AI-based differential diagnosis of dementia etiologies on multimodal data.

Differential diagnosis of dementia remains a challenge in neurology due to symptom overlap across etiologies, yet it is crucial for formulating early, personalized management strategies. Here, we present an AI model that harnesses a broad array of data, including demographics, individual and family medical history, medication use, neuropsychological assessments, functional evaluations, and multimodal neuroimaging, to identify the etiologies contributing to dementia in individuals. The study, drawing on 51,269 participants across 9 independent, geographically diverse datasets, facilitated the identification of 10 distinct dementia etiologies. It aligns diagnoses with similar management strategies, ensuring robust predictions even with incomplete data. Our model achieved a micro-averaged area under the receiver operating characteristic curve (AUROC) of 0.94 in classifying individuals with normal cognition, mild cognitive impairment and dementia. Also, the micro-averaged AUROC was 0.96 in differentiating the dementia etiologies. Our model demonstrated proficiency in addressing mixed dementia cases, with a mean AUROC of 0.78 for two co-occurring pathologies. In a randomly selected subset of 100 cases, the AUROC of neurologist assessments augmented by our AI model exceeded neurologist-only evaluations by 26.25%. Furthermore, our model predictions aligned with biomarker evidence and its associations with different proteinopathies were substantiated through postmortem findings. Our framework has the potential to be integrated as a screening tool for dementia in various clinical settings and drug trials, with promising implications for person-level management.

A Review of the Multi-Systemic Complications of a Ketogenic Diet in Children and Infants with Epilepsy.

Ketogenic diets (KDs) are highly effective in the treatment of epilepsy. However, numerous complications have been reported. During the initiation phase of the diet, common side effects include vomiting, hypoglycemia, metabolic acidosis and refusal of the diet. While on the diet, the side effects involve the following systems: gastrointestinal, hepatic, cardiovascular, renal, dermatological, hematologic and bone. Many of the common side effects can be tackled easily with careful monitoring including blood counts, liver enzymes, renal function tests, urinalysis, vitamin levels, mineral levels, lipid profiles, and serum carnitine levels. Some rare and serious side effects reported in the literature include pancreatitis, protein-losing enteropathy, prolonged QT interval, cardiomyopathy and changes in the basal ganglia. These serious complications may need more advanced work-up and immediate cessation of the diet. With appropriate monitoring and close follow-up to minimize adverse effects, KDs can be effective for patients with intractable epilepsy.

Multimodal deep learning for Alzheimer's disease dementia assessment.

Worldwide, there are nearly 10 million new cases of dementia annually, of which Alzheimer's disease (AD) is the most common. New measures are needed to improve the diagnosis of individuals with cognitive impairment due to various etiologies. Here, we report a deep learning framework that accomplishes multiple diagnostic steps in successive fashion to identify persons with normal cognition (NC), mild cognitive impairment (MCI), AD, and non-AD dementias (nADD). We demonstrate a range of models capable of accepting flexible combinations of routinely collected clinical information, including demographics, medical history, neuropsychological testing, neuroimaging, and functional assessments. We then show that these frameworks compare favorably with the diagnostic accuracy of practicing neurologists and neuroradiologists. Lastly, we apply interpretability methods in computer vision to show that disease-specific patterns detected by our models track distinct patterns of degenerative changes throughout the brain and correspond closely with the presence of neuropathological lesions on autopsy. Our work demonstrates methodologies for validating computational predictions with established standards of medical diagnosis.

Limited-Montage EEG as a Tool for the Detection of Nonconvulsive Seizures.

