Symptom Frequencies and Correlations with Temperature Variations in Suspected Cases of Neuroleptic Malignant Syndrome (NMS)

Background: The incidence of NMS is rare. Relative frequencies of symptoms that are most valuable in making a diagnosis of NMS can be assessed statistically only if a large sample of suspected NMS cases is available. Similarly, the relationship of such NMS symptoms to temperature (a cardinal symptom of NMS) can be meaningfully evaluated only by studying large samples. Method: De-identified archival data on 212 suspected NMS cases were obtained from professionals across the USA and Canada or were extracted from studies published in medical journals. We recorded the symptoms frequencies. The patients’ temperature ranged from 37.20C to 43.00C, with the mean at 39.50 (SD=1.3). All cases were caused by older first-generation antipsychotics (FGAs). We evaluated the frequencies of symptoms reported in these cases. These included symptoms in the realm of mental status, rigidity, and autonomic symptoms. We calculated the frequency of abnormal blood pressure, respiration and heart rate, symptoms such as Dysarthria, Dysphagia, Rigidity, Focal Dystonia, Waxy Flexibility, Myoclonus, Masked Facies, Bradykinesia, Akinesia, Cogwheeling, Stupor, Coma, Obtundation, Mutism, Decrease in Consciousness, Disorientation, Diaphoresis, Sialorrhea, and Seizures. We also calculated their correlations with temperature elevations, the most spectacular symptom of this dangerous syndrome. Results: The highest symptom frequencies (those > 10%) were found for Rigidity (91.0% of patients), Autonomic Instability (66.5%), Diaphoresis (45.8%), Mutism (34.4%), Tremor (31.6%), Stupor (20.3%), Confusion (15.6%), Incontinence (15.6%), Sialorrhea (14.6%), Coma (13.2%), and Dysphagia (11.3%). Other symptoms were too rare within the sample of the 212 suspected NMS cases to calculate the statistical significances of their relationships to temperature. The only significant correlations found of temperature were to increased heart rate and to the severe cases of coma. Discussion and Conclusion: Besides the elevated temperature, the most frequently reported symptoms in this sample of suspected NMS caused by FGAs were Rigidity, Autonomic Instability, Diaphoresis, Mutism, and Tremor. Higher temperature was associated with tachycardia as well as profound impairment of consciousness or coma. Reviews and database studies of second generation antipsychotics (SGAs), also referred to as atypical antipsychotics, suggest a lower incidence of NMS and milder severity of symptoms such as hyperthermia and rigidity. It would be of clinical interest to generate similar de-identified files of archival data for suspected cases of NMS in patients treated with SGAs. Furthermore, a similar profile derived from archival data on milder or prodromal NMS cases could enhance our understanding of this syndrome from a spectrum perspective.

Assessment of severity of masked facies in Parkinson’s disease by automated facial expression analysis (Preprint)

BACKGROUND Neurodegenerative diseases such as Parkinson’s Disease (PD) produce a gradual generalized loss of motor functions including the ability to contract facial muscles during spontaneous and voluntary emotional expressions, and voluntary non-emotional facial movements. This reduced ability leads to a loss of facial expressiveness which generates a signature “mask-like” appearance of the disease also known as hypomimia. OBJECTIVE We show that modern computer vision techniques can be applied to detect masked facies and quantify medication states in PD. METHODS We collected clinical interviews of PD patients in their ON and OFF motor states, as well as journalistic interviews of the actor Alan Alda obtained before and after he was diagnosed with PD. We trained a convolutional neural network on hundreds of thousand facial images extracted from videos of self-identified persons with PD, along with videos of controls, in order to detect PD-specific facial cues. This learned model was applied to (a) ON/OFF clinical interviews, and (b) pre/post-diagnosis Alan Alda interviews RESULTS The accuracy of the video-based model to separately classify ON vs. OFF states in the clinical samples was 63%, in contrast to an accuracy of 46% when using clinical rater scores for facial PD symptoms. Additionally, Alan Alda’s interviews were successfully classified as occurring before versus after his diagnosis with 100% accuracy CONCLUSIONS This work demonstrates that automated facial expression analysis may be a promising adjunctive screening tool for PD masked facies and for following a patient’s motor state.