Building a genetic risk model for bipolar disorder from genome-wide association data with random forest algorithm

Genomic Machine Learning Meta-regression: Insights on Associations of Study Features With Reported Model Performance

Many studies have been conducted with the goal of correctly predicting diagnostic status of a disorder using the combination of genomic data and machine learning. It is often hard to judge which components of a study led to better results and whether better reported results represent a true improvement or an uncorrected bias inflating performance. We extracted information about the methods used and other differentiating features in genomic machine learning models. We used these features in linear regressions predicting model performance. We tested for univariate and multivariate associations as well as interactions between features. Of the models reviewed, 46% used feature selection methods that can lead to data leakage. Across our models, the number of hyperparameter optimizations reported, data leakage due to feature selection, model type, and modeling an autoimmune disorder were significantly associated with an increase in reported model performance. We found a significant, negative interaction between data leakage and training size. Our results suggest that methods susceptible to data leakage are prevalent among genomic machine learning research, resulting in inflated reported performance. Best practice guidelines that promote the avoidance and recognition of data leakage may help the field avoid biased results.

Functional variants identify sex-specific genes and pathways in Alzheimer's Disease

The incidence of Alzheimer's Disease in females is almost double that of males. To search for sex-specific gene associations, we build a machine learning approach focused on functionally impactful coding variants. This method can detect differences between sequenced cases and controls in small cohorts. In the Alzheimer's Disease Sequencing Project with mixed sexes, this approach identified genes enriched for immune response pathways. After sex-separation, genes become specifically enriched for stress-response pathways in male and cell-cycle pathways in female. These genes improve disease risk prediction in silico and modulate Drosophila neurodegeneration in vivo. Thus, a general approach for machine learning on functionally impactful variants can uncover sex-specific candidates towards diagnostic biomarkers and therapeutic targets.

A comprehensive investigation of statistical and machine learning approaches for predicting complex human diseases on genomic variants

Quantifying an individual's risk for common diseases is an important goal of precision health. The polygenic risk score (PRS), which aggregates multiple risk alleles of candidate diseases, has emerged as a standard approach for identifying high-risk individuals. Although several studies have been performed to benchmark the PRS calculation tools and assess their potential to guide future clinical applications, some issues remain to be further investigated, such as lacking (i) various simulated data with different genetic effects; (ii) evaluation of machine learning models and (iii) evaluation on multiple ancestries studies. In this study, we systematically validated and compared 13 statistical methods, 5 machine learning models and 2 ensemble models using simulated data with additive and genetic interaction models, 22 common diseases with internal training sets, 4 common diseases with external summary statistics and 3 common diseases for trans-ancestry studies in UK Biobank. The statistical methods were better in simulated data from additive models and machine learning models have edges for data that include genetic interactions. Ensemble models are generally the best choice by integrating various statistical methods. LDpred2 outperformed the other standalone tools, whereas PRS-CS, lassosum and DBSLMM showed comparable performance. We also identified that disease heritability strongly affected the predictive performance of all methods. Both the number and effect sizes of risk SNPs are important; and sample size strongly influences the performance of all methods. For the trans-ancestry studies, we found that the performance of most methods became worse when training and testing sets were from different populations.

Machine learning algorithm performance evaluation in structural magnetic resonance imaging-based classification of pediatric bipolar disorders type I patients

The diagnosis based on clinical assessment of pediatric bipolar disorder (PBD) may sometimes lead to misdiagnosis in clinical practice. For the past several years, machine learning (ML) methods were introduced for the classification of bipolar disorder (BD), which were helpful in the diagnosis of BD. In this study, brain cortical thickness and subcortical volume of 33 PBD-I patients and 19 age-sex matched healthy controls (HCs) were extracted from the magnetic resonance imaging (MRI) data and set as features for classification. The dimensionality reduced feature subset, which was filtered by Lasso or f_classif, was sent to the six classifiers (logistic regression (LR), support vector machine (SVM), random forest classifier, naïve Bayes, k-nearest neighbor, and AdaBoost algorithm), and the classifiers were trained and tested. Among all the classifiers, the top two classifiers with the highest accuracy were LR (84.19%) and SVM (82.80%). Feature selection was performed in the six algorithms to obtain the most important variables including the right middle temporal gyrus and bilateral pallidum, which is consistent with structural and functional anomalous changes in these brain regions in PBD patients. These findings take the computer-aided diagnosis of BD a step forward.

