Search

BackgroundUnder- or late identification of pulmonary embolism (PE)—a thrombosis of 1 or more pulmonary arteries that seriously threatens patients’ lives—is a major challenge confronting modern medicine. ObjectiveWe aimed to establish accurate and informative machine learning (ML) models to identify patients at high risk for PE as they are admitted to the hospital, before their initial clinical checkup, by using only the information in their medical records. MethodsWe collected demographics, comorbidities, and medications data for 2568 patients with PE and 52,598 control patients. We focused on data available prior to emergency department admission, as these are the most universally accessible data. We trained an ML random forest algorithm to detect PE at the earliest possible time during a patient’s hospitalization—at the time of his or her admission. We developed and applied 2 ML-based methods specifically to address the data imbalance between PE and non-PE patients, which causes misdiagnosis of PE. ResultsThe resulting models predicted PE based on age, sex, BMI, past clinical PE events, chronic lung disease, past thrombotic events, and usage of anticoagulants, obtaining an 80% geometric mean value for the PE and non-PE classification accuracies. Although on hospital admission only 4% (1942/46,639) of the patients had a diagnosis of PE, we identified 2 clustering schemes comprising subgroups with more than 61% (705/1120 in clustering scheme 1; 427/701 and 340/549 in clustering scheme 2) positive patients for PE. One subgroup in the first clustering scheme included 36% (705/1942) of all patients with PE who were characterized by a definite past PE diagnosis, a 6-fold higher prevalence of deep vein thrombosis, and a 3-fold higher prevalence of pneumonia, compared with patients of the other subgroups in this scheme. In the second clustering scheme, 2 subgroups (1 of only men and 1 of only women) included patients who all had a past PE diagnosis and a relatively high prevalence of pneumonia, and a third subgroup included only those patients with a past diagnosis of pneumonia. ConclusionsThis study established an ML tool for early diagnosis of PE almost immediately upon hospital admission. Despite the highly imbalanced scenario undermining accurate PE prediction and using information available only from the patient’s medical history, our models were both accurate and informative, enabling the identification of patients already at high risk for PE upon hospital admission, even before the initial clinical checkup was performed. The fact that we did not restrict our patients to those at high risk for PE according to previously published scales (eg, Wells or revised Genova scores) enabled us to accurately assess the application of ML on raw medical data and identify new, previously unidentified risk factors for PE, such as previous pulmonary disease, in general populations.

Abstract Lipid profiles in biological fluids from patients with Parkinson’s disease (PD) are increasingly investigated in search of biomarkers. However, the lipid profiles in genetic PD remain to be determined, a gap of knowledge of particular interest in PD associated with mutant α-synuclein (SNCA), given the known relationship between this protein and lipids. The objective of this research is to identify serum lipid composition from SNCA A53T mutation carriers and to compare these alterations to those found in cells and transgenic mice carrying the same genetic mutation. We conducted an unbiased lipidomic analysis of 530 lipid species from 34 lipid classes in serum of 30 participants with SNCA mutation with and without PD and 30 healthy controls. The primary analysis was done between 22 PD patients with SNCA+ (SNCA+/PD+) and 30 controls using machine-learning algorithms and traditional statistics. We also analyzed the lipid composition of human clonal-cell lines and tissue from transgenic mice overexpressing the same SNCA mutation. We identified specific lipid classes that best discriminate between SNCA+/PD+ patients and healthy controls and found certain lipid species, mainly from the glycerophosphatidylcholine and triradylglycerol classes, that are most contributory to this discrimination. Most of these alterations were also present in human derived cells and transgenic mice carrying the same mutation. Our combination of lipidomic and machine learning analyses revealed alterations in glycerophosphatidylcholine and triradylglycerol in sera from PD patients as well as cells and tissues expressing mutant α-Syn. Further investigations are needed to establish the pathogenic significance of these α-Syn-associated lipid changes.

While policy-driven discourses promote patient engagement in research, its practice is severely limited. Drawing on participant observations and interviews conducted in 2021, we describe a process of research collaboration with amyotrophic lateral sclerosis (ALS) patients and their relatives to modify an epidemiological questionnaire on ALS, engaging patients as experts in the process of adapting the questionnaire to be patient oriented. The two versions of the questionnaire (the original and modified) were administered in the Israeli ALS patient community to explore hidden mechanisms of risk factors for the disease. Our findings demonstrate the process, measures, and impact of patient engagement on questionnaire modification and use. Our qualitative findings illustrate the participants' suggestions for new questions, feedback on biases and gaps, and an unmet wish to present the patients' life story. Our quantitative data illustrate how the patient-oriented modified questionnaire had more questions answered more comprehensively, as well as more identification, measured by patients' willingness to identify themselves when filling out the modified questionnaire.

Abstract In this research, we exploit repeated parts in daily trajectories in people’s movements, which we refer to as mobility patterns, to train models to identify and predict a person’s lifestyles. We use cellular data of a group (“society”) of people and represent a person’s daily trajectory using semantic labels (e.g., “home”, “work”, and “gym”) given to the main places of interest (POI) he has visited during the day, as determined collectively based on interviewing all people of the group. First, in an unsupervised manner using a neural network (NN), we embed POI-based daily trajectories that always appear together with others in consecutive weeks and identify the result of this embedding with social lifestyles. Second, using these lifestyles as labels for lifestyle prediction, user POI-based daily trajectories are used to train a convolutional NN to extract mobility patterns in the trajectories and a dynamic NN with flexible memory to assemble these patterns to predict a lifestyle for a trajectory never-seen-before. The two-stage algorithm shows model accuracy and generalizability in lifestyle identification and prediction (both for a novel trajectory and a novel user) that are superior to those shown by state-of-the-art algorithms. The code for the algorithm and data sets used in our experiments are available online .