Search

BackgroundPatients with cancer starting systemic treatment programs, such as chemotherapy, often develop depression. A prediction model may assist physicians and health care workers in the early identification of these vulnerable patients. ObjectiveThis study aimed to develop a prediction model for depression risk within the first month of cancer treatment. MethodsWe included 16,159 patients diagnosed with cancer starting chemo- or radiotherapy treatment between 2008 and 2021. Machine learning models (eg, least absolute shrinkage and selection operator [LASSO] logistic regression) and natural language processing models (Bidirectional Encoder Representations from Transformers [BERT]) were used to develop multimodal prediction models using both electronic health record data and unstructured text (patient emails and clinician notes). Model performance was assessed in an independent test set (n=5387, 33%) using area under the receiver operating characteristic curve (AUROC), calibration curves, and decision curve analysis to assess initial clinical impact use. ResultsAmong 16,159 patients, 437 (2.7%) received a depression diagnosis within the first month of treatment. The LASSO logistic regression models based on the structured data (AUROC 0.74, 95% CI 0.71-0.78) and structured data with email classification scores (AUROC 0.74, 95% CI 0.71-0.78) had the best discriminative performance. The BERT models based on clinician notes and structured data with email classification scores had AUROCs around 0.71. The logistic regression model based on email classification scores alone performed poorly (AUROC 0.54, 95% CI 0.52-0.56), and the model based solely on clinician notes had the worst performance (AUROC 0.50, 95% CI 0.49-0.52). Calibration was good for the logistic regression models, whereas the BERT models produced overly extreme risk estimates even after recalibration. There was a small range of decision thresholds for which the best-performing model showed promising clinical effectiveness use. The risks were underestimated for female and Black patients. ConclusionsThe results demonstrated the potential and limitations of machine learning and multimodal models for predicting depression risk in patients with cancer. Future research is needed to further validate these models, refine the outcome label and predictors related to mental health, and address biases across subgroups.

Abstract Background There is a growing interest in the use of F-18 FDG PET-CT to monitor tuberculosis (TB) treatment response. Tuberculosis lung lesions are often complex and diffuse, with dynamic changes during treatment and persisting metabolic activity after apparent clinical cure. This poses a challenge in quantifying scan-based markers of burden of disease and disease activity. We used semi-automated, whole lung quantification of lung lesions to analyse serial FDG PET-CT scans from the Catalysis TB Treatment Response Cohort to identify characteristics that best correlated with clinical and microbiological outcomes. Results Quantified scan metrics were already associated with clinical outcomes at diagnosis and 1 month after treatment, with further improved accuracy to differentiate clinical outcomes after standard treatment duration (month 6). A high cavity volume showed the strongest association with a risk of treatment failure (AUC 0.81 to predict failure at diagnosis), while a suboptimal reduction of the total glycolytic activity in lung lesions during treatment had the strongest association with recurrent disease (AUC 0.8 to predict pooled unfavourable outcomes). During the first year after TB treatment lesion burden reduced; but for many patients, there were continued dynamic changes of individual lesions. Conclusions Quantification of FDG PET-CT images better characterised TB treatment outcomes than qualitative scan patterns and robustly measured the burden of disease. In future, validated metrics may be used to stratify patients and help evaluate the effectiveness of TB treatment modalities.

Pulmonary tuberculosis (PTB) is characterized by lung granulomas, inflammation and tissue destruction. Here we used within-subject peripheral blood gene expression over time to correlate with the within-subject lung metabolic activity, as measured by positron emission tomography (PET) to identify biological processes and pathways underlying overall resolution of lung inflammation. We used next-generation RNA sequencing and [18F]FDG PET-CT data, collected at diagnosis, week 4, and week 24, from 75 successfully cured PTB patients, with the [18F]FDG activity as a surrogate for lung inflammation. Our linear mixed-effects models required that for each individual the slope of the line of [18F]FDG data in the outcome and the slope of the peripheral blood transcript expression data correlate, i.e., the slopes of the outcome and explanatory variables had to be similar. Of 10,295 genes that changed as a function of time, we identified 639 genes whose expression profiles correlated with decreasing [18F]FDG uptake levels in the lungs. Gene enrichment over-representation analysis revealed that numerous biological processes were significantly enriched in the 639 genes, including several well known in TB transcriptomics such as platelet degranulation and response to interferon gamma, thus validating our novel approach. Others not previously associated with TB pathobiology included smooth muscle contraction, a set of pathways related to mitochondrial function and cell death, as well as a set of pathways connecting transcription, translation and vesicle formation. We observed up-regulation in genes associated with B cells, and down-regulation in genes associated with platelet activation. We found 254 transcription factor binding sites to be enriched among the 639 gene promoters. In conclusion, we demonstrated that of the 10,295 gene expression changes in peripheral blood, only a subset of 639 genes correlated with inflammation in the lungs, and the enriched pathways provide a description of the biology of resolution of lung inflammation as detectable in peripheral blood. Surprisingly, resolution of PTB inflammation is positively correlated with smooth muscle contraction and, extending our previous observation on mitochondrial genes, shows the presence of mitochondrial stress. We focused on pathway analysis which can enable therapeutic target discovery and potential modulation of the host response to TB.