The application of machine learning to predict genetic relatedness using human mtDNA hypervariable region I sequences

Human identification of unknown samples following disaster and mass casualty events is essential, especially to bring closure to family and friends of the deceased. Unfortunately, victim identification is often challenging for forensic investigators as analysis becomes complicated when biological samples are degraded or of poor quality as a result of exposure to harsh environmental factors. Mitochondrial DNA becomes the ideal option for analysis, particularly for determining the origin of the samples. In such events, the estimation of genetic parameters plays an important role in modelling and predicting genetic relatedness and is useful in assigning unknown individuals to an ethnic group. Various techniques exist for the estimation of genetic relatedness, but the use of Machine learning (ML) algorithms are novel and presently the least used in forensic genetic studies. In this study, we investigated the ability of ML algorithms to predict genetic relatedness using hypervariable region I sequences; that were retrieved from the GenBank database for three race groups, namely African, Asian and Caucasian. Four ML classification algorithms; Support vector machines (SVM), Linear discriminant analysis (LDA), Quadratic discriminant analysis (QDA) and Random Forest (RF) were hybridised with one-hot encoding, Principal component analysis (PCA) and Bags of Words (BoW), and were compared for inferring genetic relatedness. The findings from this study on WEKA showed that genetic inferences based on PCA-SVM achieved an overall accuracy of 80–90% and consistently outperformed PCA-LDA, PCA-RF and PCA-QDA, while in Python BoW-PCA-RF achieved 94.4% accuracy which outperformed BoW-PCA-SVM, BoW-PCA-LDA and BoW-PCA-QDA respectively. ML results from the use of WEKA and Python software tools displayed higher accuracies as compared to the Analysis of molecular variance results. Given the results, SVM and RF algorithms are likely to also be useful in other sequence classification applications, making it a promising tool in genetics and forensic science. The study provides evidence that ML can be utilized as a supplementary tool for forensic genetics casework analysis.

Machine learning approaches for prediction of bipolar disorder based on biological, clinical and neuropsychological markers: a systematic review and meta-analysis

Applying machine learning (ML) to objective markers may overcome prognosis uncertainty due to the subjective nature of the diagnosis of bipolar disorder (BD). This PRISMA-compliant meta-analysis provides new systematic evidence of the BD classification accuracy reached by different markers and ML algorithms. We focused on neuroimaging, electrophysiological techniques, peripheral biomarkers, genetic data, neuropsychological or clinical measures, and multimodal approaches. PubMed, Embase and Scopus were searched through 3^rd December 2020. Meta-analyses were performed using random-effect models. Overall, 81 studies were included in this systematic review and 65 in the meta-analysis (11,336 participants, 3,903 BD). The overall pooled classification accuracy was 0.77 (95%CI[0.75;0.80]). Despite subgroup analyses for diagnostic comparison group, psychiatric disorders, marker, ML algorithm, and validation procedure were not significant, linear discriminant analysis significantly outperformed support vector machine for peripheral biomarkers (p=0.03). Sample size was inversely related to accuracy. Evidence of publication bias was detected. Ultimately, although ML reached a high accuracy in differentiating BD from other psychiatric disorders, best practices in methodology are needed for the advancement of future studies.

New Diagnostic Model for the Differentiation of Diabetic Nephropathy From Non-Diabetic Nephropathy in Chinese Patients

BACKGROUND

The disease pathology for diabetes mellitus patients with chronic kidney disease (CKD) may be diabetic nephropathy (DN), non-diabetic renal disease (NDRD), or DN combined with NDRD. Considering that the prognosis and treatment of DN and NDRD differ, their differential diagnosis is of significance. Renal pathological biopsy is the gold standard for diagnosing DN and NDRD. However, it is invasive and cannot be implemented in many patients due to contraindications. This article constructed a new noninvasive evaluation model for differentiating DN and NDRD.

