scholarly journals Identifying subtypes of depression in clinician-annotated text: a retrospective cohort study

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Benson Kung ◽  
Maurice Chiang ◽  
Gayan Perera ◽  
Megan Pritchard ◽  
Robert Stewart
Keyword(s):  
Retrospective Cohort ◽  
Clinical Utility ◽  
Mental Healthcare ◽  
Data Driven ◽  
Health Records ◽  
Clinical Text ◽  
Disease Prognosis ◽  
Clinical Presentations ◽  
Depressive Subtypes ◽  
Future Outcomes

AbstractCurrent criteria for depression are imprecise and do not accurately characterize its distinct clinical presentations. As a result, its diagnosis lacks clinical utility in both treatment and research settings. Data-driven efforts to refine criteria have typically focused on a limited set of symptoms that do not reflect the disorder’s heterogeneity. By contrast, clinicians often write about patients in depth, creating descriptions that may better characterize depression. However, clinical text is not commonly used to this end. Here we show that clinically relevant depressive subtypes can be derived from unstructured electronic health records. Five subtypes were identified amongst 18,314 patients with depression treated at a large mental healthcare provider by using unsupervised machine learning: severe-typical, psychotic, mild-typical, agitated, and anergic-apathetic. Subtypes were used to place patients in groups for validation; groups were found to be associated with future outcomes and characteristics that were consistent with the subtypes. These associations suggest that these categorizations are actionable due to their validity with respect to disease prognosis. Moreover, they were derived with automated techniques that might theoretically be widely implemented, allowing for future analyses in more varied populations and settings. Additional research, especially with respect to treatment response, may prove useful in further evaluation.

scholarly journals Predicting outcomes in older ED patients with influenza in real time using a big data-driven and machine learning approach to the hospital information system

2021 ◽  
Vol 21 (1) ◽  
Author(s):  
Tian-Hoe Tan ◽  
Chien-Chin Hsu ◽  
Chia-Jung Chen ◽  
Shu-Lien Hsu ◽  
Tzu-Lan Liu ◽  
...  
Keyword(s):  
Machine Learning ◽  
Information System ◽  
Real Time ◽  
Hospital Information System ◽  
Clinical Utility ◽  
Data Driven ◽  
Health Records ◽  
Machine Learning Approach ◽  
Testing Data ◽  
Model Training

Abstract Background Predicting outcomes in older patients with influenza in the emergency department (ED) by machine learning (ML) has never been implemented. Therefore, we conducted this study to clarify the clinical utility of implementing ML. Methods We recruited 5508 older ED patients (≥65 years old) in three hospitals between 2009 and 2018. Patients were randomized into a 70%/30% split for model training and testing. Using 10 clinical variables from their electronic health records, a prediction model using the synthetic minority oversampling technique preprocessing algorithm was constructed to predict five outcomes. Results The best areas under the curves of predicting outcomes were: random forest model for hospitalization (0.840), pneumonia (0.765), and sepsis or septic shock (0.857), XGBoost for intensive care unit admission (0.902), and logistic regression for in-hospital mortality (0.889) in the testing data. The predictive model was further applied in the hospital information system to assist physicians’ decisions in real time. Conclusions ML is a promising way to assist physicians in predicting outcomes in older ED patients with influenza in real time. Evaluations of the effectiveness and impact are needed in the future.

#39: Streptococcus anginosus Group Infections in Children: A Retrospective Cohort Study, 2015–2019

2021 ◽  
Vol 10 (Supplement_1) ◽  
pp. S6-S6
Author(s):  
O Amin ◽  
O Smith ◽  
F Berkowitz ◽  
T Lyon ◽  
C Kao ◽  
...  
Keyword(s):  
Antibiotic Susceptibility ◽  
Retrospective Cohort ◽  
Management Strategies ◽  
Upper Respiratory Tract ◽  
Streptococcus Anginosus ◽  
Streptococcus Constellatus ◽  
Clinical Presentations ◽  
Inflammatory Bowel ◽  
Tract Infections ◽  
Polymicrobial Infections

Abstract Background Infections attributed to the Streptococcus anginosus group (SAG), which includes Streptococcus anginosus, Streptococcus constellatus, and Streptococcus intermedius, have varying clinical presentations. SAG infections are difficult to identify initially, and members of the group may require different management strategies. Methods A retrospective review of SAG-positive cultures from January 2015, to September 2019, was conducted to describe the demographic, clinical, and laboratory features including the site of infection, antibiotic susceptibility, management, and clinical outcome. Results We identified 561 patients [median age 11.3, interquartile range (IQR) 7.1–14.9 years, male:female ratio 3:2, non-Hispanic–non-Latino 454 (81%), White 279 (49%)]. Thirty-nine (7%) had at least one underlying condition. Of these, inflammatory bowel disease 15 (39%), diabetes 7 (18%), immunodeficiency 5 (13%). SAG was found in exudate, fluid, or aspirate (537/561, 96%), blood (11/561, 2%), and tissue (11/561, 2%) samples; 388 (69%) were polymicrobial infections. The most common site of infection was intra-abdominal (175, 31%), followed by neck/odontogenic (114. 20%) and genitourinary tract (66, 12%). The median length of stay was 6 days (IQR 3–10 days) and was statistically significantly longer for patients with blood, central nervous system, and pulmonary infections compared with soft tissue and upper respiratory tract infections (P < 0.001). Beta-lactams were the most commonly used antibiotics (38%), followed by clindamycin (30 %) (see Figure for antibiotic susceptibility results) and 33 (56%) patients received combination therapy. We did not observe any SAG attributed to mortality. Conclusions In our retrospective cohort, SAG infections were more commonly identified in males, were associated with abscess formation, and presented as polymicrobial infections. Children with underlying comorbidities are more likely to present with systemic SAG infections. SAG-associated infections can be variable in presentation site and severity and should be considered as pathogens when managing patients.