PURPOSE: Prefabricated arrays with a limited number of electrodes offer an opportunity to hasten the diagnosis of seizures; however, their accuracy to detect seizures is unknown. We examined the utility of two limited-montage EEG setups for the detection of nonconvulsive seizures. METHODS: Thirty previously interpreted EEG segments with nonconvulsive seizures from 30 patients and 60 segments with background slowing or normal EEG from 60 patients were rendered in a bipolar "double banana" montage, a double distance "neonatal" montage, and a circumferential "hatband" montage. Experts reviewed 60 to 180 seconds long segments to determine whether seizures were present and if the EEG data provided were sufficient to make a decision on escalation of clinical care by ordering an additional EEG or prescribing anticonvulsants. The periodic patterns on the ictal-interictal continuum were specifically excluded for this analysis to keep the focus on definite electrographic seizures. RESULTS: The sensitivities for seizure of the neonatal and hatband montages were 0.96 and 0.84, respectively, when compared with full montage EEG, whereas the specificities were 0.94 and 0.98, respectively. Appropriate escalation of care was suggested for 96% and 92% of occurrences of seizure patterns in neonatal and hatband montages, respectively. When compared with clinical EEG, the sensitivities of the neonatal and hatband montages for seizure diagnosis were 0.85 and 0.69, respectively. CONCLUSIONS: Nonconvulsive seizures were detected with high accuracy using the limited electrode array configuration in the neonatal and hatband montages. The sensitivity of the neonatal montage EEG in detecting seizures was superior to that of a hatband montage. These findings suggest that in some patients with nonconvulsive seizures, limited-montage EEG may allow to differentiate ictal and slow patterns.

Three Dimensional Brain Reconstruction Optimizes Surgical Approaches and Medical Education in Minimally Invasive Neurosurgery for Refractory Epilepsy.

Epilepsy is a prevalent condition that affects 1-3% of the population or about 50-65 million people worldwide (WHO estimates) and about 3.5 million people in the USA alone (CDC estimates). Refractory epilepsy refers to patients that respond inadequately to medical management alone (at least two anti-seizure medications at appropriate doses) and are appropriate candidates for other interventions such as brain surgery or the use of neurostimulators for their epilepsy. Minimally invasive techniques like stereotactic EEG electrodes offer excellent investigational abilities to study the diagnostic attributes of the seizure networks, while therapies like laser ablations and neurostimulators permit intervention and modulation of these networks to offer seizure control with minimal cognitive compromise and surgical morbidity. The accuracy of these techniques is highly contingent on precise anatomical correlation between the location of the electrodes and their proximity to relevant structures of the brain. Ensuring good anatomical correlation using 3-dimensional (3D) reconstructions would permit precise localization and accurate understanding of the seizure networks. Accurate localization of stereotactic electrodes would enable precise understanding of the electrical networks and identify vital nodes in the seizure network. These reconstructions would also permit better understanding of the proximity of these electrodes to each other and help confirm arrangement of neurostimulators to maximize modulatory effects on the networks. Such reconstructions would enable better understanding of neuroanatomy and connectivity to improve knowledge of brain structures and relations in neurological conditions. These methods would enable medical students and doctors-in-training to better their understanding of neurological disease and the necessary interventions.

Ambulatory care for epilepsy via telemedicine during the COVID-19 pandemic.

OBJECTIVE: To assess feasibility, patient satisfaction, and financial advantages of telemedicine for epilepsy ambulatory care during the current COVID-19 pandemic. METHODS: The demographic and clinical characteristics of all consecutive patients evaluated via telemedicine at a level 4 epilepsy center between March 20 and April 20, 2020 were obtained retrospectively from electronic medical records. A telephone survey to assess patient satisfaction and preferences was conducted within one month following the initial visit. RESULTS: Among 223 telehealth patients, 85.7% used both synchronous audio and video technology. During the visits, 39% of patients had their anticonvulsants adjusted while 18.8% and 11.2% were referred to laboratory/diagnostic testing and specialty consults, respectively. In a post-visit survey, the highest degree of satisfaction with care was expressed by 76.9% of patients. The degree of satisfaction tended to increase the further a patient lived from the clinic (p = 0.05). Beyond the pandemic, 89% of patients reported a preference for continuing telemedicine if their epilepsy symptoms remained stable, while only 44.4% chose telemedicine should their symptoms worsen. Inclement weather and lack of transportation were factors favoring continued use of telemedicine. An estimated cost saving to patient attributed to telemedicine was $30.20 ±â€¯3.8 per visit. SIGNIFICANCE: Our findings suggest that epilepsy care via telemedicine provided high satisfaction and economic benefit, without compromising patients' quality of care, thereby supporting the use of virtual care during current and future epidemiological fallouts. Beyond the current pandemic, patients with stable seizure symptoms may prefer to use telemedicine for their epilepsy care.

Global brain network dynamics predict therapeutic responsiveness to cannabidiol treatment for refractory epilepsy.

