Machine learning characterization of a rare neurologic disease via electronic health records: a proof-of-principle study on stiff person syndrome.

BACKGROUND: Despite the frequent diagnostic delays of rare neurologic diseases (RND), it remains difficult to study RNDs and their comorbidities due to their rarity and hence the statistical underpowering. Affecting one to two in a million annually, stiff person syndrome (SPS) is an RND characterized by painful muscle spasms and rigidity. Leveraging underutilized electronic health records (EHR), this study showcased a machine-learning-based framework to identify clinical features that optimally characterize the diagnosis of SPS. METHODS: A machine-learning-based feature selection approach was employed on 319 items from the past medical histories of 48 individuals (23 with a diagnosis of SPS and 25 controls) with elevated serum autoantibodies against glutamic-acid-decarboxylase-65 (anti-GAD65) in Dartmouth Health's EHR to determine features with the highest discriminatory power. Each iteration of the algorithm implemented a Support Vector Machine (SVM) model, generating importance scores-SHapley Additive exPlanation (SHAP) values-for each feature and removing one with the least salient. Evaluation metrics were calculated through repeated stratified cross-validation. RESULTS: Depression, hypothyroidism, GERD, and joint pain were the most characteristic features of SPS. Utilizing these features, the SVM model attained precision of 0.817 (95% CI 0.795-0.840), sensitivity of 0.766 (95% CI 0.743-0.790), F-score of 0.761 (95% CI 0.744-0.778), AUC of 0.808 (95% CI 0.791-0.825), and accuracy of 0.775 (95% CI 0.759-0.790). CONCLUSIONS: This framework discerned features that, with further research, may help fully characterize the pathologic mechanism of SPS: depression, hypothyroidism, and GERD may respectively represent comorbidities through common inflammatory, genetic, and dysautonomic links. This methodology could address diagnostic challenges in neurology by uncovering latent associations and generating hypotheses for RNDs.

Neuroscience in pictures: 2. Sleep, wakefulness, and mental state biology.

Sleep is a vital restorative process that has occupied our curiosity for millennia. Despite our longstanding research efforts, the biology of sleep and its connection to mental states remains enigmatic. Unsurprisingly, sleep and wakefulness, the fundamental processes between which our mental states oscillate, are inseparable from our physical and mental health. Thus, clinical consideration of sleep impairments warrants a transdiagnostic approach whilst appropriately acknowledging that certain individual disorders (e.g. depression, schizophrenia) may have somewhat distinct sleep disturbances. Moreover, our knowledge of the anatomy and physiology of sleep regulation-albeit limited-forms the foundation for current treatments for sleep difficulties. This pictorial article overviews the core concepts and future of sleep neuroscience and mental state biology for trainees and practitioners in psychiatry and related professions.

Neuroscience in pictures:1. History of psychiatric neuroscience.

Our understanding of the brain basis of mental illness has evolved over three and half millennia. Early insights into the role of the brain in relation to the mind faded during the middle ages as mental illness became the province of religion, spirituality, and philosophy. Psychiatry became a medical discipline again as medical and scientific thinking evolved during the 17th century. However, progress in neuroscience and astute clinical observations were punctuated by setbacks due to lingering dualism, reductionistic thinking, and dogma. Accelerating neuroscience discoveries and methodological innovations are beginning to bring neuroscience and psychiatry closer than ever as we begin the 21st century, This pictorial article seeks to briefly highlight this journey for an early trainee in psychiatry and related professions in mind.

Using digital phenotyping to capture depression symptom variability: detecting naturalistic variability in depression symptoms across one year using passively collected wearable movement and sleep data.

Major Depressive Disorder (MDD) presents considerable challenges to diagnosis and management due to symptom variability across time. Only recent work has highlighted the clinical implications for interrogating depression symptom variability. Thus, the present work investigates how sociodemographic, comorbidity, movement, and sleep data is associated with long-term depression symptom variability. Participant information included (N = 939) baseline sociodemographic and comorbidity data, longitudinal, passively collected wearable data, and Patient Health Questionnaire-9 (PHQ-9) scores collected over 12 months. An ensemble machine learning approach was used to detect long-term depression symptom variability via: (i) a domain-driven feature selection approach and (ii) an exhaustive feature-inclusion approach. SHapley Additive exPlanations (SHAP) were used to interrogate variable importance and directionality. The composite domain-driven and exhaustive inclusion models were both capable of moderately detecting long-term depression symptom variability (r = 0.33 and r = 0.39, respectively). Our results indicate the incremental predictive validity of sociodemographic, comorbidity, and passively collected wearable movement and sleep data in detecting long-term depression symptom variability.

