Author(s)

Noe Garin, Laia Lopez-Vinardell, Pau Riera, Adrian Plaza, Ivan Castellvi-Barranco, Jose Mateo-Arranz, M. Antonia Mangues

Why was it done?

APS is a rare disease with a high risk of thromboembolism. Recently, some data suggested an increased risk of thrombotic events with direct-acting anticoagulants (DOAC) compared with vitamin K antagonists in APS. Some agencies advise against the use of DOACs in these patients.

This methodology can be extrapolated to other risk situations, so this was a first step with AI to further detection of safety issues.

What was done?

We implemented an Artificial intelligence (AI) tool based on natural language processing (SAVANA®) to identify patients at risk of thromboembolism, defined as Antiphospholipid Syndrome (APS) diagnosis treated with direct-acting anticoagulants (DOAC). SAVANA® is an AI tool able to extract information contained in free-text from electronic clinical records.

A prior operation work was conducted, involving: direction, pharmacy, documentation, IT, SAVANA®, data protection. The work and previous meetings evaluated: feasibility, previous requirements, privacy issues, IT involvement and contract signings.

How was it done?

The implementation consisted of:
– Transference of medical record information to the SAVANA® cloud.
– Identification of the health problem (APS) and initial search.
– Search algorithm optimization in a multidisciplinary team.
– Evaluation of the search by SAVANA® by peer review in a sample of randomly selected cases (n=200).
– Precision and sensitivity analysis. Algorithm improvement.
– Obtaining the Gold Standard and validation.
– Definitive search for the detection of patients with APS in treatment with DOACs and performance of interventions.

What has been achieved?

The project implementation is at a very advanced stage. The algorithm has currently been evaluated and is being refined after precision and sensitivity analysis. Final validation and definitive identification of patients at risk is expected at the end of 2021. Patients detected during the implementation method have been evaluated with the haematology team.

What next?

This methodology can be implemented in any centre with computerized medical records. The use of AI is the only tool available for the identification of certain groups of patients when health problems are not coded. In other cases, its use regarding the extraction of lists allows a great capacity for analysis, absence of biases derived from human error, guarantee of reproducibility and complementary data obtention, mainly in samples of high size.

Author(s)

JUDIT PERALES PASCUAL, HERMINIA NAVARRO AZNAREZ, ANA LOPEZ PEREZ, LUCIA CAZORLA PODEROSO, IRENE AGUILO LAFARGA, ANA PEÑAS FERNANDEZ, Mª REYES ABAD SAZATORNIL

Why was it done?

Despite the volume of patients seen at UPEX, the complexity of care and the cost of the treatments, in 2019 the prescription was transcribed by pharmacists with the consequent risk/investment of time that this entails. The aim was to incorporate organizational/technological changes that would improve the safety and quality of pharmaceutical care.

What was done?

An outpatient is a patient who goes to the outpatient unit of their Hospital Pharmacy Service (UPEX) to collect a drug for hospital use/diagnosis or foreign drug (it will be administered without health personnel intervention).
We collaborated in the design and validation of the PresSalud®(Dominion®) program, developing the implementation of assisted electronic prescribing (AEP) as an objective in the SAMPA project (Registration and Promotion Service for Adherence to Medications for Elderly Patients).

How was it done?

Access from the electronic medical record to the prescription, the integration of the latter with the dispensing program and the latter with the pharmacy item program guarantees an increase in the safety of medication use by incorporating clinical decision aids.
Different prescription assistance protocols were developed. Presentations and sessions were given to hospital doctors explaining how to prescribe through PresSalud® adapting them to the different services implemented with AEP.

What has been achieved?

In 2018, the AEP was implemented in the infectious, digestive, dermatology, rheumatology, neurology and hematology service (only in hemophilia consultations). Between May-September 2020, it was expanded. It is currently 92.3% implemented and 100% is expected by the end of 2021 (with the rest hematology consultations).

Currently, the percentage of prescriptions to outpatients using AEP with respect to the total prescriptions in this area is 83%; this increase contributes to avoid errors in transcription and to reduce the time spent in checking the prescription, providing greater safety in the use of the medication and better patient care which translates into higher quality of care.

What next?

The implementation of the AEP guarantees safe and efficient prescription; in short, the organizational/technological changes that this entails contribute to improving the quality of pharmaceutical care received by the patient. The proposed solution can be easily extended to other hospitals implementing AEP.