Refractory epilepsy is a chronic brain network disorder characterized by unresponsiveness to multiple (>2) anti-epileptic drugs. Cannabidiol, a non-psychotropic neuroactive substance, is an emerging anti-epileptic treatment that was recently approved by the US Food and Drug Administration for the treatment of refractory epilepsy, especially Lennox Gastaut syndrome and Dravet syndrome. Here, we evaluated associations between global brain network dynamics and related changes and responsiveness to cannabidiol therapy using a combination of electroencephalography phase coherence and graph theoretical analyses. Refractory epilepsy patients with Lennox Gastaut syndrome or Dravet syndrome underwent serial electroencephalography testing prior to and during cannabidiol treatment. Patients showing greater than 70% seizure frequency reduction were classified as treatment responders for the purposes of this study. We calculated inter-electrode electroencephalography phase coherence in delta (1-3 Hz), theta (4-7 Hz), alpha (8-12 Hz) and beta (13-30 Hz) frequency bands. Graph theoretical analysis of brain network dynamics was extracted from phase coherence to evaluate measures of network integration (i.e. characteristic path length, global efficiency and degree) and segregation (i.e. modularity and transitivity). We found that responders, relative to non-responders, showed increased network integration-as indexed by relatively higher global efficiency and lower degree-and increased network segregation-as indexed by relatively higher modularity-exclusively in the beta-frequency band. We also found that larger cannabidiol dosages were associated with increased network integration-as indexed by higher global efficiency with increasing dose-and increased network segregation-as indexed by lower transitivity with increasing dose-in the delta, theta and alpha frequency bands. In summary, we demonstrate novel effects of cannabidiol on brain network dynamics with important implications for the treatment of refractory epilepsy and, possibly, across broader research applications in the future.

ACTION-EHR: Patient-Centric Blockchain-Based Electronic Health Record Data Management for Cancer Care.

BACKGROUND: With increased specialization of health care services and high levels of patient mobility, accessing health care services across multiple hospitals or clinics has become very common for diagnosis and treatment, particularly for patients with chronic diseases such as cancer. With informed knowledge of a patient's history, physicians can make prompt clinical decisions for smarter, safer, and more efficient care. However, due to the privacy and high sensitivity of electronic health records (EHR), most EHR data sharing still happens through fax or mail due to the lack of systematic infrastructure support for secure, trustable health data sharing, which can also cause major delays in patient care. OBJECTIVE: Our goal was to develop a system that will facilitate secure, trustable management, sharing, and aggregation of EHR data. Our patient-centric system allows patients to manage their own health records across multiple hospitals. The system will ensure patient privacy protection and guarantee security with respect to the requirements for health care data management, including the access control policy specified by the patient. METHODS: We propose a permissioned blockchain-based system for EHR data sharing and integration. Each hospital will provide a blockchain node integrated with its own EHR system to form the blockchain network. A web-based interface will be used for patients and doctors to initiate EHR sharing transactions. We take a hybrid data management approach, where only management metadata will be stored on the chain. Actual EHR data, on the other hand, will be encrypted and stored off-chain in Health Insurance Portability and Accountability Act-compliant cloud-based storage. The system uses public key infrastructure-based asymmetric encryption and digital signatures to secure shared EHR data. RESULTS: In collaboration with Stony Brook University Hospital, we developed ACTION-EHR, a system for patient-centric, blockchain-based EHR data sharing and management for patient care, in particular radiation treatment for cancer. The prototype was built on Hyperledger Fabric, an open-source, permissioned blockchain framework. Data sharing transactions were implemented using chaincode and exposed as representational state transfer application programming interfaces used for the web portal for patients and users. The HL7 Fast Healthcare Interoperability Resources standard was adopted to represent shared EHR data, making it easy to interface with hospital EHR systems and integrate a patient's EHR data. We tested the system in a distributed environment at Stony Brook University using deidentified patient data. CONCLUSIONS: We studied and developed the critical technology components to enable patient-centric, blockchain-based EHR sharing to support cancer care. The prototype demonstrated the feasibility of our approach as well as some of the major challenges. The next step will be a pilot study with health care providers in both the United States and Switzerland. Our work provides an exemplar testbed to build next-generation EHR sharing infrastructures.

