Using machine learning to predict outcomes in psychosis

Predicting post-stroke cognitive impairment using machine learning: A prospective cohort study

BACKGROUND

Post-stroke cognitive impairment (PSCI) is a serious complication of stroke that warrants prompt detection and management. Consequently, the development of a diagnostic prediction model holds clinical significance.

OBJECTIVE

Machine learning algorithms were employed to identify crucial variables and forecast PSCI occurrence within 3-6 months following acute ischemic stroke (AIS).

METHODS

A prospective study was conducted on a developed cohort (331 patients) utilizing data from the Affiliated Zhongda Hospital of Southeast University between January 2022 and August 2022, as well as an external validation cohort (66 patients) from December 2022 to January 2023. The optimal model was determined by integrating nine machine learning classification models, and personalized risk assessment was facilitated by a Shapley Additive exPlanations (SHAP) interpretation.

RESULTS

Age, education, baseline National Institutes of Health Scale (NIHSS), Cerebral white matter degeneration (CWMD), Homocysteine (Hcy), and C-reactive protein (CRP) were identified as predictors of PSCI occurrence. Gaussian Naïve Bayes (GNB) model was determined to be the optimal model, surpassing other classifier models in the validation set (area under the curve [AUC]: 0.925, 95 % confidence interval [CI]: 0.861 - 0.988) and achieving the lowest Brier score. The GNB model performed well in the test sets (AUC: 0.919, accuracy: 0.864, sensitivity: 0.818, and specificity: 0.932).

CONCLUSIONS

The present study involved the development of a GNB model and its elucidation through employment of the SHAP method. These findings provide compelling evidence for preventing PSCI, which could serve as a guide for high-risk patients to undertake appropriate preventive measures.

Combining MRI and clinical data to detect high relapse risk after the first episode of psychosis

Detecting patients at high relapse risk after the first episode of psychosis (HRR-FEP) could help the clinician adjust the preventive treatment. To develop a tool to detect patients at HRR using their baseline clinical and structural MRI, we followed 227 patients with FEP for 18–24 months and applied MRIPredict. We previously optimized the MRI-based machine-learning parameters (combining unmodulated and modulated gray and white matter and using voxel-based ensemble) in two independent datasets. Patients estimated to be at HRR-FEP showed a substantially increased risk of relapse (hazard ratio = 4.58, P < 0.05). Accuracy was poorer when we only used clinical or MRI data. We thus show the potential of combining clinical and MRI data to detect which individuals are more likely to relapse, who may benefit from increased frequency of visits, and which are unlikely, who may be currently receiving unnecessary prophylactic treatments. We also provide an updated version of the MRIPredict software.

Early Diagnosis of Bipolar Disorder Coming Soon: Application of an Oxidative Stress Injury Biomarker (BIOS) Model

Early distinction of bipolar disorder (BD) from major depressive disorder (MDD) is difficult since no tools are available to estimate the risk of BD. In this study, we aimed to develop and validate a model of oxidative stress injury for predicting BD. Data were collected from 1252 BD and 1359 MDD patients, including 64 MDD patients identified as converting to BD from 2009 through 2018. 30 variables from a randomly-selected subsample of 1827 (70%) patients were used to develop the model, including age, sex, oxidative stress markers (uric acid, bilirubin, albumin, and prealbumin), sex hormones, cytokines, thyroid and liver function, and glycolipid metabolism. Univariate analyses and the Least Absolute Shrinkage and Selection Operator were applied for data dimension reduction and variable selection. Multivariable logistic regression was used to construct a model for predicting bipolar disorder by oxidative stress biomarkers (BIOS) on a nomogram. Internal validation was assessed in the remaining 784 patients (30%), and independent external validation was done with data from 3797 matched patients from five other hospitals in China. 10 predictors, mainly oxidative stress markers, were shown on the nomogram. The BIOS model showed good discrimination in the training sample, with an AUC of 75.1% (95% CI: 72.9%-77.3%), sensitivity of 0.66, and specificity of 0.73. The discrimination was good both in internal validation (AUC 72.1%, 68.6%-75.6%) and external validation (AUC 65.7%, 63.9%-67.5%). In this study, we developed a nomogram centered on oxidative stress injury, which could help in the individualized prediction of BD. For better real-world practice, a set of measurements, especially on oxidative stress markers, should be emphasized using big data in psychiatry.

