Feasibility of spirography features for objective assessment of motor function in Parkinson's disease.

OBJECTIVE: Parkinson's disease (PD) is currently incurable, however proper treatment can ease the symptoms and significantly improve the quality of life of patients. Since PD is a chronic disease, its efficient monitoring and management is very important. The objective of this paper was to investigate the feasibility of using the features and methodology of a spirography application, originally designed to detect early Parkinson's disease (PD) motoric symptoms, for automatically assessing motor symptoms of advanced PD patients experiencing motor fluctuations. More specifically, the aim was to objectively assess motor symptoms related to bradykinesias (slowness of movements occurring as a result of under-medication) and dyskinesias (involuntary movements occurring as a result of over-medication). MATERIALS AND METHODS: This work combined spirography data and clinical assessments from a longitudinal clinical study in Sweden with the features and pre-processing methodology of a Slovenian spirography application. The study involved 65 advanced PD patients and over 30,000 spiral-drawing measurements over the course of three years. Machine learning methods were used to learn to predict the "cause" (bradykinesia or dyskinesia) of upper limb motor dysfunctions as assessed by a clinician who observed animated spirals in a web interface. The classification model was also tested for comprehensibility. For this purpose a visualisation technique was used to present visual clues to clinicians as to which parts of the spiral drawing (or its animation) are important for the given classification. RESULTS: Using the machine learning methods with feature descriptions and pre-processing from the Slovenian application resulted in 86% classification accuracy and over 0.90 AUC. The clinicians also rated the computer's visual explanations of its classifications as at least meaningful if not necessarily helpful in over 90% of the cases. CONCLUSIONS: The relatively high classification accuracy and AUC demonstrates the usefulness of this approach for objective monitoring of PD patients. The positive evaluation of computer's explanations suggests the potential use of this methodology in a decision support setting.

Automatic Spiral Analysis for Objective Assessment of Motor Symptoms in Parkinson's Disease.

A challenge for the clinical management of advanced Parkinson's disease (PD) patients is the emergence of fluctuations in motor performance, which represents a significant source of disability during activities of daily living of the patients. There is a lack of objective measurement of treatment effects for in-clinic and at-home use that can provide an overview of the treatment response. The objective of this paper was to develop a method for objective quantification of advanced PD motor symptoms related to off episodes and peak dose dyskinesia, using spiral data gathered by a touch screen telemetry device. More specifically, the aim was to objectively characterize motor symptoms (bradykinesia and dyskinesia), to help in automating the process of visual interpretation of movement anomalies in spirals as rated by movement disorder specialists. Digitized upper limb movement data of 65 advanced PD patients and 10 healthy (HE) subjects were recorded as they performed spiral drawing tasks on a touch screen device in their home environment settings. Several spatiotemporal features were extracted from the time series and used as inputs to machine learning methods. The methods were validated against ratings on animated spirals scored by four movement disorder specialists who visually assessed a set of kinematic features and the motor symptom. The ability of the method to discriminate between PD patients and HE subjects and the test-retest reliability of the computed scores were also evaluated. Computed scores correlated well with mean visual ratings of individual kinematic features. The best performing classifier (Multilayer Perceptron) classified the motor symptom (bradykinesia or dyskinesia) with an accuracy of 84% and area under the receiver operating characteristics curve of 0.86 in relation to visual classifications of the raters. In addition, the method provided high discriminating power when distinguishing between PD patients and HE subjects as well as had good test-retest reliability. This study demonstrated the potential of using digital spiral analysis for objective quantification of PD-specific and/or treatment-induced motor symptoms.

Elicitation of neurological knowledge with argument-based machine learning.

OBJECTIVE: The paper describes the use of expert's knowledge in practice and the efficiency of a recently developed technique called argument-based machine learning (ABML) in the knowledge elicitation process. We are developing a neurological decision support system to help the neurologists differentiate between three types of tremors: Parkinsonian, essential, and mixed tremor (comorbidity). The system is intended to act as a second opinion for the neurologists, and most importantly to help them reduce the number of patients in the "gray area" that require a very costly further examination (DaTSCAN). We strive to elicit comprehensible and medically meaningful knowledge in such a way that it does not come at the cost of diagnostic accuracy. MATERIALS AND METHODS: To alleviate the difficult problem of knowledge elicitation from data and domain experts, we used ABML. ABML guides the expert to explain critical special cases which cannot be handled automatically by machine learning. This very efficiently reduces the expert's workload, and combines expert's knowledge with learning data. 122 patients were enrolled into the study. RESULTS: The classification accuracy of the final model was 91%. Equally important, the initial and the final models were also evaluated for their comprehensibility by the neurologists. All 13 rules of the final model were deemed as appropriate to be able to support its decisions with good explanations. CONCLUSION: The paper demonstrates ABML's advantage in combining machine learning and expert knowledge. The accuracy of the system is very high with respect to the current state-of-the-art in clinical practice, and the system's knowledge base is assessed to be very consistent from a medical point of view. This opens up the possibility to use the system also as a teaching tool.