METHODS

We retrospectively screened 1,030 patients with type 2 diabetes who has undergone kidney biopsy from January 2005 to March 2017 in a single center. Variables were ranked according to importance, and the machine learning methods (random forest, RF, and support vector machine, SVM) were then used to construct the model. The final model was validated with an external group (338 patients, April 2017-April 2019).

RESULTS

In total, 929 patients were assigned. Ten variables were selected for model development. The areas under the receiver operating characteristic curves (AUCROCs) for the RF and SVM methods were 0.953 and 0.947, respectively. Additionally, 329 patients were analyzed for external validation. The AUCROCs for the external validation of the RF and SVM methods were 0.920 and 0.911, respectively.

CONCLUSION

We successfully constructed a predictive model for DN and NDRD using machine learning methods, which were better than our regression methods.

CLINICAL TRIAL REGISTRATION

ClinicalTrial.gov, NCT03865914.

The Role of Machine Learning in Diagnosing Bipolar Disorder: Scoping Review

Background

Bipolar disorder (BD) is the 10th most common cause of frailty in young individuals and has triggered morbidity and mortality worldwide. Patients with BD have a life expectancy 9 to 17 years lower than that of normal people. BD is a predominant mental disorder, but it can be misdiagnosed as depressive disorder, which leads to difficulties in treating affected patients. Approximately 60% of patients with BD are treated for depression. However, machine learning provides advanced skills and techniques for better diagnosis of BD.

Objective

This review aims to explore the machine learning algorithms used for the detection and diagnosis of bipolar disorder and its subtypes.

Methods

The study protocol adopted the PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta-Analyses Extension for Scoping Reviews) guidelines. We explored 3 databases, namely Google Scholar, ScienceDirect, and PubMed. To enhance the search, we performed backward screening of all the references of the included studies. Based on the predefined selection criteria, 2 levels of screening were performed: title and abstract review, and full review of the articles that met the inclusion criteria. Data extraction was performed independently by all investigators. To synthesize the extracted data, a narrative synthesis approach was followed.

Results

We retrieved 573 potential articles were from the 3 databases. After preprocessing and screening, only 33 articles that met our inclusion criteria were identified. The most commonly used data belonged to the clinical category (19, 58%). We identified different machine learning models used in the selected studies, including classification models (18, 55%), regression models (5, 16%), model-based clustering methods (2, 6%), natural language processing (1, 3%), clustering algorithms (1, 3%), and deep learning–based models (3, 9%). Magnetic resonance imaging data were most commonly used for classifying bipolar patients compared to other groups (11, 34%), whereas microarray expression data sets and genomic data were the least commonly used. The maximum ratio of accuracy was 98%, whereas the minimum accuracy range was 64%.

Conclusions

This scoping review provides an overview of recent studies based on machine learning models used to diagnose patients with BD regardless of their demographics or if they were compared to patients with psychiatric diagnoses. Further research can be conducted to provide clinical decision support in the health industry.

The Role of the UPR Pathway in the Pathophysiology and Treatment of Bipolar Disorder

Bipolar disorder (BD) is a mood disorder that affects millions worldwide and is associated with severe mood swings between mania and depression. The mood stabilizers valproate (VPA) and lithium (Li) are among the main drugs that are used to treat BD patients. However, these drugs are not effective for all patients and cause serious side effects. Therefore, better drugs are needed to treat BD patients. The main barrier to developing new drugs is the lack of knowledge about the therapeutic mechanism of currently available drugs. Several hypotheses have been proposed for the mechanism of action of mood stabilizers. However, it is still not known how they act to alleviate both mania and depression. The pathology of BD is characterized by mitochondrial dysfunction, oxidative stress, and abnormalities in calcium signaling. A deficiency in the unfolded protein response (UPR) pathway may be a shared mechanism that leads to these cellular dysfunctions. This is supported by reported abnormalities in the UPR pathway in lymphoblasts from BD patients. Additionally, studies have demonstrated that mood stabilizers alter the expression of several UPR target genes in mouse and human neuronal cells. In this review, we outline a new perspective wherein mood stabilizers exert their therapeutic mechanism by activating the UPR. Furthermore, we discuss UPR abnormalities in BD patients and suggest future research directions to resolve discrepancies in the literature.

