Transfer Learning With Singular Value Decomposition of Multichannel Convolution Matrices.

The task of transfer learning using pretrained convolutional neural networks is considered. We propose a convolution-SVD layer to analyze the convolution operators with a singular value decomposition computed in the Fourier domain. Singular vectors extracted from the source domain are transferred to the target domain, whereas the singular values are fine-tuned with a target data set. In this way, dimension reduction is achieved to avoid overfitting, while some flexibility to fine-tune the convolution kernels is maintained. We extend an existing convolution kernel reconstruction algorithm to allow for a reconstruction from an arbitrary set of learned singular values. A generalization bound for a single convolution-SVD layer is devised to show the consistency between training and testing errors. We further introduce a notion of transfer learning gap. We prove that the testing error for a single convolution-SVD layer is bounded in terms of the gap, which motivates us to develop a regularization model with the gap as the regularizer. Numerical experiments are conducted to demonstrate the superiority of the proposed model in solving classification problems and the influence of various parameters. In particular, the regularization is shown to yield a significantly higher prediction accuracy.

Attributed Abnormality Graph Embedding for Clinically Accurate X-Ray Report Generation.

Despite the recent success of deep learning models for text generation, generating clinically accurate reports remains challenging. More precisely modeling the relationships of the abnormalities revealed in an X-ray image has been found promising to enhance the clinical accuracy. In this paper, we first introduce a novel knowledge graph structure called an attributed abnormality graph (ATAG). It consists of interconnected abnormality nodes and attribute nodes for better capturing more fine-grained abnormality details. In contrast to the existing methods where the abnormality graph are constructed manually, we propose a methodology to automatically construct the fine-grained graph structure based on annotated X-ray reports and the RadLex radiology lexicon. We then learn the ATAG embeddings as part of a deep model with an encoder-decoder architecture for the report generation. In particular, graph attention networks are explored to encode the relationships among the abnormalities and their attributes. A hierarchical attention attention and a gating mechanism are specifically designed to further enhance the generation quality. We carry out extensive experiments based on the benchmark datasets, and show that the proposed ATAG-based deep model outperforms the SOTA methods by a large margin in ensuring the clinical accuracy of the generated reports.

A 12-gene pharmacogenetic panel to prevent adverse drug reactions: an open-label, multicentre, controlled, cluster-randomised crossover implementation study.