European regulation on orphan medicinal products: 10 years of experience and future perspectives.

In 2000, regulation on orphan medicinal products was adopted in the European Union with the aim of benefiting patients who suffer from serious, rare conditions for which there is currently no satisfactory treatment. Since then, more than 850 orphan drug designations have been granted by the European Commission based on a positive opinion from the Committee for Orphan Medicinal Products (COMP), and more than 60 orphan drugs have received marketing authorization in Europe. Here, stimulated by the tenth anniversary of the COMP, we reflect on the outcomes and experience gained in the past decade, and contemplate issues for the future, such as catalysing drug development for the large number of rare diseases that still lack effective treatments.

Potential drug-drug interactions and admissions due to drug-drug interactions in patients treated in medical departments.

PURPOSE: Adverse drug reactions due to drug-drug interactions (DDIs) are important in drug safety. The aim of this study was to check potential DDIs (pDDIs) on hospital admission and discharge and to evaluate admissions due to DDIs in medical departments of a primary city and tertiary referral hospital. METHODS: Age, sex, presence of renal and liver failure, drug information, diagnosis, and urgency and reason for admission were retrospectively recorded in 520 randomly selected patients in medical departments of the University Medical Center Ljubljana. The screening program Drug-Reax was used to check for pDDIs in patients with drug information on both admission and discharge home, and the proportion of patients admitted as the consequence of a DDI was estimated. RESULTS: Overall, 14.6% (76/520) of patients had incomplete information on drug names in their medical documentation on admission; at the end of treatment 12.5% (52/416) of patients were discharged home with incomplete information on drug names in their discharge letters. A total of 323 patients had complete information on drug names on both admission and discharge and were included in the analysis of pDDIs: 51% (166/323) of patients on admission and 63% (204/323) on discharge had at least one pDDI (P = 0.001). Major pDDIs were found in 13% (41/323) of patients on admission and 18% (59/323) on discharge (P = 0.001). An ACE inhibitor combined with spironolactone was the most common major pDDI, representing 20.0% of all pDDIs on admission and 25.6% on discharge. Among patients with pDDI on admission, 2.4% (4/166) of were admitted because of an ADR caused by a DDI. Overall, 1.2% (4/323) of patients were admitted as the consequence of a DDI. CONCLUSIONS: The information on patient medication on hospital admission and discharge is incomplete. Half of patients on admission and almost two-thirds on discharge had pDDIs. ADRs due to DDIs caused 1.2% of admissions to medical departments in Ljubljana's primary city and tertiary referral hospital.

The frequency of adverse drug reaction related admissions according to method of detection, admission urgency and medical department specialty.

BACKGROUND: Adverse Drug Reactions (ADRs) have been regarded as a major public health problem since they represent a sizable percentage of admissions. Unfortunately, there is a wide variation of ADR related admissions among different studies. The aim of this study was to evaluate the frequency of ADR related admissions and its dependency on reporting and method of detection, urgency of admissions and included medical departments reflecting department/hospital type within one study. METHODS: The study team of internal medicine specialists retrospectively reviewed 520 randomly selected medical records (3%) of patients treated in the medical departments of the primary city and tertiary referral governmental hospital for certain ADRs causing admissions regarding WHO causality criteria. All medical records were checked for whether the treating physicians recognised and documented ADRs causing admissions. The hospital information system was checked to ensure ADR related diagnoses were properly coded and the database of a national spontaneous reporting system was searched for patients with ADRs included in this study. RESULTS: The established frequency of admissions due to certain ADRs recognised by the study team and documented in medical records by the treating physicians was the same and represented 5.8% of all patients (30/520). The frequency of ADR causing admissions detected by employing a computer-assisted approach using an ICD-10 coding system was 0.2% (1/520), and no patient admitted due to ADRs was reported to the national reporting system (0/520). The recognized frequency of ADR related admissions also depends on the department's specialty (p = 0.001) and acceptance of urgently admitted patients (p = 0.001). Patients admitted due to ADRs were significantly older compared to patients without ADRs (p = 0.025). Gastrointestinal bleeding due to NSAID, acetylsalicylic acid and warfarin was the most common ADR that resulted in admission and represented 40% of all certain ADRs (12/30) according to WHO causality criteria. CONCLUSION: ADRs cause 5.8% of admissions in medical departments in the primary city and tertiary referral hospital. The physicians recognise certain ADR related admissions according to WHO causality criteria and note them in medical records, but they rarely code and report ADRs. The established frequency of ADR related admissions depends on the detection method, department specialty and frequency of urgently admitted patients.