The roles of antimicrobial resistance, phage diversity, isolation source and selection in shaping the genomic architecture of Bacillus anthracis

Bacillus anthracis, the causative agent of anthrax disease, is a worldwide threat to livestock, wildlife and public health. While analyses of genetic data from across the globe have increased our understanding of this bacterium’s population genomic structure, the influence of selective pressures on this successful pathogen is not well understood. In this study, we investigate the effects of antimicrobial resistance, phage diversity, geography and isolation source in shaping population genomic structure. We also identify a suite of candidate genes potentially under selection, driving patterns of diversity across 356 globally extant B. anthracis genomes. We report ten antimicrobial resistance genes and 11 different prophage sequences, resulting in the first large-scale documentation of these genetic anomalies for this pathogen. Results of random forest classification suggest genomic structure may be driven by a combination of antimicrobial resistance, geography and isolation source, specific to the population cluster examined. We found strong evidence that a recombination event linked to a gene involved in protein synthesis may be responsible for phenotypic differences between comparatively disparate populations. We also offer a list of genes for further examination of B. anthracis evolution, based on high-impact single nucleotide polymorphisms (SNPs) and clustered mutations. The information presented here sheds new light on the factors driving genomic structure in this notorious pathogen and may act as a road map for future studies aimed at understanding functional differences in terms of B. anthracis biogeography, virulence and evolution.

The Role of Machine Learning in Diagnosing Bipolar Disorder: Scoping Review (Preprint).. [DOI: 10.2196/preprints.29749] [Citation(s) in RCA: 0] [Impact Index Per Article: 0]

BACKGROUND

Bipolar disorder (BD) is the 10th most common cause of frailty in young individuals and has triggered morbidity and mortality worldwide. Patients with BD have a life expectancy 9 to 17 years lower than that of normal people. BD is a predominant mental disorder, but it can be misdiagnosed as depressive disorder, which leads to difficulties in treating affected patients. Approximately 60% of patients with BD are treated for depression. However, machine learning provides advanced skills and techniques for better diagnosis of BD.

OBJECTIVE

This review aims to explore the machine learning algorithms used for the detection and diagnosis of bipolar disorder and its subtypes.

METHODS

The study protocol adopted the PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta-Analyses Extension for Scoping Reviews) guidelines. We explored 3 databases, namely Google Scholar, ScienceDirect, and PubMed. To enhance the search, we performed backward screening of all the references of the included studies. Based on the predefined selection criteria, 2 levels of screening were performed: title and abstract review, and full review of the articles that met the inclusion criteria. Data extraction was performed independently by all investigators. To synthesize the extracted data, a narrative synthesis approach was followed.

RESULTS

We retrieved 573 potential articles were from the 3 databases. After preprocessing and screening, only 33 articles that met our inclusion criteria were identified. The most commonly used data belonged to the clinical category (19, 58%). We identified different machine learning models used in the selected studies, including classification models (18, 55%), regression models (5, 16%), model-based clustering methods (2, 6%), natural language processing (1, 3%), clustering algorithms (1, 3%), and deep learning–based models (3, 9%). Magnetic resonance imaging data were most commonly used for classifying bipolar patients compared to other groups (11, 34%), whereas microarray expression data sets and genomic data were the least commonly used. The maximum ratio of accuracy was 98%, whereas the minimum accuracy range was 64%.

CONCLUSIONS

This scoping review provides an overview of recent studies based on machine learning models used to diagnose patients with BD regardless of their demographics or if they were compared to patients with psychiatric diagnoses. Further research can be conducted to provide clinical decision support in the health industry.