Author(s)

Ghalib Abbasi

Why was it done?

As we venture into the 2020s, health-system pharmacies need to consider these novel approaches to deliver pharmaceutical care to their patients given the changing population needs, lifestyles, and available home technologies accessible to most patients. The ultimate goals are to enhance patient safety, increase hospital pharmacy operational efficiency, and maximize revenue.

What was done?

Novel technologies were implemented at Houston Methodist to enhance patient safety and experience. These include voice-activated devices in patient rooms, smart glasses for pharmacists, smart phones for hospital pharmacy service provision, artificial intelligence, and tele-health

How was it done?

Careful infrastructure considerations/build took place along with pharmacist-driven algorithm write-up. During this GPI, we’d like to discuss specific steps to make this happen along with sensible benefits we realized from implementing each technology.

What has been achieved?

Our hospital pharmacists got significantly more involved in direct patient care where notable efficiencies were realized on the operational side. In addition, medication education was significantly enhanced with improved patient access to their in-house hospital pharmacist.

What next?

Next steps include deploying these these technologies to further service lines and patient care areas, as well as investing into further meaningful technologies. We’ll review what’s in the pipeline as well.

Pdf

Author(s)

ARDIZONE BEATRIZ, MARTA HERNÁNDEZ SEGURADO, MARÍA FORTE PÉREZ-MINAYO, LAURA GARCÍA JIMÉNEZ, ELENA TORTAJADA ESTEBAN, ANA CORDERO GUIJARRO, NATALIA BARRERAS RUIZ, LAURA JIMÉNEZ NAVARRO, JAVIER BÉCARES MARTÍNEZ

Why was it done?

First, we had a high number of patient inquiries by phone and by email. Furthermore, patient queries related with their treatment and their resolution were not recorded in the electronic clinical history. Finally, we needed a communication platform that would guarantee personal data privacy.

What was done?

In collaboration with the IT department, we developed a software tool called “Web Dialogue” within the e-health portal of our institution. This tool allows the patients to communicate with the pharmacist using a chat box where they can write queries about drug interactions, adverse effects and any questions about the hospital dispensing treatments, as well as other medications and herbal products. A pharmacist answers the queries within 24 hours, from Monday to Friday.

How was it done?

We asked the IT department to activate this tool for all active patients to whom we dispensed medication in our service (a total of 8000 patients). The development lasted 2 years (2017-2019), but it was not until March 2020, with the start of the COVID-19 pandemic, that the “Web Dialogue” began to be used by our patients more widely. We also made an informative video that was posted on the e-health portal in order to achieve a wider knowledge of this tool among patients. See link: https://www.youtube.com/watch?v=_Z9pd93sNY8

What has been achieved?

The median number of messages per month in 2020-2021 was 202 (IQR= 100,5; 468). At the beginning of the state of alarm in Spain there was a peak in the use of the “Web Dialogue”, mainly to query about how to access the medication (94% of the queries). Over the following months, the proportion of these consultations decreased and consultations regarding doubts about treatment, adverse effects and drug interactions increased. Furthermore, the Net Promoter Score (NPS), an indicator that allows us to measure the satisfaction of patients, shows that in the last year we have achieved, for the first time, a score over 60, which is considered excellent.

What next?

Some of our ideas for the future are: the possibility of selecting the type of inquiry and the interlocutor by the patient, creating algorithms for the automatic response of certain questions and carrying out Big Data research studies.

Pdf

Author(s)

Mathilde Roche, Annabelle Angapin, Vincent Blazy, Alexandre Hyvert, Loretta Moriconi, Matteo Federici, Bintou Diawara, Cindy Monnel, Lison Ferreol, Assia Mitha, Hail Aboudagga, Romain Desmaris

Why was it done?

Initially, robot’s operations required prescription re-transcription and chemotherapy relabelling by technicians, leading to manual data entry risks. Robots are known for high-standardised procedures, great repeatability and limited human intervention: adding bidirectional interface enabled improvement of patient safety. Moreover, it shows significant benefits during the compounding process, streamlining pharmacy workflows and ensuring full and paperless traceability.

What was done?