BACKGROUND: The benefit of pharmacogenetic testing before starting drug therapy has been well documented for several single gene-drug combinations. However, the clinical utility of a pre-emptive genotyping strategy using a pharmacogenetic panel has not been rigorously assessed. METHODS: We conducted an open-label, multicentre, controlled, cluster-randomised, crossover implementation study of a 12-gene pharmacogenetic panel in 18 hospitals, nine community health centres, and 28 community pharmacies in seven European countries (Austria, Greece, Italy, the Netherlands, Slovenia, Spain, and the UK). Patients aged 18 years or older receiving a first prescription for a drug clinically recommended in the guidelines of the Dutch Pharmacogenetics Working Group (ie, the index drug) as part of routine care were eligible for inclusion. Exclusion criteria included previous genetic testing for a gene relevant to the index drug, a planned duration of treatment of less than 7 consecutive days, and severe renal or liver insufficiency. All patients gave written informed consent before taking part in the study. Participants were genotyped for 50 germline variants in 12 genes, and those with an actionable variant (ie, a drug-gene interaction test result for which the Dutch Pharmacogenetics Working Group [DPWG] recommended a change to standard-of-care drug treatment) were treated according to DPWG recommendations. Patients in the control group received standard treatment. To prepare clinicians for pre-emptive pharmacogenetic testing, local teams were educated during a site-initiation visit and online educational material was made available. The primary outcome was the occurrence of clinically relevant adverse drug reactions within the 12-week follow-up period. Analyses were irrespective of patient adherence to the DPWG guidelines. The primary analysis was done using a gatekeeping analysis, in which outcomes in people with an actionable drug-gene interaction in the study group versus the control group were compared, and only if the difference was statistically significant was an analysis done that included all of the patients in the study. Outcomes were compared between the study and control groups, both for patients with an actionable drug-gene interaction test result (ie, a result for which the DPWG recommended a change to standard-of-care drug treatment) and for all patients who received at least one dose of index drug. The safety analysis included all participants who received at least one dose of a study drug. This study is registered with ClinicalTrials.gov, NCT03093818 and is closed to new participants. FINDINGS: Between March 7, 2017, and June 30, 2020, 41 696 patients were assessed for eligibility and 6944 (51·4 % female, 48·6% male; 97·7% self-reported European, Mediterranean, or Middle Eastern ethnicity) were enrolled and assigned to receive genotype-guided drug treatment (n=3342) or standard care (n=3602). 99 patients (52 [1·6%] of the study group and 47 [1·3%] of the control group) withdrew consent after group assignment. 652 participants (367 [11·0%] in the study group and 285 [7·9%] in the control group) were lost to follow-up. In patients with an actionable test result for the index drug (n=1558), a clinically relevant adverse drug reaction occurred in 152 (21·0%) of 725 patients in the study group and 231 (27·7%) of 833 patients in the control group (odds ratio [OR] 0·70 [95% CI 0·54-0·91]; p=0·0075), whereas for all patients, the incidence was 628 (21·5%) of 2923 patients in the study group and 934 (28·6%) of 3270 patients in the control group (OR 0·70 [95% CI 0·61-0·79]; p <0·0001). INTERPRETATION: Genotype-guided treatment using a 12-gene pharmacogenetic panel significantly reduced the incidence of clinically relevant adverse drug reactions and was feasible across diverse European health-care system organisations and settings. Large-scale implementation could help to make drug therapy increasingly safe. FUNDING: European Union Horizon 2020.

Pharmacogenomics decision support in the U-PGx project: Results and advice from clinical implementation across seven European countries.

BACKGROUND: The clinical implementation of pharmacogenomics (PGx) could be one of the first milestones towards realizing personalized medicine in routine care. However, its widespread adoption requires the availability of suitable clinical decision support (CDS) systems, which is often impeded by the fragmentation or absence of adequate health IT infrastructures. We report results of CDS implementation in the large-scale European research project Ubiquitous Pharmacogenomics (U-PGx), in which PGx CDS was rolled out and evaluated across more than 15 clinical sites in the Netherlands, Spain, Slovenia, Italy, Greece, United Kingdom and Austria, covering a wide variety of healthcare settings. METHODS: We evaluated the CDS implementation process through qualitative and quantitative process indicators. Quantitative indicators included statistics on generated PGx reports, median time from sampled upload until report delivery and statistics on report retrievals via the mobile-based CDS tool. Adoption of different CDS tools, uptake and usability were further investigated through a user survey among healthcare providers. Results of a risk assessment conducted prior to the implementation process were retrospectively analyzed and compared to actual encountered difficulties and their impact. RESULTS: As of March 2021, personalized PGx reports were produced from 6884 genotyped samples with a median delivery time of twenty minutes. Out of 131 invited healthcare providers, 65 completed the questionnaire (response rate: 49.6%). Overall satisfaction rates with the different CDS tools varied between 63.6% and 85.2% per tool. Delays in implementation were caused by challenges including institutional factors and complexities in the development of required tools and reference data resources, such as genotype-phenotype mappings. CONCLUSIONS: We demonstrated the feasibility of implementing a standardized PGx decision support solution in a multinational, multi-language and multi-center setting. Remaining challenges for future wide-scale roll-out include the harmonization of existing PGx information in guidelines and drug labels, the need for strategies to lower the barrier of PGx CDS adoption for healthcare institutions and providers, and easier compliance with regulatory and legal frameworks.

Transition from Acute Treatment to Survivorship: Exploring the Psychosocial Adjustments of Chinese Parents of Children with Cancer or Hematological Disorders.