scholarly journals Prognostic Biomarkers of Sarcoidosis: A Comparative Study of Serum Chitotriosidase, ACE, Lysozyme, and KL-6

2019 ◽  
Vol 2019 ◽  
pp. 1-7 ◽  
Author(s):  
Laura Bergantini ◽  
Francesco Bianchi ◽  
Paolo Cameli ◽  
Maria Antonietta Mazzei ◽  
Annalisa Fui ◽  
...  
Keyword(s):  
Steroid Therapy ◽  
Lung Fibrosis ◽  
Clinical Utility ◽  
Clinical Course ◽  
Unknown Etiology ◽  
Serum Concentrations ◽  
Referral Centre ◽  
Clinical Presentations ◽  
Serum Detection

Purpose. Sarcoidosis is a systemic granulomatous disease with unknown etiology. Many clinical presentations have been reported, and acute disease needs to be distinguished from subacute and chronic disease. The unpredictable clinical course of the disease prompted us to evaluate the clinical utility of biomarker serum detection in sarcoidosis follow-up. Methods. Serum concentrations of chitotriosidase, ACE, KL-6, and lysozyme were analyzed by different methods in a population of 74 sarcoidosis patients (46 on steroid therapy at sampling) regularly monitored at Siena Sarcoidosis Regional Referral Centre and in a group of controls with the aim of comparing their contribution to clinical management of sarcoidosis patients. Results. KL-6 concentrations were significantly elevated in sarcoidosis patients with lung fibrosis and were significantly correlated with DLco and CPI score, while chitotriosidase was significantly higher in patients with extrapulmonary localizations. With a cut-off value of 303.5 IU/ml, KL-6 showed the best sensitivity (78%), while chitotriosidase reported the best specificity (85%) among the biomarkers. Conclusions. KL-6 is a reliable biomarker of fibrotic lung involvement in sarcoidosis patients. Among biomarkers, KL-6 showed the best sensitivity and serum chitotriosidase the best specificity, even in patients on chronic steroid therapy, and seemed to correlate with extrapulmonary localizations.

scholarly journals Data‐driven discovery of probable Alzheimer's disease and related dementia subphenotypes using electronic health records

2020 ◽  
Vol 4 (4) ◽  
Author(s):  
Jie Xu ◽  
Fei Wang ◽  
Zhenxing Xu ◽  
Prakash Adekkanattu ◽  
Pascal Brandt ◽  
...  
Keyword(s):  
Alzheimer’S Disease ◽  
Alzheimer's Disease ◽  
Electronic Health Records ◽  
Data Driven ◽  
Health Records ◽  
Electronic Health

scholarly journals Data-driven discovery of seasonally linked diseases from an Electronic Health Records system

2014 ◽  
Vol 15 (Suppl 6) ◽  
pp. S3 ◽  
Author(s):  
Rachel D Melamed ◽  
Hossein Khiabanian ◽  
Raul Rabadan
Keyword(s):  
Electronic Health Records ◽  
Data Driven ◽  
Health Records ◽  
Electronic Health

scholarly journals Individualised risk prediction model for new-onset, progression and regression of chronic kidney disease in a retrospective cohort of patients with type 2 diabetes under primary care in Hong Kong

BMJ Open ◽  
2020 ◽  
Vol 10 (7) ◽  
pp. e035308
Author(s):  
Lin Yang ◽  
Tsun Kit Chu ◽  
Jinxiao Lian ◽  
Cheuk Wai Lo ◽  
Shi Zhao ◽  
...  
Keyword(s):  
Blood Pressure ◽  
Type 2 Diabetes ◽  
Primary Care ◽  
Retrospective Cohort ◽  
Density Lipoprotein ◽  
Test Results ◽  
Health Records ◽  
Laboratory Test Results ◽  
New Onset

ObjectivesThis study is aimed to develop and validate a prediction model for multistate transitions across different stages of chronic kidney disease (CKD) in patients with type 2 diabetes mellitus under primary care.SettingWe retrieved the anonymised electronic health records of a population-based retrospective cohort in Hong Kong.ParticipantsA total of 26 197 patients were included in the analysis.Primary and secondary outcome measuresThe new-onset, progression and regression of CKD were defined by the transitions of four stages that were classified by combining glomerular filtration rate and urine albumin-to-creatinine ratio. We applied a multiscale multistate Poisson regression model to estimate the rates of the stage transitions by integrating the baseline demographic characteristics, routine laboratory test results and clinical data from electronic health records.ResultsDuring the mean follow-up time of 1.8 years, there were 2632 patients newly diagnosed with CKD, 1746 progressed to the next stage and 1971 regressed into an earlier stage. The models achieved the best performance in predicting the new-onset and progression with the predictors of sex, age, body mass index, systolic blood pressure, diastolic blood pressure, serum creatinine, haemoglobin A1c, total cholesterol, low-density lipoprotein, high-density lipoprotein, triglycerides and drug prescriptions.ConclusionsThis study demonstrated that individual risks of new-onset and progression of CKD can be predicted from the routine physical and laboratory test results. The individualised prediction curves developed from this study could potentially be applied to routine clinical practices, to facilitate clinical decision making, risk communications with patients and early interventions.

Sign in / Sign up

Export Citation Format

Share Document