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.

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.

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.

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.