Efficacy and Safety of a Ketogenic Diet in Children and Adolescents with Refractory Epilepsy-A Review.

Epilepsy in the pediatric and adolescent populations is a devastating condition where individuals are prone to recurrent epileptic seizures or changes in behavior or movement that is the direct result of a primary change in the electrical activity in the brain. Although many children with epilepsy will have seizures controlled with antiseizure medications (ASMs), a large percentage of patients are refractory to drug therapy and may consider initiating a ketogenic diet. The term Ketogenic Diet or Ketogenic Diet Therapy (KDT) refers to any diet therapy in which dietary composition results in a ketogenic state of human metabolism. Currently, there are 4 major Ketogenic diet therapies-the classic ketogenic diet (cKD), the modified Atkins diet (MAD), the medium chain triglyceride ketogenic diet (MCTKD) and the low glycemic index treatment (LGIT). The compositions of the 4 main KDTs differ and limited evidence to distinguish the efficacy among different diets currently exists. Although it is apparent that more randomized controlled trials (RCTs) and long-term studies are needed to evaluate efficacy, side effects and individual response to the diet, it is imperative to study and understand the metabolic profiles of patients with epilepsy in order to isolate which dietary restrictions are necessary to maximize clinical benefit.

Development and validation of an interpretable deep learning framework for Alzheimer's disease classification.

Alzheimer's disease is the primary cause of dementia worldwide, with an increasing morbidity burden that may outstrip diagnosis and management capacity as the population ages. Current methods integrate patient history, neuropsychological testing and MRI to identify likely cases, yet effective practices remain variably applied and lacking in sensitivity and specificity. Here we report an interpretable deep learning strategy that delineates unique Alzheimer's disease signatures from multimodal inputs of MRI, age, gender, and Mini-Mental State Examination score. Our framework linked a fully convolutional network, which constructs high resolution maps of disease probability from local brain structure to a multilayer perceptron and generates precise, intuitive visualization of individual Alzheimer's disease risk en route to accurate diagnosis. The model was trained using clinically diagnosed Alzheimer's disease and cognitively normal subjects from the Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset (n = 417) and validated on three independent cohorts: the Australian Imaging, Biomarker and Lifestyle Flagship Study of Ageing (AIBL) (n = 382), the Framingham Heart Study (n = 102), and the National Alzheimer's Coordinating Center (NACC) (n = 582). Performance of the model that used the multimodal inputs was consistent across datasets, with mean area under curve values of 0.996, 0.974, 0.876 and 0.954 for the ADNI study, AIBL, Framingham Heart Study and NACC datasets, respectively. Moreover, our approach exceeded the diagnostic performance of a multi-institutional team of practicing neurologists (n = 11), and high-risk cerebral regions predicted by the model closely tracked post-mortem histopathological findings. This framework provides a clinically adaptable strategy for using routinely available imaging techniques such as MRI to generate nuanced neuroimaging signatures for Alzheimer's disease diagnosis, as well as a generalizable approach for linking deep learning to pathophysiological processes in human disease.

Epilepsy in spinocerebellar ataxia type 8: a case report.

BACKGROUND: Spinocerebellar ataxia type 8 is an uncommon genetic condition and presents with gait disturbances, ataxia, dysarthria, nystagmus, and cognitive and psychiatric abnormalities. Seizures are extremely uncommon in the spinocerebellar ataxias and have been reported only once before in a patient with spinocerebellar ataxia type 8. This case report highlights the need to evaluate spells in patients with a known neurodegenerative or genetic disease to exclude seizures, and it stresses the importance of timely diagnosis and therapy. CASE PRESENTATION: The patient was a 22-year-old Caucasian woman with known spinocerebellar ataxia 8 since age 10 years. She was admitted to our hospital with new-onset left hemiparesis and encephalopathy in addition to chronic occurrence of multiple spells of confusion and oromanual automatisms with postictal lethargy. Testing confirmed that she was having recurrent seizures with episodes of nonconvulsive status epilepticus. Urgent treatment with antiepileptic therapy was initiated; her seizures resolved shortly thereafter, and her mental status improved. Her left hemiparesis has improved; she remains seizure-free; and she has returned to her baseline antiepileptic medications following physical therapy. CONCLUSIONS: Seizures have been reported extremely rarely in association with spinocerebellar ataxia 8, but they must be considered in the differential diagnosis of patients with spells of altered awareness, especially in those with a known neurodegenerative or genetic condition. Clinicoradiological correlation with symptoms can help expedite diagnosis and treatment. Expert consultation with epileptologists at the earliest signs can help establish the diagnosis quickly, minimize morbidity, and enhance recovery.