Optimization of parallel random forest algorithm based on distance weight

In order to overcome the problems of long execution time and low parallelism of existing parallel random forest algorithms, an optimization method for parallel random forest algorithm based on distance weights is proposed. The concept of distance weights is introduced to optimize the algorithm. Firstly, the training sample data are extracted from the original data set by random selection. Based on the extracted results, a single decision tree is constructed. The single decision tree is grouped together according to different grouping methods to form a random forest. The distance weights of the training sample data set are calculated, and then the weighted optimization of the random forest model is realized. The experimental results show that the execution time of the parallel random forest algorithm after optimization is 110 000 ms less than that before optimization, and the operation efficiency of the algorithm is greatly improved, which effectively solves the problems existing in the traditional random forest algorithm.

Machine learning and big data analytics in bipolar disorder: A position paper from the International Society for Bipolar Disorders Big Data Task Force

OBJECTIVES

The International Society for Bipolar Disorders Big Data Task Force assembled leading researchers in the field of bipolar disorder (BD), machine learning, and big data with extensive experience to evaluate the rationale of machine learning and big data analytics strategies for BD.

METHOD

A task force was convened to examine and integrate findings from the scientific literature related to machine learning and big data based studies to clarify terminology and to describe challenges and potential applications in the field of BD. We also systematically searched PubMed, Embase, and Web of Science for articles published up to January 2019 that used machine learning in BD.

RESULTS

The results suggested that big data analytics has the potential to provide risk calculators to aid in treatment decisions and predict clinical prognosis, including suicidality, for individual patients. This approach can advance diagnosis by enabling discovery of more relevant data-driven phenotypes, as well as by predicting transition to the disorder in high-risk unaffected subjects. We also discuss the most frequent challenges that big data analytics applications can face, such as heterogeneity, lack of external validation and replication of some studies, cost and non-stationary distribution of the data, and lack of appropriate funding.

CONCLUSION

Machine learning-based studies, including atheoretical data-driven big data approaches, provide an opportunity to more accurately detect those who are at risk, parse-relevant phenotypes as well as inform treatment selection and prognosis. However, several methodological challenges need to be addressed in order to translate research findings to clinical settings.

Validation of a clinical-genetics score to predict hemorrhagic transformations after rtPA

OBJECTIVE

To validate the Genot-PA score, a clinical-genetic logistic regression score that stratifies the thrombolytic therapy safety, in a new cohort of patients with stroke.

METHODS

We enrolled 1,482 recombinant tissue plasminogen activator (rtPA)-treated patients with stroke in Spain and Finland from 2003 to 2016. Cohorts were analyzed on the basis of ethnicity and therapy: Spanish patients treated with IV rtPA within 4.5 hours of onset (cohort A and B) or rtPA in combination with mechanical thrombectomy within 6 hours of onset (cohort C) and Finnish participants treated with IV rtPA within 4.5 hours of onset (cohort D). The Genot-PA score was calculated, and hemorrhagic transformation (HT) and parenchymal hematoma (PH) risks were determined for each score stratum.

RESULTS

Genot-PA score was tested in 1,324 (cohort A, n = 726; B, n = 334; C, n = 54; and D, n = 210) patients who had enough information to complete the score. Of these, 213 (16.1%) participants developed HT and 85 (6.4%) developed PH. In cohorts A, B, and D, HT occurrence was predicted by the score (p = 2.02 × 10^-6, p = 0.023, p = 0.033); PH prediction was associated in cohorts A through C (p = 0.012, p = 0.034, p = 5.32 × 10^-4). Increased frequency of PH events from the lowest to the highest risk group was found (cohort A 4%-15.7%, cohort B 1.5%-18.2%, cohort C 0%-100%). The best odds ratio for PH prediction in the highest-risk group was obtained in cohort A (odds ratio 5.16, 95% confidence interval 1.46-18.08, p = 0.009).

CONCLUSION

The Genot-PA score predicts HT in patients with stroke treated with IV rtPA. Moreover, in an exploratory study, the score was associated with PH risk in mechanical thrombectomy-treated patients.

