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

General General

Predicting change in diagnosis from major depression to bipolar disorder after antidepressant initiation.

In Neuropsychopharmacology : official publication of the American College of Neuropsychopharmacology

We aimed to develop and validate classification models able to identify individuals at high risk for transition from a diagnosis of depressive disorder to one of bipolar disorder. This retrospective health records cohort study applied outpatient clinical data from psychiatry and nonpsychiatry practice networks affiliated with two large academic medical centers between March 2008 and December 2017. Participants included 67,807 individuals with a diagnosis of major depressive disorder or depressive disorder not otherwise specified and no prior diagnosis of bipolar disorder, who received at least one of the nine antidepressant medications. The main outcome was at least one diagnostic code reflective of a bipolar disorder diagnosis within 3 months of index antidepressant prescription. Logistic regression and random forests using diagnostic and procedure codes as well as sociodemographic features were used to predict this outcome, with discrimination and calibration assessed in a held-out test set and then a second academic medical center. Among 67,807 individuals who received at least one antidepressant medication, 925 (1.36%) subsequently received a diagnosis of bipolar disorder within 3 months. Models incorporating coded diagnoses and procedures yielded a mean area under the receiver operating characteristic curve of 0.76 (ranging from 0.73 to 0.80). Standard supervised machine learning methods enabled development of discriminative and transferable models to predict transition to bipolar disorder. With further validation, these scores may enable physicians to more precisely calibrate follow-up intensity for high-risk patients after antidepressant initiation. Fig. 1BIPOLAR RATES AMONG ALL INDEX PRESCRIPTIONS BETWEEN 2008 AND 2017 FOR DIFFERENT ANTIDEPRESSANT CATEGORIES.: SNRIs serotonin and norepinephrine reuptake inhibitors, SSRIs selective serotonin reuptake inhibitors, MDD major depressive disorder, BP bipolar disorder.Fig. 2AREA UNDER THE CURVE (AUC) IN TEST SET FOR THE LOGISTIC REGRESSION CLASSIFIER (LEFT) AND RANDOM FOREST CLASSIFIER (RIGHT) FOR SITE A AND SITE B.: Input data include sociodemographic features, specifically age, gender, and race (dem), date of prescription (date), type of insurance (insurance), type of provider (provider), and diagnostic/procedure codes (codes). Confidence intervals computed using 500 bootstraps across 50 different splits of the data in train/test/validation sets.Fig. 3LIFT HISTOGRAM FOR THE RANDOM FOREST CLASSIFIER (1ST ROW) AND LOGISTIC REGRESSION CLASSIFIER (2ND ROW) IN SITE A (1ST COLUMN) AND SITE B (2ND COLUMN) FOR A SINGLE SPLIT.: Prescriptions are sorted according to their predicted probability of transition to bipolar disorder. The dashed line corresponds to the average BPD rate at each site respectively: bars above the dashed line correspond to patients high higher-than-average BPD risk.Fig. 4POSITIVE PREDICTIVE VALUES (PPV) VERSUS NEGATIVE PREDICTIVE VALUES (NPV) FOR THE RANDOM FOREST CLASSIFIER (1ST ROW) AND LOGISTIC REGRESSION CLASSIFIER (2ND ROW) IN SITE A (1ST COLUMN) AND SITE B (2ND COLUMN) FOR A SINGLE SPLIT.: Each blue point corresponds to a different operating point (threshold) of the classifier.

Pradier Melanie F, Hughes Michael C, McCoy Thomas H, Barroilhet Sergio A, Doshi-Velez Finale, Perlis Roy H


General General

Learning to control the brain through adaptive closed-loop patterned stimulation.

In Journal of neural engineering ; h5-index 52.0

OBJECTIVE : Stimulation of neural activity is an important scientific and clinical tool, causally testing hypotheses and treating neurodegenerative and neuropsychiatric diseases. However, current stimulation approaches cannot flexibly control the pattern of activity in populations of neurons. To address this, we developed a model-free, adaptive, closed-loop stimulation (ACLS) system that learns to use multi-site electrical stimulation to control the pattern of activity of a population of neurons.

