Receive a weekly summary and discussion of the top papers of the week by leading researchers in the field.

Public Health Public Health

Using classification trees to identify psychotherapy patients at risk for poor treatment adherence.

In Psychotherapy research : journal of the Society for Psychotherapy Research

To determine the relative importance of a wide variety of personality and psychopathology variables in influencing patients' adherence to psychotherapy treatment. Two classification trees were trained to predict patients' (1) treatment utilization (i.e., their likelihood of missing a given appointment) and (2) termination status (i.e., their likelihood of dropping out of therapy prematurely). Each tree was then validated in an external dataset to examine performance accuracy. Patients' social detachment was most influential in predicting their treatment utilization, followed by affective instability and activity/energy levels. Patients' interpersonal warmth was most influential in predicting their termination status, followed by levels of disordered thought and resentment. The overall accuracy rating for the tree for termination status was 71.4%, while the tree for treatment utilization had a 38.7% accuracy rating. Classification trees are a practical tool for clinicians to determine patients at risk of premature termination. More research is needed to develop trees that predict treatment utilization with high accuracy across different types of patients and settings.

Regan Timothy, McCredie Morgan N, Harris Bethany, Clark Shaunna

2023-Mar-07

attendance, classification trees, dropout, machine learning, psychotherapy

General General

LSTM based stock prediction using weighted and categorized financial news.

In PloS one ; h5-index 176.0

A significant correlation between financial news with stock market trends has been explored extensively. However, very little research has been conducted for stock prediction models that utilize news categories, weighted according to their relevance with the target stock. In this paper, we show that prediction accuracy can be enhanced by incorporating weighted news categories simultaneously into the prediction model. We suggest utilizing news categories associated with the structural hierarchy of the stock market: that is, news categories for the market, sector, and stock-related news. In this context, Long Short-Term Memory (LSTM) based Weighted and Categorized News Stock prediction model (WCN-LSTM) is proposed. The model incorporates news categories with their learned weights simultaneously. To enhance the effectiveness, sophisticated features are integrated into WCN-LSTM. These include, hybrid input, lexicon-based sentiment analysis, and deep learning to impose sequential learning. Experiments have been performed for the case of the Pakistan Stock Exchange (PSX) using different sentiment dictionaries and time steps. Accuracy and F1-score are used to evaluate the prediction model. We have analyzed the WCN-LSTM results thoroughly and identified that WCN-LSTM performs better than the baseline model. Moreover, the sentiment lexicon HIV4 along with time steps 3 and 7, optimized the prediction accuracy. We have conducted statistical analysis to quantitatively assess our findings. A qualitative comparison of WCN-LSTM with existing prediction models is also presented to highlight its superiority and novelty over its counterparts.

Usmani Shazia, Shamsi Jawwad A

2023

General General

Can individual subjective confidence in training questions predict group performance in test questions?

In PloS one ; h5-index 176.0

When people have to solve many tasks, they can aggregate diverse individuals' judgments using the majority rule, which often improves the accuracy of judgments (wisdom of crowds). When aggregating judgments, individuals' subjective confidence is a useful cue for deciding which judgments to accept. However, can confidence in one task set predict performance not only in the same task set, but also in another? We examined this issue through computer simulations using behavioral data obtained from binary-choice experimental tasks. In our simulations, we developed a "training-test" approach: We split the questions used in the behavioral experiments into "training questions" (as questions to identify individuals' confidence levels) and "test questions" (as questions to be solved), similar to the cross-validation method in machine learning. We found that (i) through analyses of behavioral data, confidence in a certain question could predict accuracy in the same question, but not always well in another question. (ii) Through a computer simulation for the accordance of two individuals' judgments, individuals with high confidence in one training question tended to make less diverse judgments in other test questions. (iii) Through a computer simulation of group judgments, the groups constructed from individuals with high confidence in the training question(s) generally performed well; however, their performance sometimes largely decreased in the test questions especially when only one training question was available. These results suggest that when situations are highly uncertain, an effective strategy is to aggregate various individuals regardless of confidence levels in the training questions to avoid decreasing the group accuracy in test questions. We believe that our simulations, which follow a "training-test" approach, provide practical implications in terms of retaining groups' ability to solve many tasks.

Shirasuna Masaru, Honda Hidehito

2023

Surgery Surgery

Can a Deep Learning Algorithm Improve Detection of Occult Scaphoid Fractures in Plain Radiographs? A Clinical Validation Study.

In Clinical orthopaedics and related research ; h5-index 71.0

BACKGROUND : Occult scaphoid fractures on initial radiographs of an injury are a diagnostic challenge to physicians. Although artificial intelligence models based on the principles of deep convolutional neural networks (CNN) offer a potential method of detection, it is unknown how such models perform in the clinical setting.