Individualized prediction of psychiatric readmissions for patients with major depressive disorder: a 10-year retrospective cohort study

Patients with major depressive disorder (MDD) are at high risk of psychiatric readmission while the factors associated with such adverse illness trajectories and the impact of the same factor at different follow-up times remain unclear. Based on machine learning (ML) approaches and real-world electronic medical records (EMR), we aimed to predict individual psychiatric readmission within 30, 60, 90, 180, and 365 days of an initial major depression hospitalization. In addition, we examined to what extent our prediction model could be made interpretable by quantifying and visualizing the features that drive the predictions at different follow-up times. By identifying 13,177 individuals discharged from a hospital located in western China between 2009 and 2018 with a recorded diagnosis of MDD, we established five prediction-modeling cohorts with different follow-up times. Four different ML models were trained with features extracted from the EMR, and explainable methods (SHAP and Break Down) were utilized to analyze the contribution of each of the features at both population-level and individual-level. The model showed a performance on the holdout testing dataset that decreased over follow-up time after discharge: AUC 0.814 (0.758-0.87) within 30 days, AUC 0.780 (0.728-0.833) within 60 days, AUC 0.798 (0.75-0.846) within 90 days, AUC 0.740 (0.687-0.794) within 180 days, and AUC 0.711 (0.676-0.747) within 365 days. Results add evidence that markers of depression severity and symptoms (recurrence of the symptoms, combination of key symptoms, the number of core symptoms and physical symptoms), along with age, gender, type of payment, length of stay, comorbidity, treatment patterns such as the use of anxiolytics, antipsychotics, antidepressants (especially Fluoxetine, Clonazepam, Olanzapine, and Alprazolam), physiotherapy, and psychotherapy, and vital signs like pulse and SBP, may improve prediction of psychiatric readmission. Some features can drive the prediction towards readmission at one follow-up time and towards non-readmission at another. Using such a model for decision support gives the clinician dynamic information of the patient's risk of psychiatric readmission and the specific features pulling towards readmission. This finding points to the potential of establishing personalized interventions that change with follow-up time.

Analysis of Seasonal Clinical Characteristics in Patients With Bipolar or Unipolar Depression

This study was to investigate the characteristics of seasonal symptoms and non-enzymatic oxidative stress in the first hospitalized patients with bipolar and unipolar depression, aiming to differentiate bipolar depression from unipolar depression and reduce their misdiagnosis. A total of 450 patients with bipolar depression and 855 patients with depression were included in the present study. According to the season when the patients were admitted to the hospital due to the acute onset of depression, they were further divided into spring, summer, autumn and winter groups. According to the characteristics of symptoms of bipolar disorder in the DSM-5, the characteristic symptoms of bipolar disorder were collected from the medical record information, and clinical biochemical indicators that can reflect the oxidative stress were also recorded. The seasonal risk factors in patients with bipolar or unipolar depression were analyzed. The relationship of age and gender with the bipolar or unipolar depression which attacked in winter was explored. There were significant differences between groups in the melancholic features, atypical features and conjugated bilirubin in spring. In summer, there were significant differences between groups in the melancholic features, uric acid and conjugated bilirubin. In autumn, there were marked differences between groups in melancholic features, anxiety and pain, atypical features, uric acid, total bilirubin, conjugated bilirubin and albumin. In winter, the conjugated bilirubin and prealbumin were significantly different between two groups. The melancholic features and uric acid that in summer as well as melancholic features, uric acid and total bilirubin in autumn were the seasonal independent risk factors for the unipolar depression as compared to bipolar depression. In winter, significant difference was noted in the age between two groups. In conclusion, compared with patients with unipolar depression, patients with bipolar depression have seasonal characteristics. Clinical symptoms and indicators of oxidative stress may become factors for the differentiation of seasonal unipolar depression from bipolar depression. Young subjects aged 15-35 years are more likely to develop bipolar depression in winter.