OBJECTIVES: Parents of children diagnosed with critical illnesses face multiple challenges during their caregiving experience. However, relevant studies have been limited in the Chinese context. Guided by the stress and coping model, we conducted a qualitative study to identify the stressors, coping strategies, and adjustment experiences of Hong Kong parents of children with cancer or hematological disorders. METHODS: We recruited 15 parents of children with cancer or hematological disorders requiring bone marrow transplantation and were currently >2 years post-treatment. They participated in a 30-min semi-structured interview. Thematic analysis was performed using the grounded theory approach. RESULTS: The stressors reported by parents included a high caregiving burden during their children's diagnosis and treatment stages. The fear of recurrence, the need for information, and concerns about late effects were also common among the parents during their children's transition/survivorship stage. To cope with these stressors, the parents commonly used problem-focused (e.g., seeking help from professionals and support groups) and emotion-focused (e.g., behavioral distractions, venting, and crying) strategies. Despite these stressors, parents reported positive changes through the caregiving experience, such as improved family relationships, developing health-protective habits, and the reprioritization of different aspects of life. CONCLUSIONS: Parents encounter different stressors during the cancer care continuum. Using different coping strategies, parents experience positive changes amidst caregiving. Future studies should explore culturally relevant adaptive coping strategies to enhance parents' psychosocial adjustment.

[Fitness to drive when taking medicines]. / Rijvaardigheid bij het gebruik van geneesmiddelen.

The regulations for driving fitness of people using drugs with potential influence on driving capability are embodied in the 'Regelingeisengeschiktheid 2000' (REG2000). The Health Council of the Netherlands (HCN) adviced to design more strict regulations for professional drivers. This advice has not yet been approved by the minister due to implementation complexity. The HCN recommends to follow the by the KNMP formulated advices when using category II psychostimulants or category III antidepressants, benzodiazepines, antipsychotics, antihistamines, anti-epileptics or opioids. The KNMP advices for driving participation are broadly available via the public websites www.apotheek.nl and www.rijveiligmetmedicijnen.nl. Both websites are written in accessible language level. The HCN advices to enhance scientific research concerning influence on driving fitness before approving a drug, to use standard procedures to prevent ad hoc decisions concerning driving fitness and the use of checklists for doctors when preparing driving fitness attests.

Generating evidence for precision medicine: considerations made by the Ubiquitous Pharmacogenomics Consortium when designing and operationalizing the PREPARE study.

OBJECTIVES: Pharmacogenetic panel-based testing represents a new model for precision medicine. A sufficiently powered prospective study assessing the (cost-)effectiveness of a panel-based pharmacogenomics approach to guide pharmacotherapy is lacking. Therefore, the Ubiquitous Pharmacogenomics Consortium initiated the PREemptive Pharmacogenomic testing for prevention of Adverse drug Reactions (PREPARE) study. Here, we provide an overview of considerations made to mitigate multiple methodological challenges that emerged during the design. METHODS: An evaluation of considerations made when designing the PREPARE study across six domains: study aims and design, primary endpoint definition and collection of adverse drug events, inclusion and exclusion criteria, target population, pharmacogenomics intervention strategy, and statistical analyses. RESULTS: Challenges and respective solutions included: (1) defining and operationalizing a composite primary endpoint enabling measurement of the anticipated effect, by including only severe, causal, and drug genotype-associated adverse drug reactions; (2) avoiding overrepresentation of frequently prescribed drugs within the patient sample while maintaining external validity, by capping drugs of enrolment; (3) designing the pharmacogenomics intervention strategy to be applicable across ethnicities and healthcare settings; and (4) designing a statistical analysis plan to avoid dilution of effect by initially excluding patients without a gene-drug interaction in a gatekeeping analysis. CONCLUSION: Our design considerations will enable quantification of the collective clinical utility of a panel of pharmacogenomics-markers within one trial as a proof-of-concept for pharmacogenomics-guided pharmacotherapy across multiple actionable gene-drug interactions. These considerations may prove useful to other investigators aiming to generate evidence for precision medicine.

