"Using network analysis modularity to group health code systems and decrease dimensionality in machine learning models".

Background: Machine learning (ML) prediction models in healthcare and pharmacy-related research face challenges with encoding high-dimensional Healthcare Coding Systems (HCSs) such as ICD, ATC, and DRG codes, given the trade-off between reducing model dimensionality and minimizing information loss. Objectives: To investigate using Network Analysis modularity as a method to group HCSs to improve encoding in ML models. Methods: The MIMIC-III dataset was utilized to create a multimorbidity network in which ICD-9 codes are the nodes and the edges are the number of patients sharing the same ICD-9 code pairs. A modularity detection algorithm was applied using different resolution thresholds to generate 6 sets of modules. The impact of four grouping strategies on the performance of predicting 90-day Intensive Care Unit readmissions was assessed. The grouping strategies compared: 1) binary encoding of codes, 2) encoding codes grouped by network modules, 3) grouping codes to the highest level of ICD-9 hierarchy, and 4) grouping using the single-level Clinical Classification Software (CCS). The same methodology was also applied to encode DRG codes but limiting the comparison to a single modularity threshold to binary encoding.The performance was assessed using Logistic Regression, Support Vector Machine with a non-linear kernel, and Gradient Boosting Machines algorithms. Accuracy, Precision, Recall, AUC, and F1-score with 95% confidence intervals were reported. Results: Models utilized modularity encoding outperformed ungrouped codes binary encoding models. The accuracy improved across all algorithms ranging from 0.736 to 0.78 for the modularity encoding, to 0.727 to 0.779 for binary encoding. AUC, recall, and precision also improved across almost all algorithms. In comparison with other grouping approaches, modularity encoding generally showed slightly higher performance in AUC, ranging from 0.813 to 0.837, and precision, ranging from 0.752 to 0.782. Conclusions: Modularity encoding enhances the performance of ML models in pharmacy research by effectively reducing dimensionality and retaining necessary information. Across the three algorithms used, models utilizing modularity encoding showed superior or comparable performance to other encoding approaches. Modularity encoding introduces other advantages such as it can be used for both hierarchical and non-hierarchical HCSs, the approach is clinically relevant, and can enhance ML models' clinical interpretation. A Python package has been developed to facilitate the use of the approach for future research.

Metastatic Breast Cancer and Pre-Diagnostic Blood Gene Expression Profiles-The Norwegian Women and Cancer (NOWAC) Post-Genome Cohort.

Breast cancer patients with metastatic disease have a higher incidence of deaths from breast cancer than patients with early-stage cancers. Recent findings suggest that there are differences in immune cell function between metastatic and non-metastatic cases, even years before diagnosis. We have analyzed whole blood gene expression by Illumina bead chips in blood samples taken using the PAXgene blood collection system up to two years before diagnosis. The final study sample included 197 breast cancer cases and 197 age-matched controls. We defined a causal directed acyclic graph to guide a Bayesian data analysis to estimate the risk of metastasis associated with the expression of all genes and with relevant sets of genes. We ranked genes and gene sets according to the sign probability for excess risk. Among the screening detected cancers, 82% were without metastasis, compared to 53% of between-screening detected cancers. Among the highest ranking genes and gene sets associated with metastasis risk, we identified plasmacytiod dentritic cell function, the SLC22 family of transporters, and glutamine metabolism as potential links between the immune system and metastasis. We conclude that there may be potentially wide-reaching differences in blood gene expression profiles between metastatic and non-metastatic breast cancer cases up to two years before diagnosis, which warrants future study.

Predicting breast cancer metastasis from whole-blood transcriptomic measurements.

OBJECTIVE: In this exploratory work we investigate whether blood gene expression measurements predict breast cancer metastasis. Early detection of increased metastatic risk could potentially be life-saving. Our data comes from the Norwegian Women and Cancer epidemiological cohort study. The women who contributed to these data provided a blood sample up to a year before receiving a breast cancer diagnosis. We estimate a penalized maximum likelihood logistic regression. We evaluate this in terms of calibration, concordance probability, and stability, all of which we estimate by the bootstrap. RESULTS: We identify a set of 108 candidate predictor genes that exhibit a fold change in average metastasized observation where there is none for the average non-metastasized observation.

Systematic review with meta-analysis: mortality in acute severe ulcerative colitis.

BACKGROUND: Acute severe ulcerative colitis (ASUC) is a life-threatening condition. Mortality in ASUC decreased in published series but there is uncertainty as to whether this also applies to the real-life setting. AIM: To perform a systematic review and meta-analysis of mortality in ASUC in studies from referral centres and in population-based studies, separately and combined. A second aim was to identify risk factors of mortality in ASUC. METHODS: We searched pubmed and embase from 1998 to 2016, to identify studies that reported 3-month or 12-month mortalities of acute UC in adult patients treated in referral centres, and in population-based studies. RESULTS: Six population-based studies with 741 743 patients and 47 referral centre-based studies with 2556 patients were included. The pooled 3-month and 12-month mortalities were respectively 0.84% and 1.01%. Advanced age was significantly associated with both 3 month and 12 month mortalities (OR = 1.15 per year, 95% CI: 1.10-1.20 and OR = 1.19 per year, 95% CI: 1.15-1.23 respectively). The pooled 3-month and 12-month mortalities were 0.78% and 0.85% in studies with median age of less than 50 and 2.81% and 4.17% in studies with median age of 50 or more, respectively. After adjustment for age, 3-month and 12-month mortalities did not differ between population-based and referral centre-based studies. CONCLUSIONS: Mortality in acute severe ulcerative colitis is approximately 1%; it is higher in older patients. Efforts should be made to improve the care of elderly patients with severe UC.

Convolutional Neural Network for Breathing Phase Detection in Lung Sounds.

We applied deep learning to create an algorithm for breathing phase detection in lung sound recordings, and we compared the breathing phases detected by the algorithm and manually annotated by two experienced lung sound researchers. Our algorithm uses a convolutional neural network with spectrograms as the features, removing the need to specify features explicitly. We trained and evaluated the algorithm using three subsets that are larger than previously seen in the literature. We evaluated the performance of the method using two methods. First, discrete count of agreed breathing phases (using 50% overlap between a pair of boxes), shows a mean agreement with lung sound experts of 97% for inspiration and 87% for expiration. Second, the fraction of time of agreement (in seconds) gives higher pseudo-kappa values for inspiration (0.73-0.88) than expiration (0.63-0.84), showing an average sensitivity of 97% and an average specificity of 84%. With both evaluation methods, the agreement between the annotators and the algorithm shows human level performance for the algorithm. The developed algorithm is valid for detecting breathing phases in lung sound recordings.