"It's all about delivery": researchers and health professionals' views on the moral challenges of accessing neurobiological information in the context of psychosis

Background

The convergence of neuroscience, genomics, and data science holds promise to unveil the neurobiology of psychosis and to produce new ways of preventing, diagnosing, and treating psychotic illness. Yet, moral challenges arise in neurobiological research and in the clinical translation of research findings. This article investigates the views of relevant actors in mental health on the moral challenges of accessing neurobiological information in the context of psychosis.

Methods

Semi-structured individual interviews with two groups: researchers employed in the National Health Service (NHS) or a university in England (n = 14), and mental health professionals employed in NHS mental health services (n = 14). This article compares results in the two groups (total n = 28).

Results

This article presents findings around three conceptual areas: (1) research ethics as mostly unproblematic, (2) psychosis, neurobiological information, and mental health care, and (3) identity, relationships, and the future. These areas are drawn from the themes and topics that emerged in the interviews across the two groups of participants. Researchers and health professionals provided similar accounts of the moral challenges of accessing—which includes acquisition, communication, and use of—neurobiological information in the context of psychosis. Acquiring neurobiological information was perceived as mostly unproblematic, provided ethical safeguards are put in place. Conversely, participants argued that substantive moral challenges arise from how neurobiological information is delivered—that is, communicated and used—in research and in clinical care. Neurobiological information was seen as a powerful tool in the process through which individuals define their identity and establish personal and clinical goals. The pervasiveness of this narrative tool may influence researchers and health professionals’ perception of ethical principles and moral obligations.

Conclusions

This study suggests that the moral challenges that arise from accessing neurobiological information in the context of psychosis go beyond traditional research and clinical ethics concerns. Reflecting on how accessing neurobiological information can influence individual self-narratives will be vital to ensure the ethical translation of neuroscience and genomics into mental health.

Trial registration

The study did not involve a health care intervention on human participants. It was retrospectively registered on 11 July 2018, registration number: researchregistry4255.

Psychosis, vulnerability, and the moral significance of biomedical innovation in psychiatry. Why ethicists should join efforts

The study of the neuroscience and genomics of mental illness are increasingly intertwined. This is mostly due to the translation of medical technologies into psychiatry and to technological convergence. This article focuses on psychosis. I argue that the convergence of neuroscience and genomics in the context of psychosis is morally problematic, and that ethics scholarship should go beyond the identification of a number of ethical, legal, and social issues. My argument is composed of two strands. First, I argue that we should respond to technological convergence by developing an integrated, patient-centred approach focused on the assessment of individual vulnerabilities. Responding to technological convergence requires that we (i) integrate insights from several areas of ethics, (ii) translate bioethical principles into the mental health context, and (iii) proactively try to anticipate future ethical concerns. Second, I argue that a nuanced understanding of the concept of vulnerability might help us to accomplish this task. I borrow Florencia Luna's notion of 'layers of vulnerability' to show how potential harms or wrongs to individuals who experience psychosis can be conceptualised as stemming from different sources, or layers, of vulnerability. I argue that a layered notion of vulnerability might serve as a common ground to achieve the ethical integration needed to ensure that biomedical innovation can truly benefit, and not harm, individuals who suffer from psychosis.

Prediction of premature all-cause mortality: A prospective general population cohort study comparing machine-learning and standard epidemiological approaches

BACKGROUND

Prognostic modelling using standard methods is well-established, particularly for predicting risk of single diseases. Machine-learning may offer potential to explore outcomes of even greater complexity, such as premature death. This study aimed to develop novel prediction algorithms using machine-learning, in addition to standard survival modelling, to predict premature all-cause mortality.