Migraine and vertigo.

Vertigo and migraine are commonly co-occurring problems. The diagnostic criteria for vestibular migraine have recently been updated in the International Classification of Headache Disorders, 3rd edition (beta version), which allow better detection of this under-recognized condition. In many cases, a diagnosis of vestibular migraine will be established based on a typical history of concurrent migraine headache, photophobia, and/or migraine aura with the vertigo. Certain mimickers, such as Ménière's disease, likely exist on a pathophysiologic continuum with vestibular migraine. In our review, we provide an update on the salient literature regarding the diagnosis and management of this condition.

Refractory anaplastic astrocytoma responsive to PCV in combination with bevacizumab.

We present a patient with anaplastic astrocytoma who had recurrent disease after treatment with surgery, radiation, procarbazine, lomustine (CCNU) and vincristine (PCV) over one year followed by poor response to second line treatment with temozolomide, irinotecan with bevacizumab, Novocure TTF therapy successively over a four year period after her initial treatment who then responded to PCV in combination with bevacizumab as third line therapy. This is the first report demonstrating benefit of concurrent PCV and bevacizumab treatment in a highly treatment refractory tumor.

Nutrition and prevention of Alzheimer's dementia.

A nutritional approach to prevent, slow, or halt the progression of disease is a promising strategy that has been widely investigated. Much epidemiologic data suggests that nutritional intake may influence the development and progression of Alzheimer's dementia (AD). Modifiable, environmental causes of AD include potential metabolic derangements caused by dietary insufficiency and or excess that may be corrected by nutritional supplementation and or dietary modification. Many nutritional supplements contain a myriad of health promoting constituents (anti-oxidants, vitamins, trace minerals, flavonoids, lipids, …etc.) that may have novel mechanisms of action affecting cellular health and regeneration, the aging process itself, or may specifically disrupt pathogenic pathways in the development of AD. Nutritional modifications have the advantage of being cost effective, easy to implement, socially acceptable and generally safe and devoid of significant adverse events in most cases. Many nutritional interventions have been studied and continue to be evaluated in hopes of finding a successful agent, combination of agents, or dietary modifications that can be used for the prevention and or treatment of AD. The current review focuses on several key nutritional compounds and dietary modifications that have been studied in humans, and further discusses the rationale underlying their potential utility for the prevention and treatment of AD.

Anomalous coronary circulation: left anterior descending and left circumflex coronary arteries arising from the right sinus of valsalva.

Approximately 1% of adults who undergo cardiac catheterization have coronary anomalies. Patients may present with chest pain, arrhythmias, presyncope, and sometimes sudden cardiac death. Multidetector computed tomography (MDCT) is an excellent tool for identifying coronary artery anomalies and defining their course and relationship to the great vessels and surrounding structures; its value is incremental to conventional angiography. We present a rare case of a coronary anomaly involving three separate ostia at the right sinus of Valsalva for the left and right coronary vessels.

Assessment of dose proportionality of muraglitazar after repeated oral dosing in rats via a sparse sampling methodology.

Muraglitazar is an alpha/gamma-dual peroxisome proliferator-activated receptor (PPAR) agonist. This study evaluated the single- and multiple-dose oral toxicokinetics of muraglitazar in rats at doses of 3, 30 and 300 mg/kg/day. In total, 15 rats/gender/dose group received muraglitazar every day for 1 month. On both day 1 and day 28, blood samples were obtained at 0.5, 2, 4, 6, 8 and 24 h post-dose, followed by LC/MS analysis. In order to minimize blood loss in the rats, a sparse sampling approach was used to delineate the toxicokinetics. The peak plasma concentration (C(max)) and area under the plasma concentration-time curve (TAUC(0-t)) values for muraglitazar increased in a proportion less than the increment in dose. As the dose increased in the ratio 1:10:100, the C(max) for muraglitazar in male and female rats increased in the ratio of 1:10.3:58.6 and 1:15.3:75.3 on day 1, and 1:5.9:28.1 and 1:13.3:37.3 on day 28, respectively. The corresponding TAUC(0-t) values for males and females were in the ratio of 1:10.2:131 and 1:12.4:131 on day 1, and 1:9.5:93.4 and 1:11.8:94.3 on day 28, respectively. The results indicate that muraglitazar exhibits a dose dependent toxicokinetics in rats and the systemic exposure of muraglitazar was decreased on day 28 compared with day 1.