Arterial spin labeling (ASL) has undergone significant development since its inception, with a focus on improving standardization and reproducibility of its acquisition and quantification. In a community-wide effort towards robust and reproducible clinical ASL image processing, we developed the software package ExploreASL, allowing standardized analyses across centers and scanners.The procedures used in ExploreASL capitalize on published image processing advancements and address the challenges of multi-center datasets with scanner-specific processing and artifact reduction to limit patient exclusion. ExploreASL is self-contained, written in MATLAB and based on Statistical Parameter Mapping (SPM) and runs on multiple operating systems. To facilitate collaboration and data-exchange, the toolbox follows several standards and recommendations for data structure, provenance, and best analysis practice.ExploreASL was iteratively refined and tested in the analysis of >10,000 ASL scans using different pulse-sequences in a variety of clinical populations, resulting in four processing modules: Import, Structural, ASL, and Population that perform tasks, respectively, for data curation, structural and ASL image processing and quality control, and finally preparing the results for statistical analyses on both single-subject and group level. We illustrate ExploreASL processing results from three cohorts: perinatally HIV-infected children, healthy adults, and elderly at risk for neurodegenerative disease. We show the reproducibility for each cohort when processed at different centers with different operating systems and MATLAB versions, and its effects on the quantification of gray matter cerebral blood flow.ExploreASL facilitates the standardization of image processing and quality control, allowing the pooling of cohorts which may increase statistical power and discover between-group perfusion differences. Ultimately, this workflow may advance ASL for wider adoption in clinical studies, trials, and practice.

Abstract Background There is a growing interest in the use of 18F-FDG PET-CT to monitor tuberculosis (TB) treatment response. However, TB causes complex and widespread pathology, which is challenging to segment and quantify in a reproducible manner. To address this, we developed a technique to standardise uptake (Z-score), segment and quantify tuberculous lung lesions on PET and CT concurrently, in order to track changes over time. We used open source tools and created a MATLAB script. The technique was optimised on a training set of five pulmonary tuberculosis (PTB) cases after standard TB therapy and 15 control patients with lesion-free lungs. Results We compared the proposed method to a fixed threshold (SUV > 1) and manual segmentation by two readers and piloted the technique successfully on scans of five control patients and five PTB cases (four cured and one failed treatment case), at diagnosis and after 1 and 6 months of treatment. There was a better correlation between the Z-score-based segmentation and manual segmentation than SUV > 1 and manual segmentation in terms of overall spatial overlap (measured in Dice similarity coefficient) and specificity (1 minus false positive volume fraction). However, SUV > 1 segmentation appeared more sensitive. Both the Z-score and SUV > 1 showed very low variability when measuring change over time. In addition, total glycolytic activity, calculated using segmentation by Z-score and lesion-to-background ratio, correlated well with traditional total glycolytic activity calculations. The technique quantified various PET and CT parameters, including the total glycolytic activity index, metabolic lesion volume, lesion volumes at different CT densities and combined PET and CT parameters. The quantified metrics showed a marked decrease in the cured cases, with changes already apparent at month one, but remained largely unchanged in the failed treatment case. Conclusions Our technique is promising to segment and quantify the lung scans of pulmonary tuberculosis patients in a semi-automatic manner, appropriate for measuring treatment response. Further validation is required in larger cohorts.

BackgroundCerebral microbleeds (CMB) occur in the context of cerebral small vessel disease. Other brain MRI markers of cerebral small vessel disease are associated with the occurrence of postoperative delirium (POD) and postoperative cognitive dysfunction (POCD), but for CMB this is unknown. We aimed to study the association between CMB and the occurrence of POD and POCD in older individuals.MethodsThe current study consists of 65 patients (72±5 years) from the BIOCOG study, which is a prospective, observational study of patients who underwent an elective surgery of at least 60 minutes. Patients in the current study received a preoperative cerebral MRI scan including a 3D susceptibility-weighted imaging sequence to detect CMB. The occurrence of POD was screened for twice a day until postoperative day 7 by using the DSM-5, NuDesc, CAM, and CAM-ICU. The occurrence of POCD was determined by the reliable change index model at 7 days after surgery or discharge, respectively, and 3 months after surgery. Statistical analyses consisted of logistic regression adjusted for age and gender.ResultsA total of 39 CMB were detected in 17 patients (26%) prior to surgery. POD occurred in 14 out of 65 patients (22%). POCD at 7 days after surgery occurred in 11 out of 54 patients (20%) and in 3 out of 40 patients at the 3 month follow-up (8%). Preoperative CMB were not associated with the occurrence of POD (OR (95%-CI): 0.28 (0.05, 1.57); p = 0.147) or POCD at 7 days after surgery (0.76 (0.16, 3.54); p = 0.727) or at 3 months follow-up (0.61 (0.03, 11.64); p = 0.740).ConclusionWe did not find an association between preoperative CMB and the occurrence of POD or POCD.Trial registrationclinicaltrials.gov (NCT02265263) on 23 September 2014.