Oral adverse effects of drugs: Taste disorders.

OBJECTIVE: Oral healthcare professionals are frequently confronted with patients using drugs on a daily basis. These drugs can cause taste disorders as adverse effect. The literature that discusses drug-induced taste disorders is fragmented. This article aims to support oral healthcare professionals in their decision making whether a taste disorder can be due to use of drugs by providing a comprehensive overview of drugs with taste disorders as an adverse effect. MATERIALS AND METHODS: The national drug information database for Dutch pharmacists, based on scientific drug information, guidelines, and summaries of product characteristics, was analyzed for drug-induced taste disorders. "MedDRA classification" and "Anatomic Therapeutical Chemical codes" were used to categorize the results. RESULTS: Of the 1,645 drugs registered in the database, 282 (17%) were documented with "dysgeusia" and 61 (3.7%) with "hypogeusia." Drug-induced taste disorders are reported in all drug categories, but predominantly in "antineoplastic and immunomodulating agents," "antiinfectives for systemic use," and "nervous system." In ~45%, "dry mouth" coincided as adverse effect with taste disorders. CONCLUSION: Healthcare professionals are frequently confronted with drugs reported to cause taste disorders. This article provides an overview of these drugs to support clinicians in their awareness, diagnosis, and treatment of drug-induced taste disorders.

Relevance of foreign alerts and newsletters for the medication errors reporting programme in the Netherlands: an explorative retrospective study.

INTRODUCTION: National reporting programmes usually collect and analyse medication error reports from healthcare providers in their own country and only disseminate guidance to healthcare providers within the borders of their country. It is unclear how much different national programmes could learn from each other. The aim of this study was therefore to explore to what extent alerts and newsletters about medication errors issued in other countries could also be relevant for the Netherlands. METHODS: Ninety disseminated information items that had been issued by three national programmes (Canada, the US and the UK) in the period from June 2009 until June 2012 were collected. These items were compared with the national reporting programme Central Medication Incidents Registration (CMR-NL) in The Netherlands. Each selected item was subsequently assessed independently with six assessment criteria: is the medicine available in the Netherlands? If so, could a similar error occur in the Netherlands? Did the CMR-NL reporting programme receive any reports about a comparable (or even identical) error? If so, did these reports include any errors with serious temporary or permanent harm? Did the CMR-NL disseminate output about it?; If so, what was the dissemination date of CMR-NL? RESULTS: From the 90 items, 87.8 % (n = 79) were relevant for Dutch healthcare. For 43 of the 90 items (47.8 %), the CMR-NL had received comparable (or even identical) errors but had not disseminated any alert or newsletter about these errors. The CMR-NL had disseminated an alert or newsletter for 14 of the 90 items (15.6 %). CONCLUSION: This study showed for a broad range of errors that the Dutch national reporting programme could learn from the three reporting programmes in Canada, the US and the UK. National reporting programmes can benefit from sharing alerts and newsletters that enhance the learning between countries.

Medication incidents related to automated dose dispensing in community pharmacies and hospitals--a reporting system study.

INTRODUCTION: Automated dose dispensing (ADD) is being introduced in several countries and the use of this technology is expected to increase as a growing number of elderly people need to manage their medication at home. ADD aims to improve medication safety and treatment adherence, but it may introduce new safety issues. This descriptive study provides insight into the nature and consequences of medication incidents related to ADD, as reported by healthcare professionals in community pharmacies and hospitals. METHODS: The medication incidents that were submitted to the Dutch Central Medication incidents Registration (CMR) reporting system were selected and characterized independently by two researchers. MAIN OUTCOME MEASURES: Person discovering the incident, phase of the medication process in which the incident occurred, immediate cause of the incident, nature of incident from the healthcare provider's perspective, nature of incident from the patient's perspective, and consequent harm to the patient caused by the incident. RESULTS: From January 2012 to February 2013 the CMR received 15,113 incidents: 3,685 (24.4%) incidents from community pharmacies and 11,428 (75.6%) incidents from hospitals. Eventually 1 of 50 reported incidents (268/15,113 = 1.8%) were related to ADD; in community pharmacies more incidents (227/3,685 = 6.2%) were related to ADD than in hospitals (41/11,428 = 0.4%). The immediate cause of an incident was often a change in the patient's medicine regimen or relocation. Most reported incidents occurred in two phases: entering the prescription into the pharmacy information system and filling the ADD bag. CONCLUSION: A proportion of incidents was related to ADD and is reported regularly, especially by community pharmacies. In two phases, entering the prescription into the pharmacy information system and filling the ADD bag, most incidents occurred. A change in the patient's medicine regimen or relocation was the immediate causes of an incident.