Urinary serotonin level is associated with serotonin syndrome after moclobemide, sertraline, and citalopram overdose.

INTRODUCTION: Altered mental status, autonomic dysfunction, and neuromuscular abnormalities are a characteristic triad of serotonin syndrome. No laboratory tests confirm the diagnosis of serotonin syndrome. CASE REPORT: A 35-year-old woman took moclobemide, sertraline, and citalopram in a suicide attempt. She was conscious with mild tachycardia, hypertension, and tachypnea one hour after ingestion. In the second hour after ingestion diaphoresis, mydriasis, horizontal nystagmus, trismus, hyperreflexia, clonus, and tremor appeared. She became agitated and unresponsive. In the third hour after ingestion she became comatose and hyperthermic. She was anesthetized, paralyzed, intubated, and ventilated for 24 hours. Serum moclobemide, sertraline, and citalopram levels were above therapeutic levels. The serum serotonin level was within normal limits and the urinary 5-hydroxyindoleacetic acid:creatinine ratio was below the average daily value. The urinary serotonin:creatinine ratio was increased on arrival (1 mg/g). DISCUSSION AND CONCLUSION: The urinary serotonin level is increased in serotonin syndrome due to a monoamine oxidase inhibitor and selective serotonin-reuptake inhibitors overdose. It is possible that urinary serotonin concentration could be used as a biochemical marker of serotonin syndrome.

Predictive model for estimating risk of crush syndrome: a data mining approach.

BACKGROUND: There is no standard triage method for earthquake victims with crush injuries because of a scarcity of epidemiologic and quantitative data. We conducted a retrospective cohort study to develop predictive models based on clinical data for crush injury in the Kobe earthquake. METHODS: The medical records of 372 patients with crush injuries from the Kobe earthquake were retrospectively analyzed. Twenty-one risk factors were assessed with logistic regression analysis for three outcomes relating to crush syndrome. Two types of predictive triage models--initial evaluation in the field and secondary assessment at the hospital--were developed using logistic regression analysis. Classification accuracy, Brier score and area under the receiver operating characteristic curve (AUC) were used to evaluate the model. RESULTS: The initial triage model, which includes pulse rate, delayed rescue, and abnormal urine color, has an AUC of 0.73. The secondary model, which includes WBC, tachycardia, abnormal urine color, and hyperkalemia, shows an AUC of 0.76. CONCLUSIONS: These triage models may be especially useful to nondisaster experts for distinguishing earthquake victims at high risk of severe crush syndrome from those at lower risk. Application of the model may allow relief workers to better utilize limited medical and transportation resources in the aftermath of a disaster.

Prolonged psychosis after Amanita muscaria ingestion.

Amanita muscaria has a bright red or orange cap covered with small white plaques. It contains the isoxazole derivatives ibotenic acid, muscimol and muscazone and other toxins such as muscarine. The duration of clinical manifestations after A. muscaria ingestion does not usually exceed 24 hours; we report on a 5-day paranoid psychosis after A. muscaria ingestion. A 48-year-old man, with no previous medical history, gathered and ate mushrooms he presumed to be A. caesarea. Half an hour later he started to vomit and fell asleep. He was found comatose having a seizure-like episode. On admission four hours after ingestion he was comatose, but the remaining physical and neurological examinations were unremarkable. Creatine kinase was 8.33 microkat/l. Other laboratory results and brain CT scan were normal. Toxicology analysis did not find any drugs in his blood or urine. The mycologist identified A. muscaria among the remaining mushrooms. The patient was given activated charcoal. Ten hours after ingestion, he awoke and was completely orientated; 18 hours after ingestion his condition deteriorated again and he became confused and uncooperative. Afterwards paranoid psychosis with visual and auditory hallucinations appeared and persisted for five days. On the sixth day all symptoms of psychosis gradually disappeared. One year later he is not undergoing any therapy and has no symptoms of psychiatric disease. We conclude that paranoid psychosis with visual and auditory hallucinations can appear 18 hours after ingestion of A. muscaria and can last for up to five days.

