Algorithmic Identification of Treatment-Emergent Adverse Events From Clinical Notes Using Large Language Models: A Pilot Study in Inflammatory Bowel Disease

Outpatient clinical notes are a rich source of information regarding drug safety. However, data in these notes are currently underutilized for pharmacovigilance due to methodological limitations in text mining. Large language models (LLMs) like Bidirectional Encoder Representations from Transformers (BERT) have shown progress in a range of natural language processing tasks but have not yet been evaluated on adverse event (AE) detection. We adapted a new clinical LLM, University of California - San Francisco (UCSF)-BERT, to identify serious AEs (SAEs) occurring after treatment with a non-steroid immunosuppressant for inflammatory bowel disease (IBD). We compared this model to other language models that have previously been applied to AE detection. We annotated 928 outpatient IBD notes corresponding to 928 individual patients with IBD for all SAE-associated hospitalizations occurring after treatment with a non-steroid immunosuppressant. These notes contained 703 SAEs in total, the most common of which was failure of intended efficacy. Out of eight candidate models, UCSF-BERT achieved the highest numerical performance on identifying drug-SAE pairs from this corpus (accuracy 88-92%, macro F1 61-68%), with 5-10% greater accuracy than previously published models. UCSF-BERT was significantly superior at identifying hospitalization events emergent to medication use (P < 0.01). LLMs like UCSF-BERT achieve numerically superior accuracy on the challenging task of SAE detection from clinical notes compared with prior methods. Future work is needed to adapt this methodology to improve model performance and evaluation using multicenter data and newer architectures like Generative pre-trained transformer (GPT). Our findings support the potential value of using large language models to enhance pharmacovigilance.

Trends in Influenza Vaccination Rates among a Medicaid Population from 2016 to 2021

Seasonal influenza is a leading cause of death in the U.S., causing significant morbidity, mortality, and economic burden. Despite the proven efficacy of vaccinations, rates remain notably low, especially among Medicaid enrollees. Leveraging Medicaid claims data, this study characterizes influenza vaccination rates among Medicaid enrollees and aims to elucidate factors influencing vaccine uptake, providing insights that might also be applicable to other vaccine-preventable diseases, including COVID-19. This study used Medicaid claims data from nine U.S. states (2016-2021], encompassing three types of claims: fee-for-service, major Medicaid managed care plan, and combined. We included Medicaid enrollees who had an in-person healthcare encounter during an influenza season in this period, excluding those under 6 months of age, over 65 years, or having telehealth-only encounters. Vaccination was the primary outcome, with secondary outcomes involving in-person healthcare encounters. Chi-square tests, multivariable logistic regression, and Fisher's exact test were utilized for statistical analysis. A total of 20,868,910 enrollees with at least one healthcare encounter in at least one influenza season were included in the study population between 2016 and 2021. Overall, 15% (N = 3,050,471) of enrollees received an influenza vaccine between 2016 and 2021. During peri-COVID periods, there was an increase in vaccination rates among enrollees compared to pre-COVID periods, from 14% to 16%. Children had the highest influenza vaccination rates among all age groups at 29%, whereas only 17% were of 5-17 years, and 10% were of the 18-64 years were vaccinated. We observed differences in the likelihood of receiving the influenza vaccine among enrollees based on their health conditions and medical encounters. In a study of Medicaid enrollees across nine states, 15% received an influenza vaccine from July 2016 to June 2021. Vaccination rates rose annually, peaking during peri-COVID seasons. The highest uptake was among children (6 months-4 years), and the lowest was in adults (18-64 years). Female gender, urban residency, and Medicaid-managed care affiliation positively influenced uptake. However, mental health and substance abuse disorders decreased the likelihood. This study, reliant on Medicaid claims data, underscores the need for outreach services.