Paraphilic disorders, psychopathy, and those who sexually offend: a narrative review of treatment modalities.

Despite its critical importance, the treatment of paraphilic disorders remains an often-overlooked domain both in clinical research and practice. Challenges have arisen in the morphing understanding of paraphilias and paraphilic disorders, now considered separate concepts, and efforts at developing a more nuanced understanding of these conditions is ongoing, resulting in a muddled history that can frustrate efforts at study and treatment. These populations are by nature more heterogeneous than may first be obvious-particularly among those with comorbid psychopathic traits-and may require a more nuanced and individualized approach based on risk, needs, and responsivity to treatment. Until recently, there were few guidelines to assist clinicians when confronted with these complicated clinical pictures and a sea of discrete studies investigating various biological and non-biological interventions. Treatments range from several variations of psychotherapy and behavioral therapies to SSRIs, anti-androgenic medications, to orchiectomy, all displaying varying degrees of effectiveness and evidence across decades of research. Fortunately, recent efforts to collate these studies supported by a task force of the World Federation of Societies of Biological Psychiatry (WFSBP) have helped form a better-focused and better-evidenced picture of effective treatments and the unique challenges faced by (and with) these populations.

Testing domain knowledge and risk of bias of a large-scale general artificial intelligence model in mental health.

Background: With a rapidly expanding gap between the need for and availability of mental health care, artificial intelligence (AI) presents a promising, scalable solution to mental health assessment and treatment. Given the novelty and inscrutable nature of such systems, exploratory measures aimed at understanding domain knowledge and potential biases of such systems are necessary for ongoing translational development and future deployment in high-stakes healthcare settings. Methods: We investigated the domain knowledge and demographic bias of a generative, AI model using contrived clinical vignettes with systematically varied demographic features. We used balanced accuracy (BAC) to quantify the model's performance. We used generalized linear mixed-effects models to quantify the relationship between demographic factors and model interpretation. Findings: We found variable model performance across diagnoses; attention deficit hyperactivity disorder, posttraumatic stress disorder, alcohol use disorder, narcissistic personality disorder, binge eating disorder, and generalized anxiety disorder showed high BAC (0.70 ≤ BAC ≤ 0.82); bipolar disorder, bulimia nervosa, barbiturate use disorder, conduct disorder, somatic symptom disorder, benzodiazepine use disorder, LSD use disorder, histrionic personality disorder, and functional neurological symptom disorder showed low BAC (BAC ≤ 0.59). Interpretation: Our findings demonstrate initial promise in the domain knowledge of a large AI model, with performance variability perhaps due to the more salient hallmark symptoms, narrower differential diagnosis, and higher prevalence of some disorders. We found limited evidence of model demographic bias, although we do observe some gender and racial differences in model outcomes mirroring real-world differential prevalence estimates.

Effects of clozapine-N-oxide and compound 21 on sleep in laboratory mice.

Designer receptors exclusively activated by designer drugs (DREADDs) are chemogenetic tools for remote control of targeted cell populations using chemical actuators that bind to modified receptors. Despite the popularity of DREADDs in neuroscience and sleep research, potential effects of the DREADD actuator clozapine-N-oxide (CNO) on sleep have never been systematically tested. Here, we show that intraperitoneal injections of commonly used CNO doses (1, 5, and 10 mg/kg) alter sleep in wild-type male laboratory mice. Using electroencephalography (EEG) and electromyography (EMG) to analyse sleep, we found a dose-dependent suppression of rapid eye movement (REM) sleep, changes in EEG spectral power during non-REM (NREM) sleep, and altered sleep architecture in a pattern previously reported for clozapine. Effects of CNO on sleep could arise from back-metabolism to clozapine or binding to endogenous neurotransmitter receptors. Interestingly, we found that the novel DREADD actuator, compound 21 (C21, 3 mg/kg), similarly modulates sleep despite a lack of back-metabolism to clozapine. Our results demonstrate that both CNO and C21 can modulate sleep of mice not expressing DREADD receptors. This implies that back-metabolism to clozapine is not the sole mechanism underlying side effects of chemogenetic actuators. Therefore, any chemogenetic experiment should include a DREADD-free control group injected with the same CNO, C21, or newly developed actuator. We suggest that electrophysiological sleep assessment could serve as a sensitive tool to test the biological inertness of novel chemogenetic actuators.

