential to enhance risk classification in primary prostate cancer patients built on PET/MRI radiomics and machine learning without biopsy sampling.

Mdpg: a novel multi-disease diagnosis prediction method based on patient knowledge graphs.

Diagnosis prediction, a key factor in enhancing healthcare efficiency, remains a focal point in clinical decision support research. However, the time-series, sparse and multi-noise characteristics of electronic health record (EHR) data make it a great challenge. Existing methods commonly address these issues using RNNs and incorporating medical prior knowledge from medical knowledge bases, but they neglect the local spatial characteristics and spatial-temporal correlation of the data. Consequently, we propose MDPG, a diagnosis prediction model based on patient knowledge graphs. Initially, we represent the electronic visit records of patients as a patient-centered temporal knowledge graph, capturing the local spatial structure and temporal characteristics of the visit information. Subsequently, we design the spatial graph convolution block, temporal self-attention block, and spatial-temporal synchronous graph convolution block to capture the spatial, temporal, and spatial-temporal correlations embedded in them, respectively. Ultimately, we accomplish the prediction of patients' future states through multi-label classification. We conduct comprehensive experiments on two real-world datasets independently and evaluate the results using visit-level precision@k and code-level accuracy@k metrics. The experimental results demonstrate that MDPG outperforms all baseline models, yielding the best performance.

Bias in algorithms of AI systems developed for COVID-19: A scoping review.

To analyze which ethically relevant biases have been identified by academic literature in artificial intelligence (AI) algorithms developed either for patient risk prediction and triage, or for contact tracing to deal with the COVID-19 pandemic. Additionally, to specifically investigate whether the role of social determinants of health (SDOH) have been considered in these AI developments or not. We conducted a scoping review of the literature, which covered publications from March 2020 to April 2021. ​Studies mentioning biases on AI algorithms developed for contact tracing and medical triage or risk prediction regarding COVID-19 were included. From 1054 identified articles, 20 studies were finally included. We propose a typology of biases identified in the literature based on bias, limitations and other ethical issues in both areas of analysis. Results on health disparities and SDOH were classified into five categories: racial disparities, biased data, socio-economic disparities, unequal accessibility and workforce, and information communication. SDOH needs to be considered in the clinical context, where they still seem underestimated. Epidemiological conditions depend on geographic location, so the use of local data in studies to develop international solutions may increase some biases. Gender bias was not specifically addressed in the articles included. The main biases are related to data collection and management. Ethical problems related to privacy, consent, and lack of regulation have been identified in contact tracing while some bias-related health inequalities have been highlighted. There is a need for further research focusing on SDOH and these specific AI apps.