Algorithmic identification of treatment-emergent adverse events from clinical notes using large language models: a pilot study in inflammatory bowel disease

Background and Aims

Outpatient clinical notes are a rich source of information regarding drug safety. However, data in these notes are currently underutilized for pharmacovigilance due to methodological limitations in text mining. Large language models (LLM) like BERT have shown progress in a range of natural language processing tasks but have not yet been evaluated on adverse event detection.

Methods

We adapted a new clinical LLM, UCSF BERT, to identify serious adverse events (SAEs) occurring after treatment with a non-steroid immunosuppressant for inflammatory bowel disease (IBD). We compared this model to other language models that have previously been applied to AE detection.

Results

We annotated 928 outpatient IBD notes corresponding to 928 individual IBD patients for all SAE-associated hospitalizations occurring after treatment with a non-steroid immunosuppressant. These notes contained 703 SAEs in total, the most common of which was failure of intended efficacy. Out of 8 candidate models, UCSF BERT achieved the highest numerical performance on identifying drug-SAE pairs from this corpus (accuracy 88-92%, macro F1 61-68%), with 5-10% greater accuracy than previously published models. UCSF BERT was significantly superior at identifying hospitalization events emergent to medication use (p < 0.01).

Conclusions

LLMs like UCSF BERT achieve numerically superior accuracy on the challenging task of SAE detection from clinical notes compared to prior methods. Future work is needed to adapt this methodology to improve model performance and evaluation using multi-center data and newer architectures like GPT. Our findings support the potential value of using large language models to enhance pharmacovigilance.

Novel computational methods on electronic health record yields new estimates of transfusion-associated circulatory overload in populations enriched with high-risk patients

BACKGROUND

Transfusion-associated circulatory overload (TACO) is a severe adverse reaction (AR) contributing to the leading cause of mortality associated with transfusions. As strategies to mitigate TACO have been increasingly adopted, an update of prevalence rates and risk factors associated with TACO using the growing sources of electronic health record (EHR) data can help understand transfusion safety.

STUDY DESIGN AND METHODS

This retrospective study aimed to provide a timely and reproducible assessment of prevalence rates and risk factors associated with TACO. Novel natural language processing methods, now made publicly available on GitHub, were developed to extract ARs from 3178 transfusion reaction reports. Other patient-level data were extracted computationally from UCSF EHR between 2012 and 2022. The odds ratio estimates of risk factors were calculated using a multivariate logistic regression analysis with case-to-control matched on sex and age at a ratio of 1:5.

RESULTS

A total of 56,208 patients received transfusions (total 573,533 units) at UCSF during the study period and 102 patients developed TACO. The prevalence of TACO was estimated to be 0.2% per patient (102/total 56,208). Patients with a history of coagulopathy (OR, 1.36; 95% CI, 1.04-1.79) and transplant (OR, 1.99; 95% CI, 1.48-2.68) were associated with increased odds of TACO.

DISCUSSION

While TACO is a serious AR, events remained rare, even in populations enriched with high-risk patients. Novel computational methods can be used to find and continually surveil for transfusion ARs. Results suggest that patients with history or presence of coagulopathy and organ transplant should be carefully monitored to mitigate potential risks of TACO.

Dataset of night-time emissions of the Earth in the near UV range (290-430 nm), with 6.3 km resolution in the latitude range -51.6<L<+51.6 degrees, acquired on board the International Space Station with the Mini-EUSO detector