In 2018, our chemotherapy production unit implemented an automated anticancer drugs compounding platform, embedding two APOTECAchemo robots. This aims to meet the increasing patient-specific chemotherapy demands (78,000 preparations/year). In order to minimise human risk and optimise work efficiency, implementation of a bidirectional interface between the robots and the hospital’s Electronic Prescribing Software (EPS) was considered as mandatory, to allow exchange and clinical information retrieval.

How was it done?

In 2020, pharmacists and the IT team defined the interface specifications. Bidirectional information flow was implemented using Health Level Seven (HL7) standards. Interface between EPS and APOTECAmanager was developed and a comparative robot performance analysis was undertaken by evaluating processed drug products, compounded preparation numbers and actual average usage time per day. The staff (i.e. two technicians) remained identical. Data were retrieved from robot’s embedded statistical tool over three months, before (March-May 2020) and after interface implementation (July-September 2020).

What has been achieved?

During these six months, 13,746 preparations were compounded, with 95% infusion bags and 5% elastomeric pumps. Most of these preparations were produced in advance (administration on day+2 or day+3). After interface implementation, the average production raised by 40.5% (from 1,905 to 2,676/month). Interface implementation increased also the average robot operating hours from 3.6 hours/day/robot to 5.8 hours/day/robot (+61.1%). In total, 19 different molecules were compounded, including conventional anticancer drugs and monoclonal antibodies with the number of reconstituted drug vials increasing by 38.1% (from 625 to 863).

What next?

Interface between robots and the EPS was successfully implemented, thereby enabling improved safety and efficiency. Today, syringes and paediatric preparations are still made manually. They require visual and analytical controls to verify their conformity. Mid 2021, a third robot customized for syringes and paediatric preparations will be installed in the compounding unit, to secure these preparations in a more efficient way.

Pdf

Author(s)

MARINA CORRALES PAZ, CLAUDIA RODRIGUEZ MORETA, INMACULADA LOMARES MANZANO, ANA GANFORNINA ANDRADES

Why was it done?

Due to the health crisis caused by the SARS-COV-2 virus, many hospitals have seen
the necessity to implement a safe dispensing system (telepharmacy) to provide medication to
high risk patients and those infected with Covid-19 in order to prevent interrupting their
treatments.

What was done?

To implement a system that guarantees a sure and effective supply of medical treatments to those vulnerable patients, those at increased risk or with difficult access to the hospital during the coronavirus pandemic.

How was it done?

A database was created with those patients attending our hospital’s outpatient service(OS)to pick up their medication within the next 7 days, verifying through pharmaceutical software and the patient’s medical history records (MHR)their next dispensing date. After checking if the patient had a medical appointmentthat could coincide with the dispensing date, a phone interview was conducted with the patient to schedule the pick-up of the medication through theOS or by telepharmacy(patients’ consent was requiredto use their personal information and we asked how the treatment was going). In our case the patients could pick-up their medication in the referral hospital (RH), a newly created OS in an affiliate hospital or by telepharmacy toprevent the collapse of the hospitals. We registered: number of patients attended in RH, new OS or by telepharmacy and number of dispensations. Patients were grouped in areas based on their city and delivery date for telepharmacy and in the case of patients picking up their own medication they were made an appointment.

What has been achieved?

During the months the state of emergency was in place in Spain (March 14th– June 21st)3385 patients were attended in total and 9316 medicationswere dispensed. 2245(66.3%) patients were attended in the RH (5794 dispensations), 583(17.2%) patients were attended through the new OS (1436 dispensations) and the rest 557(16.5%) had their medication sent to their address (2086 dispensations).

What next?

A safe and effective dispensing system was achieved to outpatients during the Covid-19 pandemic through the implementation of a new telepharmacymethod and the establishment of a new OSthat allows convenient dispensation of medication while minimising the risk of virus spread.

Pdf

Author(s)

Pauline Barreau, Joséphine Courouble, Pierre Pilven, David Vandecapelle, Thibault Stala, Geoffrey Strobbe, Guillaume Marliot, Frédéric Feutry

Why was it done?

Two prescription assistance software are using in the hospital: DXCare®, for global drug management, and Chimio®, specific to the prescription and preparation of injectable chemotherapies. Clinical pharmacists (DXCare®) and pharmacists in charge of preparation (Chimio®) carry out the pharmaceutical analysis independently and they may not detect potential pharmacokinetics/pharmacodynamics drugs interactions or pathophysiological contraindications, slowing down the pharmaceutical analysis. Pharmaclass® can improve that by crossing all data flows between DXCare® and Chimio® and alerting the pharmacist. The objective were to select and code priority alerts and evaluate the detectability of drugs interactions and pathophysiological contraindications by the software Pharmaclass®.