Prolonged hypoglycaemia after insulin lispro overdose.

Insulin lispro has a more rapid onset and a shorter duration of hypoglycaemic action than regular insulin. We report a 39-year-old woman, with no previous medical history, who injected 300 U of the insulin lispro (Humalog) in an attempted suicide. Half an hour later, she was found comatose and brought to our emergency department. On arrival, she was comatose, with capillary glucose of 0.4 mmol/L. She awoke after a 50 ml intravenous bolus of 50% glucose. A continuous infusion of 10% glucose was started. Intermittent hypoglycaemia with neurological signs requiring treatment with 50% glucose was recorded three times during subsequent hospitalization, the last episode being 11 h after insulin injection. The plasma insulin level 4 h after injection was 1465 mU/L, and 18 h after injection was 11 mU/L. Hypoglycaemia after an insulin lispro overdose may last for more than 11 h. Repeated hypoglycaemia after an insulin overdose could be avoided with a glucose infusion rate equivalent to the maximal glucose disposal rate.

Prognostic value of S100B protein in carbon monoxide-poisoned rats.

OBJECTIVE: To assess the possible role of S100B, a structural protein of astroglial cells, as a biochemical marker in acute carbon monoxide-poisoned rats and to compare its prognostic value with consciousness level, which is one of the major parameters for treatment decision in acute carbon monoxide poisoning. DESIGN: Nonrandomized, controlled interventional trial. SETTING: University laboratory. SUBJECTS: Male Wistar rats weighing 263 +/- 18 g. INTERVENTIONS: The rats were exposed to a mixture of 3000 ppm carbon monoxide in air for 60 mins (group 1) and a mixture of 5000 ppm carbon monoxide in air for 30 mins (group 2). Blood samples were taken from the jugular vein just before and immediately after the carbon monoxide poisoning. The level of consciousness was evaluated at the end of the exposure, and the survival rate was monitored for 7 days. The S100B concentrations were measured with a commercial immunoluminometric assay. MEASUREMENTS AND MAIN RESULTS: In the first group, the unconscious rats after carbon monoxide exposure had significantly higher S100B levels compared with the rats without loss of consciousness. In the second group, the unconscious rats that later died had significantly higher S100B levels compared with the unconscious rats that survived. The S100B levels of all conscious and unconscious surviving rats were not significantly different. The serum level of S100B below 0.44 microg/L predicted survival of carbon monoxide-poisoned rats, with a sensitivity of 100% and a specificity of 86%. CONCLUSIONS: Acute carbon monoxide poisoning is associated with elevated S100B levels. S100B is a better predictor of final outcome than the consciousness level, so it could be used as a prognostic parameter for acute carbon monoxide poisoning in rats.

Polydipsia as another mechanism of hyponatremia after 'ecstasy' (3,4 methyldioxymethamphetamine) ingestion.

Acute symptomatic hyponatremia after ecstasy (3,4 methyldioxymethamphetamine; MDMA) ingestion is well documented and has been attributed to the syndrome of inappropriate antidiuretic hormone (SIADH). We report the case of an 18-year-old woman who took five tablets of ecstasy in a suicide attempt and drank 1700 ml water at the Emergency Department (ED). The laboratory findings obtained 5 h after ingestion showed a serum sodium concentration of 130 mmol/l, plasma osmolality of 264 mOsm/kg, urinary osmolality of 335 mOsm/kg and natriuresis of 101 mmol/l. The plasma arginine vasopressin level by radioimmunoassay was 33.7 pmol/l 5 h after ingestion. A gas chromatography-mass spectrometry assay confirmed MDMA in blood samples, with serum concentrations of 0.87 mg/l on arrival. This case report strongly suggests that MDMA reduces serum sodium levels through the dual pathways of SIADH and polydipsia. Accordingly, we believe that hyponatremia may be prevented in ED patients after MDMA ingestion by the early restriction of water intake.

S100B protein in carbon monoxide poisoning: a pilot study.