METHODS

A prospective population cohort of 502,628 participants aged 40-69 years were recruited to the UK Biobank from 2006-2010 and followed-up until 2016. Participants were assessed on a range of demographic, biometric, clinical and lifestyle factors. Mortality data by ICD-10 were obtained from linkage to Office of National Statistics. Models were developed using deep learning, random forest and Cox regression. Calibration was assessed by comparing observed to predicted risks; and discrimination by area under the 'receiver operating curve' (AUC).

FINDINGS

14,418 deaths (2.9%) occurred over a total follow-up time of 3,508,454 person-years. A simple age and gender Cox model was the least predictive (AUC 0.689, 95% CI 0.681-0.699). A multivariate Cox regression model significantly improved discrimination by 6.2% (AUC 0.751, 95% CI 0.748-0.767). The application of machine-learning algorithms further improved discrimination by 3.2% using random forest (AUC 0.783, 95% CI 0.776-0.791) and 3.9% using deep learning (AUC 0.790, 95% CI 0.783-0.797). These ML algorithms improved discrimination by 9.4% and 10.1% respectively from a simple age and gender Cox regression model. Random forest and deep learning achieved similar levels of discrimination with no significant difference. Machine-learning algorithms were well-calibrated, while Cox regression models consistently over-predicted risk.

CONCLUSIONS

Machine-learning significantly improved accuracy of prediction of premature all-cause mortality in this middle-aged population, compared to standard methods. This study illustrates the value of machine-learning for risk prediction within a traditional epidemiological study design, and how this approach might be reported to assist scientific verification.

Applying Machine Learning Techniques to Identify Undiagnosed Patients with Exocrine Pancreatic Insufficiency

BACKGROUND

Exocrine pancreatic insufficiency (EPI) is a serious condition characterized by a lack of functional exocrine pancreatic enzymes and the resultant inability to properly digest nutrients. EPI can be caused by a variety of disorders, including chronic pancreatitis, pancreatic cancer, and celiac disease. EPI remains underdiagnosed because of the nonspecific nature of clinical symptoms, lack of an ideal diagnostic test, and the inability to easily identify affected patients using administrative claims data.

OBJECTIVES

To develop a machine learning model that identifies patients in a commercial medical claims database who likely have EPI but are undiagnosed.

METHODS

A machine learning algorithm was developed in Scikit-learn, a Python module. The study population, selected from the 2014 Truven MarketScan® Commercial Claims Database, consisted of patients with EPI-prone conditions. Patients were labeled with 290 condition category flags and split into actual positive EPI cases, actual negative EPI cases, and unlabeled cases. The study population was then randomly divided into a training subset and a testing subset. The training subset was used to determine the performance metrics of 27 models and to select the highest performing model, and the testing subset was used to evaluate performance of the best machine learning model.

RESULTS

The study population consisted of 2088 actual positive EPI cases, 1077 actual negative EPI cases, and 437 530 unlabeled cases. In the best performing model, the precision, recall, and accuracy were 0.91, 0.80, and 0.86, respectively. The best-performing model estimated that the number of patients likely to have EPI was about 12 times the number of patients directly identified as EPI-positive through a claims analysis in the study population. The most important features in assigning EPI probability were the presence or absence of diagnosis codes related to pancreatic and digestive conditions.

CONCLUSIONS

Machine learning techniques demonstrated high predictive power in identifying patients with EPI and could facilitate an enhanced understanding of its etiology and help to identify patients for possible diagnosis and treatment.

