Epidemiology and management of bleeding in patients using vitamin K antagonists

Development and validation of a mobile application based on a machine learning model to aid in predicting dosage of vitamin K antagonists among Indian patients post mechanical heart valve replacement

Patients who undergo heart valve replacements with mechanical valves need to take Vitamin K Antagonists (VKA) drugs (Warfarin, Nicoumalone) which has got a very narrow therapeutic range and needs very close monitoring using PT-INR. Accessibility to physicians to titrate drugs doses is a major problem in low-middle income countries (LMIC) like India. Our work was aimed at predicting the maintenance dosage of these drugs, using the de-identified medical data collected from patients attending an INR Clinic in South India. We used artificial intelligence (AI) - machine learning to develop the algorithm. A Support Vector Machine (SVM) regression model was built to predict the maintenance dosage of warfarin, who have stable INR values between 2.0 and 4.0. We developed a simple user friendly android mobile application for patients to use the algorithm to predict the doses. The algorithm generated drug doses in 1100 patients were compared to cardiologist prescribed doses and found to have an excellent correlation.

Unusual localization of bleeding under acenocoumarol: Spinal subdural hematoma

•

The spinal subdural hematoma is a rare situation which should be evoked in any patient treated by vitamin K antagonists with signs of spinal cord compression.

•

Magnetic resonance imaging is the imaging exam of choice to establish the diagnosis.

•

Rapid correction of bleeding disorders is required.

•

Sometimes, emergent surgical evacuation of the hematoma is the only therapeutic option to ensure optimal neurological prognosis.

•

The procedures for resuming anticoagulation should be subject to a multidisciplinary consultation.

Background

The spinal subdural hematoma (SSH) is an extremely rare entity which represents only 4.1% of all spinal hematomas. It needs accurate diagnosis and rapid intervention because of the major neurological risk induced by spinal compression. Several etiologies have been reported: anticoagulant treatments, haematological disorders, arterio-venous malformation, repeated attempts at lumbar punctures and tumors. We report the case of an 82-year-old patient under acenocoumarol for atrial fibrillation who presented with paraplegia secondary to SSH.

Case report

An 82-year-old patient with a history of ischemic heart disease and atrial fibrillation under acenocoumarol was admitted to emergency department with sudden onset of paraplegia and intense back pain associated with urinary incontinence and anal sphincter disorder. On examination his lower limb power was MRC grade 0 out of 5 in all ranges of movement bilaterally and a complete bilateral anesthesia reaching the T12 dermatome was noted. Biological test results showed an International Normalized Ratio at 10. Magnetic resonance imaging revealed a posteriorly located spinal hematoma at T12 level, measuring 36 mm with spinal cord compression. After correction of hemostasis disorders the patient was admitted to the operating room for a T11-L1 laminectomy with evacuation of the subdural hematoma. Muscle power showed a gradual improvement in the lower limbs estimated at 3/5 with regression of sphincter disorders but unfortunately a sequellar sensory impairment persisted.

Conclusion

SSH is a rare situation of acenocoumarol bleeding incident, it should be evoked in any patient treated by this molecule with signs of spinal cord compression.

Differences in patient outcomes and chronic care management of oral anticoagulant therapy: an explorative study

BACKGROUND

The oral anticoagulant therapy - provided to prevent thrombosis - is known to be associated with substantial avoidable hospitalization. Improving the quality of the oral anticoagulant therapy could avoid drug related hospitalizations. Therefore, this study compared the patient outcomes between Dutch anticoagulant clinic (AC) regions taking the variation in chronic care management into account in order to explore whether chronic care management elements could improve the quality of oral anticoagulant therapy.

METHODS

Two data sources were combined. The first source was a questionnaire that was send to all ACs in the Netherlands in 2008 (response = 100%) to identify the application of chronic care management elements in the AC regions. The Chronic Care Model of Wagner was used to make the concept of chronic care management operational. The second source was the report of the Dutch National Network of ACs which contains patient outcomes of the ACs.

RESULTS

Patient outcomes achieved by the ACs were good, yet differences existed; for instance the percentage of patients in the appropriate therapeutic ranges varied from 67 to 87% between AC regions. Moreover, differences existed in the use of chronic care management elements of the chronic care model, for example 12% of the ACs had multidisciplinary meetings and 58% of the ACs had formal agreements with at least one hospital within their region. Patient outcomes were significantly associated with patient orientation and the number of specialized nurses versus doctors (p-values < 0.05). Furthermore, the overall extent to which chronic care management elements were applied was positively associated with patient outcomes (p-values < 0.05).

CONCLUSIONS

Substantial differences in the patient outcomes as well as chronic care management of oral anticoagulant therapy existed. Since our results showed a positive association between overall application of chronic care management and patient outcomes, additional research is needed to fully understand the working mechanism of chronic care management.

[Bleeding complications due to anticoagulatoric therapy]

Anticoagulation is a standard treatment in patients with thrombosis and commonly used in surgical procedures for primary thrombosis prophylaxis. The occurrence of bleeding episodes is the predominant treatment complication. Although monitoring of hemostatic parameters reduces the risk of bleeding, bleedings occur in approximately 10% of patients. Besides standard life saving procedures it is crucial to ensure sufficient coagulation by administering factor concentrates (e.g. fresh frozen plasma, prothrombin complex, recombinant factor VIIa), platelet concentrates and fluid. Specific antidotes are not available for the majority of anticoagulant agents.