What was done?

Pharmaclass® is a software based on rules created by the pharmacist, from pharmaceutical algorithms. This rules engine crosses in real time all data flows of several software and sends alerts that must be analyzed by a pharmacist. It was applied in oncology for injectable chemotherapies.

How was it done?

An interface was set up between DXCare®/Chimio® and Pharmaclass® to allow the creation of requests. An analysis of drug consumptions and drugs at risk of interactions helped to select seven molecules (Methotrexate, Bevacizumab, Fluorouracil, Ifosfamide, Irinotecan, Cisplatin, Pemetrexed). A study of the summaries of the product characteristics and the drug interaction thesaurus and a bibliography was conducted and the rules were coded. These were checked by creating test patients with false prescriptions.

What has been achieved?

Eleven rules were created and, after some tests and coding readjustments, all was detected. Nine rules are about drugs interactions: three contraindications (Methotrexate/Trimethoprim, Methotrexate/Acetylsalicylic acid, Bevacizumab/Naloxegol), three associations not recommended (Methotrexate/Amoxicillin, Methotrexate/Ciprofloxacin, Fluorouracil/Antivitamin K), one precaution of use (Ifosfamide/Aprepitant) and two other rules concern enzymatic induction and inhibition of the metabolism of Irinotecan. The last two rules link the glomerular filtration rate with Cisplatin and Pemetrexed.

What next?

Following these creations, Pharmaclass® has allowed to detect drug interactions and pathophysiological contraindications that were not previously detectable. Thereafter, objective will be to establish an organization for the management of alerts and evaluate the number and the relevance of these alerts. New rules will be created for all injectable chemotherapies used in the hospital. Other center of Unicancer will be able to use these rules.

Pdf

Author(s)

Xando Díaz-Villamarín, Ana Pozo-Agundo, Paloma García-Navas, Alba Antúnez-Rodríguez, Celia Castaño-Amores, Cristina Lucía Dávila-Fajardo

Why was it done?

Nowadays, it is known that at least 33% of patients show variable response to drugs. Of those, genetic polymorphisms explain around 15-30% of these cases, single nucleotide polymorphisms (SNP) being the genetic markers most clinically relevant. In 2013, 40 million SNPs were identified in humans and some have been observed to determine drug response. These observations lead to the incorporation of genotyping some of these SNPs as a recommendation in many drug labels before treatment initiation.
Since patient´s drug response may be determined by certain SNPs in different genes it is necessary to develop CDSS based on pharmacogenetic (PGx) information that makes feasible its application in clinical routine, translating genotypes into phenotypes and dosing recommendations.

What was done?

We have developed a local Clinical Decision Support Systems (CDSS) that informs the physician on the availability of a PGx test in our hospital for certain prescribing drugs. This system will also be able to translate the genetic information into dosing recommendations.

How was it done?

We selected all the SNPs affecting drug response for which there is already a PGx test available in our hospital. All of them have been previously validated, and, only genes/SNPs related to drug response with the highest level of evidence, available in the Dutch Pharmacogenomics Working Group (DPWG) and Clinical Pharmacogenetics Implementation Consortium (CPIC) dosing guidelines with a minor allele frequency higher than 0,1% in our population have been included. We have considered all the different genotypes according to the SNPs included and linked them to a phenotype and dossing recommendation according to CPIC/DPWG guidelines.

What has been achieved?

Our CDSS connects different drugs with available PGx test in our unit, showing which gene should be genotyped before prescription. It translates genotypes into phenotypes and also provides dosing recommendations once PGx results are received, according to the CPIC and/or DPWG guidelines. Nowadays, this system facilitates the workflow for the implementation of pharmacogenetic tests in our hospital.

What next?

We have developed a CDSS that manages PGx information facilitating the implementation of pharmacogenetics in daily clinical routine. It will also allow us to expand our services to other medical departments within our hospital.