Carbon monoxide (CO) poisoning is the most common form of lethal poisoning. The aim of this prospective clinical study was to assess the possible role of S100B, the structural protein in the astroglia, as a biochemical marker of brain injury in carbon monoxide poisoning. Serum S100B determination was performed in 38 consecutive patients poisoned by carbon monoxide who were admitted to the Emergency Department (ED) in Ljubljana. All three unconscious patients had elevated S100B levels. The patient with the highest S100B died. S100B was elevated in two of the six patients with initial transitory unconsciousness at the scene. All 29 patients without loss of consciousness had normal S100B levels. Carbon monoxide poisoning appears to be associated with elevated S100B levels.

Acute poisoning with autumn crocus (Colchicum autumnale L.).

INTRODUCTION: Colchicum autumnale, commonly known as the autumn crocus or meadow saffron, contains the antimitotic colchicine, which binds to tubulin and prevents it forming microtubules that are part of the cytoskeleton in all cells. CASE REPORT: A 71-year-old woman ate a plant she thought to be wild garlic (Allium ursinum). Ten hours later she arrived at the emergency department complaining of nausea, vomiting and watery diarrhea. Ingestion of a poisonous plant was suspected and she was treated with gastric lavage, oral activated charcoal and an infusion of normal saline. Toxicology analysis with gas chromatography and mass spectrometry revealed colchicine in the patient's gastric lavage, blood (5 microg/l) and urine (30 microg/l). She developed arrhythmias, liver failure, pancreatitis, ileus, and bone marrow suppression with pancytopenia. Alopecia began in the third week. Treatment was supportive only. Five months later she had no clinical or laboratory signs of poisoning. DISCUSSION: The patient mistakenly ingested autumn crocus instead of wild garlic because of their great similarity. Colchicine primarily blocks mitosis in tissues with rapid cell turnover; this results in gastroenterocolitis in the first phase of colchicine poisoning, bone marrow hypoplasia with pancytopenia in the second and alopecia in the third, all of which were present in our patient. Colchicine toxicity in tissues without rapid cell turnover caused arrhythmias, acute liver failure and pancreatitis. CONCLUSION: Colchicine poisoning can result in gastroenterocolitis followed by multi-organ dysfunction syndrome. In unexplained gastroenterocolitis after ingestion of wild plants as a salad or spice, especially when wild garlic is mentioned, we should always consider autumn crocus. Diagnosis could be confirmed only by toxicology analyses. Management of colchicine poisoning is restricted to supportive therapy.

Case report: fatal poisoning with Colchicum autumnale.

INTRODUCTION: Colchicum autumnale, commonly known as the autumn crocus, contains alkaloid colchicine with antimitotic properties. CASE REPORT: A 76-year-old man with a history of alcoholic liver disease and renal insufficiency, who mistakenly ingested Colchicum autumnale instead of wild garlic (Aliium ursinum), presented with nausea, vomiting and diarrhea 12 hours after ingestion. On admission the patient had laboratory signs of dehydration. On the second day the patient became somnolent and developed respiratory insufficiency. The echocardiogram showed heart dilatation with diffuse hypokinesia with positive troponin I. The respiratory insufficiency was further deteriorated by pneumonia, confirmed by chest X-ray and later on by autopsy. Laboratory tests also revealed rhabdomyolysis, coagulopathy and deterioration of renal function and hepatic function. The toxicological analysis disclosed colchicine in the patient's urine (6 microgram/l) and serum (9 microgram/l) on the second day. Therapy was supportive with hydration, vasopressors, mechanical ventilation and antibiotics. On the third day the patient died due to asystolic cardiac arrest. DISCUSSION AND CONCLUSION: Colchicine poisoning should be considered in patients with gastroenterocolitis after a meal of wild plants. Management includes only intensive support therapy. A more severe clinical presentation should be expected in patients with pre-existing liver and renal diseases. The main reasons for death are cardiovascular collapse, respiratory failure and leukopenia with infection.

The potential value of the protein S-100B level as a criterion for hyperbaric oxygen treatment and prognostic marker in carbon monoxide poisoned patients.

Carbon monoxide (CO) poisoning resulting in diffuse tissue hypoxia. Cerebral hypoxia is a major cause of morbidity and mortality after CO poisoning. There are some clinical criteria that could help a physician to make a decision concerning the application of hyperbaric oxygenation therapy. However, it would be convenient to discover an objective biochemical serum marker that could help in the grade evaluation of CO poisoning and indication of therapy in CO-poisoned patients. We present two case reports where the established criteria for the CO poisoning were not optimum for the decision regarding therapy. It seems that the S-100B protein could be used as a biochemical marker of CO induced brain injury. S-100B values could perhaps help us to select patients for hyperbaric oxygen therapy and to predict the short and long term outcome.