Scientists have developed ways to remotely turn on and off populations of neurons in the brain to test the role they play in behaviour. One technique that is frequently used is chemogenetics. In this approach, specific neurons are genetically modified to contain a special 'designer receptor' which switches cells on or off when its corresponding 'designer drug' is present. Recent studies have shown that the drug most commonly used in these experiments, clozapine-N-oxide (CNO), is broken down into small amounts of clozapine, an antipsychotic drug that binds to many natural receptors in the brain and modulates sleep. Nevertheless, CNO is still widely believed to not affect animals' sleep-wake patterns which in turn could influence a range of other brain activities and behaviours. However, there have been reports of animals lacking designer receptors still displaying unusual behaviours when administered CNO. This suggests that the breakdown of CNO to clozapine may cause off-target effects which could be skewing the results of chemogenetic studies. To investigate this possibility, Traut, Mengual et al. treated laboratory mice that do not have a designer receptor with three doses of CNO, and one dose of a new designer drug called compound-21 (C21) that is not broken down to clozapine. They found that high and medium doses of CNO, but also C21 altered the sleep-wake patterns of the mice and their brain activity during sleep. These findings show that CNO and C21 both have sleep-modulating effects on the brain and suggest that these effects are not only due to the production of clozapine, but the drugs binding to off-target natural receptors. To counteract this, Traut, Mengual et al. recommend optimizing the dose of drugs given to mice, and repeating the experiment on a control group which do not have the designer receptor. This will allow researchers to determine which behavioural changes are the result of turning on or off the neuron population of interest, and which are artefacts caused by the drug itself. They also suggest testing how newly developed designer drugs impact sleep before using them in behavioural experiments. Refining chemogenetic studies in these ways may yield more reliable insights about the role specific groups of cells have in the brain.

Dr. Djunga: First Congolese Neurosurgeon.

Antoine Shako Hiango Omokanda Djunga was the pioneer of neurosurgery in the Democratic Republic of Congo (DRC), a country located in Central Africa. He was born in 1938 in Sankuru, a province of the DRC. He graduated from the Free University of Brussels medical school and later trained there in neurosurgery. Thereafter, he completed a fellowship at Bellevue Hospital in New York. As a neurosurgeon, he worked at the Kinshasa University Clinic of Lovanium School of Medicine in the DRC, where he introduced neurosurgery and advocated for the construction of the first dedicated neurosurgical operating room. His leadership helped ensure sustainability in the field in the DRC. He died at the age of 48, leaving a void in neurosurgery and an unfulfilled mission of advocating for the construction of an independent neurosurgery hospital in the DRC.

Historical Overview of the Only Neuro-Psycho-Pathology Center in the Democratic Republic of Congo.

The Neuro-Psycho-Pathology Center (NPPC) in the Democratic Republic of Congo is a 450-bed neuropsychiatric clinic that pioneered efforts to synergize various disciplines: neurology, neurosurgery, neuropsychiatry, and psychiatry. It serves the brain and behavioral health needs of Congolese patients, and at its peak, the NPPC was a major domestic neuropsychiatry center that averaged 320 admissions annually. Financial and resources shortages have curtailed its functions at 10% of its real capacity. Our report accounts the NPPC's early vision, and we also highlight the ongoing challenges faced by this institution.

Use of Stereoelectroencephalography Beyond Epilepsy: A Systematic Review.

BACKGROUND: Stereoelectroencephalography (sEEG) is an increasingly popular surgical technique used clinically to study neural circuits involved in medication-refractory epilepsy, and it is concomitantly used in the scientific investigation of neural circuitry underlying behavior. METHODS: Using PRISMA guidelines, the U.S. National Library of Medicine at the National Institutes of Health PubMed database was queried for investigational or therapeutic applications of sEEG in human subjects. Abstracts were analyzed independently by 2 authors for inclusion or exclusion. RESULTS: The study search identified 752 articles, and after exclusion criteria were applied, 8 studies were selected for in-depth review. Among those 8 studies, 122 patients were included, with indications ranging from schizophrenia to Parkinson disease. All the included studies were single-institution case series representing level IV scientific evidence. CONCLUSIONS: sEEG is an important method in epilepsy surgery that could be applied to other neurologic and psychiatric diseases. Information from these studies could provide additional pathophysiologic information and lead to further development and refinement of neuromodulation therapies for such conditions.