APPROACH : The ACLS system combined multi-electrode electrophysiological recordings with multi-site electrical stimulation to simultaneously record the activity of a population of 5-15 multiunit neurons and deliver spatially-patterned electrical stimulation across 4-16 sites. Using a closed-loop learning system, ACLS iteratively updated the pattern of stimulation to reduce the difference between the observed neural response and a specific target pattern of firing rates in the recorded multiunits.

MAIN RESULTS : In silico and in vivo experiments showed ACLS learns to produce specific patterns of neural activity (in ~15 minutes) and was robust to noise and drift in neural responses. In visual cortex of awake mice, ACLS learned electrical stimulation patterns that produced responses similar to the natural response evoked by visual stimuli. Similar to how repetition of a visual stimulus causes an adaptation in the neural response, the response to electrical stimulation was adapted when it was preceded by the associated visual stimulus.

SIGNIFICANCE : Our results show an adaptive closed-loop stimulation system that can learn, in real-time, to generate specific patterns of neural activity. This work provides a framework for using model-free closed-loop learning to control neural activity.

Tafazoli Sina, MacDowell Camden, Che Zongda, Letai Kate C, Steinhardt Cynthia R, Buschman Tim


brain stimulation, closed-loop stimulation, electrical stimulation, machine learning, neuromodulation

Surgery Surgery

Artificial intelligence in trauma systems.

In Surgery ; h5-index 54.0

Local trauma care and regional trauma systems are data-rich environments that are amenable to machine learning, artificial intelligence, and big-data analysis mechanisms to improve timely access to care, to measure outcomes, and to improve quality of care. Pilot work has been done to demonstrate that these methods are useful to predict patient flow at individual centers, so that staffing models can be adapted to match workflow. Artificial intelligence has also been proven useful in the development of regional trauma systems as a tool to determine the optimal location of a new trauma center based on trauma-patient geospatial injury data and to minimize response times across the trauma network. Although the utility of artificial intelligence is apparent and proven in small pilot studies, its operationalization across the broader trauma system and trauma surgery space has been slow because of cost, stakeholder buy-in, and lack of expertise or knowledge of its utility. Nevertheless, as new trauma centers or systems are developed, or existing centers are retooled, machine learning and sophisticated analytics are likely to be important components to help facilitate decision-making in a wide range of areas, from determining bedside nursing and provider ratios to determining where to locate new trauma centers or emergency medical services teams.

Stonko David P, Guillamondegui Oscar D, Fischer Peter E, Dennis Bradley M


General General

Using Machine Learning to Generate Novel Hypotheses: Increasing Optimism About COVID-19 Makes People Less Willing to Justify Unethical Behaviors.

In Psychological science ; h5-index 93.0

How can we nudge people to not engage in unethical behaviors, such as hoarding and violating social-distancing guidelines, during the COVID-19 pandemic? Because past research on antecedents of unethical behavior has not provided a clear answer, we turned to machine learning to generate novel hypotheses. We trained a deep-learning model to predict whether or not World Values Survey respondents perceived unethical behaviors as justifiable, on the basis of their responses to 708 other items. The model identified optimism about the future of humanity as one of the top predictors of unethicality. A preregistered correlational study (N = 218 U.S. residents) conceptually replicated this finding. A preregistered experiment (N = 294 U.S. residents) provided causal support: Participants who read a scenario conveying optimism about the COVID-19 pandemic were less willing to justify hoarding and violating social-distancing guidelines than participants who read a scenario conveying pessimism. The findings suggest that optimism can help reduce unethicality, and they document the utility of machine-learning methods for generating novel hypotheses.

Sheetal Abhishek, Feng Zhiyu, Savani Krishna


COVID-19, machine learning, neural network, open data, open materials, optimism, preregistered, unethical behavior

Radiology Radiology

Development and clinical implementation of tailored image analysis tools for COVID-19 in the midst of the pandemic: The synergetic effect of an open, clinically embedded software development platform and machine learning.