Structural elucidation of human oxidative metabolites of muraglitazar: use of microbial bioreactors in the biosynthesis of metabolite standards.

Muraglitazar (Pargluva), a dual alpha/gamma peroxisome proliferator-activated receptor activator, is currently in clinical development for treatment of type 2 diabetes. This study describes the structural elucidation of the human oxidative metabolites of muraglitazar through the use of a combination of microbial bioreactors, NMR and accurate mass analyses, and organic synthesis. Plasma, urine, and feces were collected from six healthy subjects following oral administration of 14C-labeled muraglitazar (10 mg, 100 microCi) and pooled samples were analyzed. Approximately 96% of the recovered radioactive dose was found in the feces and 3.5% in the urine. The parent compound represented >85% of the radioactivity in plasma. The fecal radioactivity was distributed among 16 metabolites (M1-M12, M14-M16, and M8a) and the parent drug, of which hydroxylation and O-demethylation metabolites (M5, M10, M11, M14, and M15) represented the prominent human metabolites. The urinary radioactivity was distributed into several peaks including muraglitazar glucuronide (M13) and the parent drug. Low concentrations of metabolites in human samples prevented direct identification of metabolites beyond liquid chromatographic (LC)-mass spectrometric analysis. Microbial strains Cunninghamella elegans and Saccharopolyspora hirsuta produced muraglitazar metabolites that had the same high performance liquid chromatography retention times and the same tandem mass spectrometric (MS/MS) properties as the corresponding human metabolites. The microbial metabolites M9, M10, M11, M14, M15, and M16 were isolated and analyzed by NMR. Based on these LC-MS/MS and NMR analyses, and organic synthesis, the structures of 16 human oxidative metabolites were identified. The oxidative metabolism of muraglitazar was characterized by hydroxylation, O-demethylation, oxazolering opening, and O-demethylation/hydroxylation, as well as O-dealkylation and carboxylic acid formation. This study demonstrated the utility of microbial bioreactors for the identification of metabolites.

Glucuronidation as a major metabolic clearance pathway of 14c-labeled muraglitazar in humans: metabolic profiles in subjects with or without bile collection.

The metabolism and disposition of 14C-labeled muraglitazar (Pargluva), a novel dual alpha/gamma peroxisome proliferator-activated receptor activator, was investigated in eight healthy male subjects with and without bile collection (groups 1 and 2) after a single 20-mg oral dose. Bile samples were collected for 3 to 8 h after dosing from group 2 subjects in addition to the urine and feces collection. In plasma, the parent compound was the major component, and circulating metabolites, including several glucuronide conjugates, were minor components at all time points. The exposure to parent drug (Cmax and area under the plasma concentration versus time curve) in subjects with bile collection was generally lower than that in subjects without bile collection. The major portion of the radioactive dose was recovered in feces (91% for group 1 and 51% for group 2). In addition, 40% of the dose was recovered in the bile from group 2 subjects. In this 3- to 8-h bile, the glucuronide of muraglitazar (M13, 15% of dose) and the glucuronides of its oxidative metabolites (M17a,b,c, M18a,b,c, and M20, together, 16% of dose) accounted for approximately 80% of the biliary radioactivity; muraglitazar and its O-demethylated metabolite (M15) each accounted for approximately 4% of the dose. In contrast, fecal samples only contained muraglitazar and its oxidative metabolites, suggesting hydrolysis of biliary glucuronides in the intestine before fecal excretion. Thus, the subjects with and without bile collection showed different metabolic profiles of muraglitazar after oral administration, and glucuronidation was not observed as a major pathway of metabolic clearance from subjects with the conventional urine and fecal collection, but was found as a major elimination pathway from subjects with bile collection.