Big Brain Data: On the Responsible Use of Brain Data from Clinical and Consumer-Directed Neurotechnological Devices

The focus of this paper are the ethical, legal and social challenges for ensuring the responsible use of “big brain data”—the recording, collection and analysis of individuals’ brain data on a large scale with clinical and consumer-directed neurotechnological devices. First, I highlight the benefits of big data and machine learning analytics in neuroscience for basic and translational research. Then, I describe some of the technological, social and psychological barriers for securing brain data from unwarranted access. In this context, I then examine ways in which safeguards at the hardware and software level, as well as increasing “data literacy” in society, may enhance the security of neurotechnological devices and protect the privacy of personal brain data. Regarding ethical and legal ramifications of big brain data, I first discuss effects on the autonomy, the sense of agency and authenticity, as well as the self that may result from the interaction between users and intelligent, particularly closed-loop, neurotechnological devices. I then discuss the impact of the “datafication” in basic and clinical neuroscience research on the just distribution of resources and access to these transformative technologies. In the legal realm, I examine possible legal consequences that arises from the increasing abilities to decode brain states and their corresponding subjective phenomenological experiences on the hitherto inaccessible privacy of these information. Finally, I discuss the implications of big brain data for national and international regulatory policies and models of good data governance.

Using a Guided Machine Learning Ensemble Model to Predict Discharge Disposition following Meningioma Resection

Objective  Machine learning (ML) algorithms are powerful tools for predicting patient outcomes. This study pilots a novel approach to algorithm selection and model creation using prediction of discharge disposition following meningioma resection as a proof of concept. Materials and Methods  A diversity of ML algorithms were trained on a single-institution database of meningioma patients to predict discharge disposition. Algorithms were ranked by predictive power and top performers were combined to create an ensemble model. The final ensemble was internally validated on never-before-seen data to demonstrate generalizability. The predictive power of the ensemble was compared with a logistic regression. Further analyses were performed to identify how important variables impact the ensemble. Results  Our ensemble model predicted disposition significantly better than a logistic regression (area under the curve of 0.78 and 0.71, respectively, p  = 0.01). Tumor size, presentation at the emergency department, body mass index, convexity location, and preoperative motor deficit most strongly influence the model, though the independent impact of individual variables is nuanced. Conclusion  Using a novel ML technique, we built a guided ML ensemble model that predicts discharge destination following meningioma resection with greater predictive power than a logistic regression, and that provides greater clinical insight than a univariate analysis. These techniques can be extended to predict many other patient outcomes of interest.

Realising stratified psychiatry using multidimensional signatures and trajectories

Background

Stratified or personalised medicine targets treatments for groups of individuals with a disorder based on individual heterogeneity and shared factors that influence the likelihood of response. Psychiatry has traditionally defined diagnoses by constellations of co-occurring signs and symptoms that are assigned a categorical label (e.g. schizophrenia). Trial methodology in psychiatry has evaluated interventions targeted at these categorical entities, with diagnoses being equated to disorders. Recent insights into both the nosology and neurobiology of psychiatric disorder reveal that traditional categorical diagnoses cannot be equated with disorders. We argue that current quantitative methodology (1) inherits these categorical assumptions, (2) allows only for the discovery of average treatment response, (3) relies on composite outcome measures and (4) sacrifices valuable predictive information for stratified and personalised treatment in psychiatry.

Methods and findings

To achieve a truly ‘stratified psychiatry’ we propose and then operationalise two necessary steps: first, a formal multi-dimensional representation of disorder definition and clinical state, and second, the similar redefinition of outcomes as multidimensional constructs that can expose within- and between-patient differences in response. We use the categorical diagnosis of schizophrenia—conceptualised as a label for heterogeneous disorders—as a means of introducing operational definitions of stratified psychiatry using principles from multivariate analysis. We demonstrate this framework by application to the Clinical Antipsychotic Trials of Intervention Effectiveness dataset, showing heterogeneity in both patient clinical states and their trajectories after treatment that are lost in the traditional categorical approach with composite outcomes. We then systematically review a decade of registered clinical trials for cognitive deficits in schizophrenia highlighting existing assumptions of categorical diagnoses and aggregate outcomes while identifying a small number of trials that could be reanalysed using our proposal.

Conclusion

We describe quantitative methods for the development of a multi-dimensional model of clinical state, disorders and trajectories which practically realises stratified psychiatry. We highlight the potential for recovering existing trial data, the implications for stratified psychiatry in trial design and clinical treatment and finally, describe different kinds of probabilistic reasoning tools necessary to implement stratification.