A risk identification model for detection of patients at risk of antidepressant discontinuation.

Purpose: Between 30 and 68% of patients prematurely discontinue their antidepressant treatment, posing significant risks to patient safety and healthcare outcomes. Online healthcare forums have the potential to offer a rich and unique source of data, revealing dimensions of antidepressant discontinuation that may not be captured by conventional data sources. Methods: We analyzed 891 patient narratives from the online healthcare forum, "askapatient.com," utilizing content analysis to create PsyRisk-a corpus highlighting the risk factors associated with antidepressant discontinuation. Leveraging PsyRisk, alongside PsyTAR [a publicly available corpus of adverse drug reactions (ADRs) related to antidepressants], we developed a machine learning-driven algorithm for proactive identification of patients at risk of abrupt antidepressant discontinuation. Results: From the analyzed 891 patients, 232 reported antidepressant discontinuation. Among these patients, 92% experienced ADRs, and 72% found these reactions distressful, negatively affecting their daily activities. Approximately 26% of patients perceived the antidepressants as ineffective. Most reported ADRs were physiological (61%, 411/673), followed by cognitive (30%, 197/673), and psychological (28%, 188/673) ADRs. In our study, we employed a nested cross-validation strategy with an outer 5-fold cross-validation for model selection, and an inner 5-fold cross-validation for hyperparameter tuning. The performance of our risk identification algorithm, as assessed through this robust validation technique, yielded an AUC-ROC of 90.77 and an F1-score of 83.33. The most significant contributors to abrupt discontinuation were high perceived distress from ADRs and perceived ineffectiveness of the antidepressants. Conclusion: The risk factors identified and the risk identification algorithm developed in this study have substantial potential for clinical application. They could assist healthcare professionals in identifying and managing patients with depression who are at risk of prematurely discontinuing their antidepressant treatment.

Direct Versus Indirect Query Performance of ICD-9/-10 Coding to Identify Anaphylaxis.

BACKGROUND: Anaphylaxis is an often under =diagnosed, severe allergic event for which epidemiological data are sporadic. Researchers have leveraged administrative and claims data algorithms to study large databases of anaphylactic events; however, little longitudinal data analysis is available after transition to the International Classification of Diseases, 10th Revision, Clinical Modification (ICD-10-CM). OBJECTIVE: Study longitudinal trends in anaphylaxis incidence using direct and indirect query methods. METHODS: Emergency department (ED) and inpatient data were analyzed from a large state health care administration database from 2011 to 2020. Incidence was calculated using direct queries of anaphylaxis ICD-9-CM and ICD-10-CM codes and indirect queries using a symptom-based ICD-9-CM algorithm and forward mapped ICD-10-CM version to identify undiagnosed anaphylaxis episodes and to assess algorithm performance at the population level. RESULTS: An average of 2.4 million inpatient and 7.5 million ED observations/y were analyzed. Using the direct query method, annual ED anaphylaxis cases increased steadily from 1,454 (2011) to 4,029 (2019) then declined to 3,341 in 2020 during the coronavirus disease 2019 (COVID-19) pandemic. In contrast, inpatient cases remained relatively steady, with a slight decline after 2015 during the ICD version transition, until a significant drop occurred in 2020. Using the indirect queries, anaphylaxis cases increased markedly after the ICD transition year, especially involving drug-related anaphylaxis. CONCLUSIONS: Nontypical drug associations with anaphylaxis episodes using the ICD-10-CM version of the algorithm suggest poor performance with drug-related codes. Further, the increased granularity of ICD-10-CM identified potential limitations of a previously validated symptom-based ICD-9-CM algorithm used to detect undiagnosed cases.

The PsyTAR dataset: From patients generated narratives to a corpus of adverse drug events and effectiveness of psychiatric medications.

The "Psychiatric Treatment Adverse Reactions" (PsyTAR) dataset contains patients' expression of effectiveness and adverse drug events associated with psychiatric medications. The PsyTAR was generated in four phases. In the first phase, a sample of 891 drugs reviews posted by patients on an online healthcare forum, "askapatient.com", was collected for four psychiatric drugs: Zoloft, Lexapro, Cymbalta, and Effexor XR. For each drug review, patient demographic information, duration of treatment, and satisfaction with the drugs were reported. In the second phase, sentence classification, drug reviews were split to 6009 sentences, and each sentence was labeled for the presence of Adverse Drug Reaction (ADR), Withdrawal Symptoms (WDs), Sign/Symptoms/Illness (SSIs), Drug Indications (DIs), Drug Effectiveness (EF), Drug Infectiveness (INF), and Others (not applicable). In the third phases, entities including ADRs (4813 mentions), WDs (590 mentions), SSIs (1219 mentions), and DIs (792 mentions) were identified and extracted from the sentences. In the four phases, all the identified entities were mapped to the corresponding UMLS Metathesaurus concepts (916) and SNOMED CT concepts (755). In this phase, qualifiers representing severity and persistency of ADRs, WDs, SSIs, and DIs (e.g., mild, short term) were identified. All sentences and identified entities were linked to the original post using IDs (e.g., Zoloft.1, Effexor.29, Cymbalta.31). The PsyTAR dataset can be accessed via Online Supplement #1 under the CC BY 4.0 Data license. The updated versions of the dataset would also be accessible in https://sites.google.com/view/pharmacovigilanceinpsychiatry/home.

A systematic approach for developing a corpus of patient reported adverse drug events: A case study for SSRI and SNRI medications.