Multivariate Pattern Analysis of Genotype-Phenotype Relationships in Schizophrenia

Genetic risk variants for schizophrenia have been linked to many related clinical and biological phenotypes with the hopes of delineating how individual variation across thousands of variants corresponds to the clinical and etiologic heterogeneity within schizophrenia. This has primarily been done using risk score profiling, which aggregates effects across all variants into a single predictor. While effective, this method lacks flexibility in certain domains: risk scores cannot capture nonlinear effects and do not employ any variable selection. We used random forest, an algorithm with this flexibility designed to maximize predictive power, to predict 6 cognitive endophenotypes in a combined sample of psychiatric patients and controls (N = 739) using 77 genetic variants strongly associated with schizophrenia. Tenfold cross-validation was applied to the discovery sample and models were externally validated in an independent sample of similar ancestry (N = 336). Linear approaches, including linear regression and task-specific polygenic risk scores, were employed for comparison. Random forest models for processing speed (P = .019) and visual memory (P = .036) and risk scores developed for verbal (P = .042) and working memory (P = .037) successfully generalized to an independent sample with similar predictive strength and error. As such, we suggest that both methods may be useful for mapping a limited set of predetermined, disease-associated SNPs to related phenotypes. Incorporating random forest and other more flexible algorithms into genotype-phenotype mapping inquiries could contribute to parsing heterogeneity within schizophrenia; such algorithms can perform as well as standard methods and can capture a more comprehensive set of potential relationships.

The revolution of personalized psychiatry: will technology make it happen sooner?

Personalized medicine (PM) aims to establish a new approach in clinical decision-making, based upon a patient's individual profile in order to tailor treatment to each patient's characteristics. Although this has become a focus of the discussion also in the psychiatric field, with evidence of its high potential coming from several proof-of-concept studies, nearly no tools have been developed by now that are ready to be applied in clinical practice. In this paper, we discuss recent technological advances that can make a shift toward a clinical application of the PM paradigm. We focus specifically on those technologies that allow both the collection of massive as much as real-time data, i.e., electronic medical records and smart wearable devices, and to achieve relevant predictions using these data, i.e. the application of machine learning techniques.

Supervised Machine-Learning Reveals That Old and Obese People Achieve Low Dapsone Concentrations

The human species is becoming increasingly obese. Dapsone, which is extensively used across the globe for dermatological disorders, arachnid bites, and for treatment of several bacterial, fungal, and parasitic diseases, could be affected by obesity. We performed a clinical experiment, using optimal design, in volunteers weighing 44-150 kg, to identify the effect of obesity on dapsone pharmacokinetic parameters based on maximum-likelihood solution via the expectation-maximization algorithm. Artificial intelligence-based multivariate adaptive regression splines were used for covariate selection, and identified weight and/or age as predictors of absorption, systemic clearance, and volume of distribution. These relationships occurred only between certain patient weight and age ranges, delimited by multiple hinges and regions of discontinuity, not identified by standard pharmacometric approaches. Older and obese people have lower drug concentrations after standard dosing, but with complex patterns. Given that efficacy is concentration-dependent, optimal dapsone doses need to be personalized for obese patients.

The impact of machine learning techniques in the study of bipolar disorder: A systematic review

Machine learning techniques provide new methods to predict diagnosis and clinical outcomes at an individual level. We aim to review the existing literature on the use of machine learning techniques in the assessment of subjects with bipolar disorder. We systematically searched PubMed, Embase and Web of Science for articles published in any language up to January 2017. We found 757 abstracts and included 51 studies in our review. Most of the included studies used multiple levels of biological data to distinguish the diagnosis of bipolar disorder from other psychiatric disorders or healthy controls. We also found studies that assessed the prediction of clinical outcomes and studies using unsupervised machine learning to build more consistent clinical phenotypes of bipolar disorder. We concluded that given the clinical heterogeneity of samples of patients with BD, machine learning techniques may provide clinicians and researchers with important insights in fields such as diagnosis, personalized treatment and prognosis orientation.