Classification of medication incidents associated with information technology.

INTRODUCTION: Information technology (IT) plays a pivotal role in improving patient safety, but can also cause new problems for patient safety. This study analyzed the nature and consequences of a large sample of IT-related medication incidents, as reported by healthcare professionals in community pharmacies and hospitals. METHODS: The medication incidents submitted to the Dutch central medication incidents registration (CMR) reporting system were analyzed from the perspective of the healthcare professional with the Magrabi classification. During classification new terms were added, if necessary. MAIN MEASURES: The principal source of the IT-related problem, nature of error. Additional measures: consequences of incidents, IT systems, phases of the medication process. RESULTS: From March 2010 to February 2011 the CMR received 4161 incidents: 1643 (39.5%) from community pharmacies and 2518 (60.5%) from hospitals. Eventually one of six incidents (16.1%, n=668) were related to IT; in community pharmacies more incidents (21.5%, n=351) were related to IT than in hospitals (12.6%, n=317). In community pharmacies 41.0% (n=150) of the incidents were about choosing the wrong medicine. Most of the erroneous exchanges were associated with confusion of medicine names and poor design of screens. In hospitals 55.3% (n=187) of incidents concerned human-machine interaction-related input during the use of computerized prescriber order entry. These use problems were also a major problem in pharmacy information systems outside the hospital. CONCLUSIONS: A large sample of incidents shows that many of the incidents are related to IT, both in community pharmacies and hospitals. The interaction between human and machine plays a pivotal role in IT incidents in both settings.

Self-reported uptake of recommendations after dissemination of medication incident alerts.

INTRODUCTION: In the Netherlands, a Central Medication Incidents Registration (CMR) system is operational. To prevent recurrence of reported medication incidents the CMR sends medication incident alerts with recommendations. It is up to the healthcare workers whether or not to implement the recommendations in clinical practice, which may lead to variations in degrees of uptake of the recommendations. OBJECTIVE: The aim of this study was to explore the degree of self-reported uptake of the recommendations and to identify potential determinants associated with successful uptake. DESIGN: This is a cross-sectional study conducted within a convenience sample of 33 Dutch hospital pharmacies. The study was carried out from April 2009 to September 2010. MEASUREMENTS: Three alerts were selected for the study: administration of methotrexate in a dosage of once a day instead of once a week, administration of undiluted potassium-sodium-phosphate concentrate, and administration of glucose 50% instead of 5%. The primary outcome was the degree of self-reported uptake of the specific recommendations and the associations of the degree of uptake with several potential determinants. RESULTS: Twenty-one hospitals (63.6%) had adopted all recommendations about methotrexate. A quarter of the hospitals (24.2%) had adopted all recommendations related to potassium-sodium-phosphate concentrate. For the alert about glucose 50%, none of the hospitals had implemented all the recommendations. No statistically significant associations between potential determinants and the degree of uptake were found. CONCLUSIONS: This study is the first to investigate the degree of uptake of the recommendations of three different CMR alerts. The alerts varied in the degrees of self-reported uptake of the recommendations, with the methotrexate alert having the highest degree of uptake. No significant associations with potential determinants were found.