"Psychiatric Treatment Adverse Reactions" (PsyTAR) corpus is an annotated corpus that has been developed using patients narrative data for psychiatric medications, particularly SSRIs (Selective Serotonin Reuptake Inhibitor) and SNRIs (Serotonin Norepinephrine Reuptake Inhibitor) medications. This corpus consists of three main components: sentence classification, entity identification, and entity normalization. We split the review posts into sentences and labeled them for presence of adverse drug reactions (ADRs) (2168 sentences), withdrawal symptoms (WDs) (438 sentences), sign/symptoms/illness (SSIs) (789 sentences), drug indications (517), drug effectiveness (EF) (1087 sentences), and drug infectiveness (INF) (337 sentences). In the entity identification phase, we identified and extracted ADRs (4813 mentions), WDs (590 mentions), SSIs (1219 mentions), and DIs (792). In the entity normalization phase, we mapped the identified entities to the corresponding concepts in both UMLS (918 unique concepts) and SNOMED CT (755 unique concepts). Four annotators double coded the sentences and the span of identified entities by strictly following guidelines rules developed for this study. We used the PsyTAR sentence classification component to automatically train a range of supervised machine learning classifiers to identifying text segments with the mentions of ADRs, WDs, DIs, SSIs, EF, and INF. SVMs classifiers had the highest performance with F-Score 0.90. We also measured performance of the cTAKES (clinical Text Analysis and Knowledge Extraction System) in identifying patients' expressions of ADRs and WDs with and without adding PsyTAR dictionary to the core dictionary of cTAKES. Augmenting cTAKES dictionary with PsyTAR improved the F-score cTAKES by 25%. The findings imply that PsyTAR has significant implications for text mining algorithms aimed to identify information about adverse drug events and drug effectiveness from patients' narratives data, by linking the patients' expressions of adverse drug events to medical standard vocabularies. The corpus is publicly available at Zolnoori et al. [30].

Life-Threatening Allergies: Using a Patient-Engaged Approach.

BACKGROUND: Adolescents at risk for anaphylaxis are a growing concern. Novel training methods are needed to better prepare individuals to manage anaphylaxis in the community. INTRODUCTION: Didactic training as the sole method of anaphylaxis education has been shown to be ineffective. We developed a smartphone-based interactive teaching tool with decision support and epinephrine auto-injector (EAI) training to provide education accessible beyond the clinic. METHODS: This study consisted of two parts: (1) Use of food allergy scenarios to assess the decision support's ability to improve allergic reaction management knowledge. (2) An assessment of our EAI training module on participant's ability to correctly demonstrate the use of an EAI by comparing it to label instructions. RESULTS: Twenty-two adolescents were recruited. The median (range) baseline number of correct answers on the scenarios before the intervention was 9 (3-11). All subjects improved with decision support, increasing to 11 (9-12) (p < .001). The median (range) demonstration score was 6 (5-6) for the video training module group and 4.5 (3-6) for the label group (p < 0.001). DISCUSSION: Results suggest that the use of this novel m-health application can improve anaphylaxis symptom recognition and increase the likelihood of choosing the appropriate treatment. In addition, performing EAI steps in conjunction with the video training resulted in more accurate medication delivery with fewer missed steps compared to the use of written instructions alone. CONCLUSION: The results suggest that mobile health decision support technology for anaphylaxis emergency preparedness may support traditional methods of training by providing improved access to anaphylaxis training in the community setting.

Using health information technology to engage communities in health, education, and research.

The August 2011 Clinical and Translational Science Awards conference "Using IT to Improve Community Health: How Health Care Reform Supports Innovation" convened four "Think Tank" sessions. Thirty individuals, representing various perspectives on community engagement, attended the "Health information technology (HIT) as a resource to improve community health and education" session, which focused on using HIT to improve patient health, education, and research involvement. Participants discussed a range of topics using a semistructured format. This article describes themes and lessons that emerged from that session, with a particular focus on using HIT to engage communities to improve health and reduce health disparities in populations.

Accurate determination of imaging modality using an ensemble of text- and image-based classifiers.

Imaging modality can aid retrieval of medical images for clinical practice, research, and education. We evaluated whether an ensemble classifier could outperform its constituent individual classifiers in determining the modality of figures from radiology journals. Seventeen automated classifiers analyzed 77,495 images from two radiology journals. Each classifier assigned one of eight imaging modalities--computed tomography, graphic, magnetic resonance imaging, nuclear medicine, positron emission tomography, photograph, ultrasound, or radiograph-to each image based on visual and/or textual information. Three physicians determined the modality of 5,000 randomly selected images as a reference standard. A "Simple Vote" ensemble classifier assigned each image to the modality that received the greatest number of individual classifiers' votes. A "Weighted Vote" classifier weighted each individual classifier's vote based on performance over a training set. For each image, this classifier's output was the imaging modality that received the greatest weighted vote score. We measured precision, recall, and F score (the harmonic mean of precision and recall) for each classifier. Individual classifiers' F scores ranged from 0.184 to 0.892. The simple vote and weighted vote classifiers correctly assigned 4,565 images (F score, 0.913; 95% confidence interval, 0.905-0.921) and 4,672 images (F score, 0.934; 95% confidence interval, 0.927-0.941), respectively. The weighted vote classifier performed significantly better than all individual classifiers. An ensemble classifier correctly determined the imaging modality of 93% of figures in our sample. The imaging modality of figures published in radiology journals can be determined with high accuracy, which will improve systems for image retrieval.