QUESTIONS/PURPOSES : (1) Does CNN-assisted image interpretation improve interobserver agreement for scaphoid fractures? (2) What is the sensitivity and specificity of image interpretation performed with and without CNN assistance (as stratified by type: normal scaphoid, occult fracture, and apparent fracture)? (3) Does CNN assistance improve time to diagnosis and physician confidence level?

METHODS : This survey-based experiment presented 15 scaphoid radiographs (five normal, five apparent fractures, and five occult fractures) with and without CNN assistance to physicians in a variety of practice settings across the United States and Taiwan. Occult fractures were identified by follow-up CT scans or MRI. Participants met the following criteria: Postgraduate Year 3 or above resident physician in plastic surgery, orthopaedic surgery, or emergency medicine; hand fellows; and attending physicians. Among the 176 invited participants, 120 completed the survey and met the inclusion criteria. Of the participants, 31% (37 of 120) were fellowship-trained hand surgeons, 43% (52 of 120) were plastic surgeons, and 69% (83 of 120) were attending physicians. Most participants (73% [88 of 120]) worked in academic centers, whereas the remainder worked in large, urban private practice hospitals. Recruitment occurred between February 2022 and March 2022. Radiographs with CNN assistance were accompanied by predictions of fracture presence and gradient-weighted class activation mapping of the predicted fracture site. Sensitivity and specificity of the CNN-assisted physician diagnoses were calculated to assess diagnostic performance. We calculated interobserver agreement with the Gwet agreement coefficient (AC1). Physician diagnostic confidence was estimated using a self-assessment Likert scale, and the time to arrive at a diagnosis for each case was measured.

RESULTS : Interobserver agreement among physicians for occult scaphoid radiographs was higher with CNN assistance than without (AC1 0.42 [95% CI 0.17 to 0.68] versus 0.06 [95% CI 0.00 to 0.17], respectively). No clinically relevant differences were observed in time to arrive at a diagnosis (18 ± 12 seconds versus 30 ± 27 seconds, mean difference 12 seconds [95% CI 6 to 17]; p < 0.001) or diagnostic confidence levels (7.2 ± 1.7 seconds versus 6.2 ± 1.6 seconds; mean difference 1 second [95% CI 0.5 to 1.3]; p < 0.001) for occult fractures.

CONCLUSION : CNN assistance improves physician diagnostic sensitivity and specificity as well as interobserver agreement for the diagnosis of occult scaphoid fractures. The differences observed in diagnostic speed and confidence is likely not clinically relevant. Despite these improvements in clinical diagnoses of scaphoid fractures with the CNN, it is unknown whether development and implementation of such models is cost effective.

LEVEL OF EVIDENCE : Level II, diagnostic study.

Yoon Alfred P, Chung William T, Wang Chien-Wei, Kuo Chang-Fu, Lin Chihung, Chung Kevin C

2023-Mar-07

General General

Effects of Antidepressants on COVID Outcome: A Retrospective Study on Large Scale Electronic Health Record Data.

In Interactive journal of medical research

BACKGROUND : Antidepressants are a type of medication used to treat clinical depression or prevent it recurring. Antidepressants exert an anticholinergic effect in varying degrees and various classes of antidepressants also can produce a different effect on immune function. While early usage of antidepressants has notional role on COVID-19 outcomes, the relationship between the risk of COVID-19 severity and the use of all kinds of antidepressants is not properly investigated before due to the exceeding cost involved with clinical trials. Large-scale observational data such as electronic health records and recent advancement of statistical analysis provide ample opportunity to virtualize clinical trial to discover detrimental effects of early usage of these drugs.

OBJECTIVE : By mining a large-scale electronic health record data set of COVID-19 positive patients, we aim to identify common drugs that are associated with COVID-19 outcome. However, whereas the statisticians have made great progress toward using such rich association estimation methods for risk estimation, precise effects of the medicines as treatments require causal models. Thus, our central aim of this paper lies on investigating electronic health record analytic for causal effect estimation and utilize that in discovering causal effects of early antidepressants use on COVID-19 outcomes. As a secondary aim, we develop methods for validating our causal effect estimation pipeline.

METHODS : We focus on antidepressants, a commonly used category of drugs that have been linked to unexpected effects on diverse inflammatory and cardiovascular outcomes and infer early use of such drug use effects on COVID-19 outcomes. However, whereas the machine learning and statistics community have made great progress toward using rich inference models, precise effects of the medicines as treatments require causal models, for which there is significantly less theoretical and practical guidance available. We used National COVID Cohort Collaborative (N3C), a database aggregating health history for over 12+ million people in the USA, including 5+ million with a positive COVID-19 test. We selected 241,952 COVID-19 positive patients with at least one year of medical history and age>13 that included 18,584-dimensional covariate vector for each person and 16 different antidepressants usage histories. We used propensity score weighting based on logistic regression method to estimate causal effect on whole data. Then we used Node2Vec embedding method to encode SNOMED medical code and apply random forest regression to estimate causal effect. We use both methods to estimate causal effects of antidepressants on COVID-19 outcome. We also selected few negatively effective conditions on COVID-19 outcomes and estimated their effects using our proposed methods to validate their efficacy.