In European journal of radiology ; h5-index 47.0

PURPOSE : During the emerging COVID-19 pandemic, radiology departments faced a substantial increase in chest CT admissions coupled with the novel demand for quantification of pulmonary opacities. This article describes how our clinic implemented an automated software solution for this purpose into an established software platform in 10 days. The underlying hypothesis was that modern academic centers in radiology are capable of developing and implementing such tools by their own efforts and fast enough to meet the rapidly increasing clinical needs in the wake of a pandemic.

METHOD : Deep convolutional neural network algorithms for lung segmentation and opacity quantification on chest CTs were trained using semi-automatically and manually created ground-truth (Ntotal = 172). The performance of the in-house method was compared to an externally developed algorithm on a separate test subset (N = 66).

RESULTS : The final algorithm was available at day 10 and achieved human-like performance (Dice coefficient = 0.97). For opacity quantification, a slight underestimation was seen both for the in-house (1.8 %) and for the external algorithm (0.9 %). In contrast to the external reference, the underestimation for the in-house algorithm showed no dependency on total opacity load, making it more suitable for follow-up.

CONCLUSIONS : The combination of machine learning and a clinically embedded software development platform enabled time-efficient development, instant deployment, and rapid adoption in clinical routine. The algorithm for fully automated lung segmentation and opacity quantification that we developed in the midst of the COVID-19 pandemic was ready for clinical use within just 10 days and achieved human-level performance even in complex cases.

Anastasopoulos Constantin, Weikert Thomas, Yang Shan, Abdulkadir Ahmed, Schmülling Lena, Bühler Claudia, Paciolla Fabiano, Sexauer Raphael, Cyriac Joshy, Nesic Ivan, Twerenbold Raphael, Bremerich Jens, Stieltjes Bram, Sauter Alexander W, Sommer Gregor


COVID-19, Computed tomography, Machine learning, Software

General General

Diagnose ADHD disorder in children using convolutional neural network based on continuous mental task EEG.

In Computer methods and programs in biomedicine

BACKGROUND AND OBJECTIVE : Attention-Deficit/Hyperactivity Disorder (ADHD) is a chronic behavioral disorder in children. Children with ADHD face many difficulties in maintaining their concentration and controlling their behaviors. Early diagnosis of this disorder is one of the most important challenges in its control and treatment. No definitive expert method has been found to detect this disorder early. Our goal in this study is to develop an assistive tool for physicians to recognize ADHD children from healthy children using electroencephalography (EEG) based on a continuous mental task.

METHODS : We used EEG signals recorded from 31 ADHD children and 30 healthy children. In this study, we developed a deep learning model using a convolutional neural network that have had significant performance in image processing fields. For this purpose, we first preprocessed EEG signals to eliminate noise and artifacts. Then we segmented preprocessed samples into more samples. We extracted the theta, alpha, beta, and gamma frequency bands from each segmented sample and formed a color RGB image with three channels. Eventually, we imported the resulting images into a 13-layer convolutional neural network for feature extraction and classification.

RESULTS : The proposed model was evaluated by 5-fold cross validation for train, evaluation, and test data and achieved an average accuracy of 99.06%, 97.81%, 97.47% for segmented samples. The average accuracy for subject-based test samples was 98.48%. Also, the performance of the model was evaluated using the confusion matrix with precision, recall, and f1-score metrics. The results of these metrics also confirmed the outstanding performance of the model.

CONCLUSIONS : The accuracy, precision, recall, and f1-score of our model were better than all previous works for diagnosing ADHD in children. Based on these prominent and reliable results, this technique can be used as an assistive tool for the physicians in the early diagnosis of ADHD in children.

Moghaddari Majid, Lighvan Mina Zolfy, Danishvar Sebelan


ADHD, Convolutional neural network, Deep learning, Electroencephalography