Pdf

Author(s)

MAR GOMIS-PASTOR, ANNA DE DIOS LÓPEZ, MARIA ANTONIA MANGUES, MIRIAM ORS, MERITXELL CUCALA, CATERINA SANPOL, VICTOR ROBERT, XAVIER BORRAS, GEMMA CRAYWINCKEL

Why was it done?

HTP are therapeutically complex patients who may benefit from an intensive telematic follow-up. Moreover, human relations among patients and health providers may be enhanced to improve patients’ empowerment with their health care. Additionally, interdisciplinary eHealth projects lead to increased interaction among health providers, expanding advanced patient-centered care in healthcare systems.

What was done?

An eHealth program directed to heart transplant patients (HTP) was implemented. The software developed was called mHeart and consists on a mobile phone application complemented by a website(https://n9.cl/ajut). A pilot study to validate the software and a clinical trial were conducted. This tool is now extended into clinical practice.

How was it done?

This project and its potential scalability has achieved the creation of a well-established framework involving among relevant others the Legal Department, the Information Systems Department, the patient data protection supervisor, and the Innovation Research Institute.
The success and the scalability of these innovative projects in our centre depended on health providers’ engagement with eHealth, new interoperability solutions, adequate institutional support, and government reimbursement models.

What has been achieved?

The clinical trial conducted in 134HTP has demonstrated to improve recipients’ adherence to immunosuppressants (85% mHeart follow-up vs 46% conventional follow-up)[OR=6.7 (2.9;15.8),P-value=.000], to improve patients’ experience of therapeutic regimens and to reduce in-clinic facilities because the mHeart follow-up. (65% mHeart follow-up vs 35% conventional follow-up)[OR=3.4 (1.7;6.9),P-value=.001].

What next?

This eHealth experience has allowed continuing creating evidence on the use of the eHealth in other populations: an onco-hematological platform, EMMA(Ehealth Medical self-Management Aid), has been designed including diverse profiles depending on the clinical specifications (e.g. multiple myeloma or bone marrow transplant conditions); MyPlan has been adapted to perform an interdisciplinary follow-up of any multimorbid population with polypharmacy. Thus, the system can be used in any multimorbid patients by activating or omitting certain modules that define the target patients’ specific comorbidities (e.g. glycemia module or blood pressure module).
The new EMMA and MyPlan will be clinically tested in diverse trials in 2020 including several health care interdisciplinary teams, including the emergency setting, onco-hematology, migraine, dyslipidemia and cardiovascular risk, among relevant others. In addition, other Spanish centers are implementing the eHealth model and the software in their Institutions assisted by the experience gathered.

Pdf

Author(s)

Karina Doherty

Why was it done?

VTE is a collective term for blood clots usually in the legs or lungs. In Europe, there are 544,000 VTE-related deaths every year. VTE is responsible for more deaths than AIDS, breast cancer, prostate cancer and motor vehicle accidents combined. SVPH Pharmacy Department has been conducting annual Clinical Audits on VTE prophylaxis using a paper based system. However, the process was time consuming and limited the frequency of audit and the opportunities for identifying opportunities for improvement in compliance. SVPH has a high number of patients with high risk of VTE including Medical Oncology patients and Surgical patients. Compliance rates over preceding years were running at 75%; however, it is hoped to achieve a target of 90% compliance by 2020.

What was done?

An App was developed to collect data on venous thromboembolism (VTE) prophylaxis compliance across St Vincent’s Private Hospital (SVPH)

How was it done?

Different technologies were explored and an App developer was selected. Funding was sourced. Stakeholders were invited to get involved in the development team; this part was challenging and a lot of negotiations were had as to how the format of the App would be developed and carried forward. The next step when all the details had been finalised was launching the App.

What has been achieved?

Every month seven patients are randomly selected for audit and an auditor (in SVPH a pharmacist) inputs the data on the App which the lead auditor analysis. At SVPH compliance has increased from 75% prior to the app, to post implementation of the App where monthly VTE audits were conducted on all inpatient wards. The results are 92% compliance with VTE prophylaxis for 2018, and for 2019 up to Sept 2019 96% compliance.

What next?

It is hoped that this App will be a useful tool that will help SVPH and other hospitals to achieve a higher compliance with VTE prophylaxis guidelines and help prevent clots in patients. This App can be customised to individual hospital requirements. Technology has been shown to assist with clinical audit and will be used in various projects to make auditing easier and faster and therefore help healthcare workers to provide a better service to patients.