A nationwide medication incidents reporting system in The Netherlands.

OBJECTIVE: Many Dutch hospitals have established internal systems for reporting incidents. However, such internal systems do not allow learning from incidents that occur in other hospitals. Therefore a multicenter, information technology (IT) supported reporting system named central medication incidents registration (CMR) was developed. This article describes the architecture, implementation and current status of the CMR in The Netherlands and compare it with similar systems in other countries. SYSTEM DESCRIPTION: Adequate IT is required to sufficiently support a multicenter reporting system. The CMR system consists of a website, a database, a web-based reporting form, an application to import reports generated in other reporting systems, an application to generate an overview of reported medication incidents, and a national warning system for healthcare providers. CURRENT STATUS: From the start of CMR 90 of all 93 (96.8%) hospitals and 872 of 1948 (44.8%) community pharmacies participated. Between March 2006 and March 2010 the CMR comprised 15,694 reports of incidents. In the period from March 2010 to March 2011, 1642 reports were submitted by community pharmacies in CMR and the hospitals submitted 2517 reports. CMR is similar to various systems in other countries, but it seems to use more IT applications. DISCUSSION: The CMR is developing into a nationwide reporting system of medication incidents in The Netherlands, in which hospitals, community pharmacies, mental healthcare organizations and general practitioners participate. CONCLUSION: The architecture of the system met the requirements of a nationwide reporting system across different healthcare providers.

Erroneous exchange of asparaginase forms in the treatment of acute lymphoblastic leukemia.

For the treatment of children with acute lymphoblastic leukemia (ALL), Dutch pediatric oncologists use the Dutch Childhood Oncology Group ALL 10 protocol. This protocol is complex, as it comprises many different drug regimens. One of the drugs is asparaginase which is available in different forms with different pharmacokinetics: Escherichia coli asparaginase, Erwinia asparaginase, and pegylated E. coli asparaginase [polyethylene glycol (PEG) asparaginase]. Here, we report the case of a 3-year-old patient treated with ALL who was 8 times erroneously treated with E. coli asparaginase instead of PEG asparaginase. As E. coli asparaginase was administered to the patient in the lower dosage regimen of PEG asparaginase, she was undertreated, but at the end of the treatment the patient was in complete remission. This case report describes the actual course of treatment, the reasons why it went wrong, and possible preventive measures.

Medication errors: the importance of safe dispensing.

1. Although rates of dispensing errors are generally low, further improvements in pharmacy distribution systems are still important because pharmacies dispense such high volumes of medications that even a low error rate can translate into a large number of errors. 2. From the perspective of pharmacy organization and quality assurance, pharmacists should intensify their checking of prescriptions, in order to reduce prescription errors, and should implement strategies to communicate adequately with patients, in order to prevent administration errors. More and better studies are still needed in these areas. 3. More research is also required into: dispensing errors in out-patient health-care settings, such as community pharmacies in the USA and Europe; dispensing errors in hospitals and out-patient health-care settings in middle- and low-income countries; and the underlying causes of dispensing errors.

Direct-to-consumer communication on prescription only medicines via the internet in the Netherlands, a pilot study. Opinion of the pharmaceutical industry, patient associations and support groups.

OBJECTIVE: Investigation of the current application of direct-to-consumer (DTC) communication on prescription only medicines via the Intemet in the Netherlands. METHOD: Questionnaires were sent by e-mail to 43 Dutch innovative pharmaceutical industries and 130 Patient Association and Support Groups (PASGs). RESULTS: In this pilot study, the response of the pharmaceutical industry was rather low but the impression is that they were willing to invest in DTC communication. The majority of the websites of PASGs did not link to websites of pharmaceutical companies. The PASGs had no opinion whether patients can make a good distinction between DTC advertising and information on websites of the pharmaceutical industry nor about the quality. PASGs did not think unambiguously about the impact on the patient-doctor relationship. CONCLUSION: The impact of DTC communication on prescription only medicines via the internet is not yet clear in the Netherlands.