RESULTS : Average Treatment Effect (ATE) of using any one of the antidepressants is -0.076 with 95% CI from -0.082 to - 0.069 with propensity score weighting method. The result is statistically significant at p<0.0001. In case of the method using SNOMED medical embedding, the ATE of using any one of the antidepressants is -0.423 with 95% CI from -0.382 to -0.463. This result is also statistically significant at p<0.0001.

CONCLUSIONS : In this study, we apply multiple causal inference methods incorporating with a novel application of health embeddings to investigate the effects of antidepressants on COVID-19 outcome. Additionally, we propose a novel non-affecting drug effect analysis-based evaluation technique to justify the efficacy of proposed method. This study offers causal inference methods on large-scale EHR data to discover common antidepressants' effects on COVID-19 hospitalization, or a worse outcome. The study finds that common antidepressants may increase risk of COVID-19 complications and uncovers a pattern where certain antidepressants are associated with lower risk of hospitalization. While discovering detrimental effects of these drugs on outcome could guide preventive care, identification of beneficial effects would allow us to propose drug repurposing for COVID-19 treatment.

Rahman Md Mahmudur, Mahi Atqiya Munawara, Melamed Rachel D, Alam Mohammad Arif Ul

2023-Mar-05

General General

Development and validation of a respiratory-responsive vocal biomarker-based tool for generalizable detection of respiratory impairment: independent case-control studies in multiple respiratory conditions including asthma, chronic obstructive pulmonary disease, and COVID-19.

In Journal of medical Internet research ; h5-index 88.0

BACKGROUND : Vocal biomarker-based machine learning approaches have shown promising results in detecting various health conditions, including respiratory diseases such as asthma. In this study, we aim to validate a respiratory-responsive vocal-biomarker (RRVB) platform initially trained on an asthma and healthy volunteer dataset for its ability to differentiate, without modification, active COVID-19 infection vs. healthy volunteers in patients presenting to hospitals in the US and India.

OBJECTIVE : The objective of this study was to determine whether the RRVB model can differentiate patients with active COVID-19 infection vs. asymptomatic healthy volunteers by assessing its sensitivity, specificity, and odds ratio. Another objective was to evaluate whether the RRVB model outputs correlate with symptom severity in COVID-19.

METHODS : A logistic regression model using a weighted sum of voice acoustic features was previously trained and validated on a dataset of about 1,700 patients with a confirmed asthma diagnosis vs. a similar number of healthy controls. The same model has shown generalizability to patients with chronic obstructive pulmonary disease (COPD), interstitial lung disease (ILD), and cough. In the present study, a total of 497 participants (46% male, 54% female; 94% < 65 years, 6% >= 65 years; 51% Marathi, 45% English, 5% Spanish speakers) were enrolled across four clinical sites in US and India and provided voice samples and symptom reports on their personal smartphones. The participants included symptomatic COVID-19 positive and negative patients as well as asymptomatic healthy volunteers. The RRVB model performance was assessed by comparison with clinical diagnosis of COVID-19 confirmed by RT-PCR.

RESULTS : The RRVB model's ability to differentiate patients with respiratory conditions vs. healthy controls was previously demonstrated on validation data in asthma, COPD, ILD and cough with odds ratios of 4.3, 9.1, 3.1, and 3.9 respectively. The same RRVB model in the present study in COVID-19 performed with a sensitivity of 73.2%, specificity of 62.9%, and odds ratio of 4.64 (p<0.0001). Patients experiencing respiratory symptoms were detected more frequently than those not experiencing respiratory symptoms and completely asymptomatic patients (78.4% vs. 67.4% vs. 68.0%).

CONCLUSIONS : The RRVB model has shown good generalizability across respiratory conditions, geographies, and language. Results in COVID-19 demonstrate its meaningful potential to serve as a pre-screening tool for identifying subjects at risk for COVID-19 infection in combination with temperature and symptom reports. Although not a COVID-19 test, these results suggest that the RRVB model could encourage targeted testing. Moreover, the generalizability of this model for detecting respiratory symptoms across different linguistic and geographic contexts suggests a potential path to development and validation of voice-based tools for broader disease surveillance and monitoring applications in the future.

CLINICALTRIAL : ClinicalTrials.gov (NCT04582331.

Kaur Savneet, Larsen Erik, Harper James, Purandare Bharat, Uluer Ahmet, Hasdianda Mohammad Adrian, Umale Nikita, Killeen James, Castillo Edward, Jariwala Sunit

2023-Feb-28