The data presented in this article are related to the research paper entitled "Observation of night-time emissions of the Earth in the near UV range from the International Space Station with the Mini-EUSO detector" (Remote Sensing of Environment, Volume 284, January 2023, 113336, https://doi.org/10.1016/j.rse.2022.113336). The data have been acquired with the Mini-EUSO detector, an UV telescope operating in the range 290-430 nm and located inside the International Space Station. The detector was launched in August 2019, and it has started operations from the nadir-facing UV-transparent window in the Russian Zvezda module in October 2019. The data presented here refer to 32 sessions acquired between 2019-11-19 and 2021-05-06. The instrument consists of a Fresnel-lens optical system and a focal surface composed of 36 multi-anode photomultiplier tubes, each with 64 channels, for a total of 2304 channels with single photon counting sensitivity. The telescope, with a square field-of-view of 44°, has a spatial resolution on the Earth surface of 6.3 km and saves triggered transient phenomena with a temporal resolution of 2.5 µs and 320 µs. The telescope also operates in continuous acquisition at a 40.96 ms scale. In this article, large-area night-time UV maps obtained processing the 40.96 ms data, taking averages over regions of some specific geographical areas (e.g., Europe, North America) and over the entire globe, are presented. Data are binned into 0.1° × 0.1° or 0.05° × 0.05° cells (depending on the scale of the map) over the Earth's surface. Raw data are made available in the form of tables (latitude, longitude, counts) and .kmz files (containing the .png images). These are - to the best of our knowledge - the highest sensitivity data in this wavelength range and can be of use to various disciplines.

Search for Dark Matter Axions with CAST-CAPP

The CAST-CAPP axion haloscope, operating at CERN inside the CAST dipole magnet, has searched for axions in the 19.74 μeV to 22.47 μeV mass range. The detection concept follows the Sikivie haloscope principle, where Dark Matter axions convert into photons within a resonator immersed in a magnetic field. The CAST-CAPP resonator is an array of four individual rectangular cavities inserted in a strong dipole magnet, phase-matched to maximize the detection sensitivity. Here we report on the data acquired for 4124 h from 2019 to 2021. Each cavity is equipped with a fast frequency tuning mechanism of 10 MHz/ min between 4.774 GHz and 5.434 GHz. In the present work, we exclude axion-photon couplings for virialized galactic axions down to g_aγγ = 8 × 10⁻¹⁴ GeV⁻¹ at the 90% confidence level. The here implemented phase-matching technique also allows for future large-scale upgrades.

Haloscopes aim at detecting axions by converting them into photons using high-quality resonant cavities, where the cavity resonance should be tuned with the unknown axion mass. Here, the authors improve exclusion limits using four phase-matched resonant cavities and a fast frequency scanning technique.

Detection of allergic transfusion-related adverse events from electronic medical records

BACKGROUND

Transfusion-related adverse events can be unrecognized and unreported. As part of the US Food and Drug Administration's Center for Biologics Evaluation and Research Biologics Effectiveness and Safety initiative, we explored whether machine learning methods, such as natural language processing (NLP), can identify and report transfusion allergic reactions (ARs) from electronic health records (EHRs).

STUDY DESIGN AND METHODS

In a 4-year period, all 146 reported transfusion ARs were pulled from a database of 86,764 transfusions in an academic health system, along with a random sample of 605 transfusions without reported ARs. Structured and unstructured EHR data were retrieved, including demographics, new symptoms, medications, and lab results. In unstructured data, evidence from clinicians' notes, test results, and prescriptions fields identified transfusion ARs, which were used to extract NLP features. Clinician reviews of selected validation cases assessed and confirmed model performance.

RESULTS

Clinician reviews of selected validation cases yielded a sensitivity of 67.9% and a specificity of 97.5% at a threshold of 0.9, with a positive predictive value (PPV) of 84%, estimated to 4.5% when extrapolated to match transfusion AR incidence in the full transfusion dataset. A higher threshold achieved sensitivity of 43% with specificity/PPV of 100% in our validation set. Essential features predicting ARs were recognized transfusion reactions, administration of antihistamines or glucocorticoids, and skin symptoms (e.g., hives and itching). Removal of NLP features decreased model performance.

DISCUSSION

NLP algorithms can identify transfusion reactions from the EHR with a reasonable level of precision for subsequent clinician review and confirmation.

Early administration of COVID-19 convalescent plasma with high titer antibody content by live viral neutralization assay is associated with modest clinical efficacy

The efficacy of COVID‐19 convalescent plasma (CCP) as a treatment for hospitalized patients with COVID‐19 remains somewhat controversial; however, many studies have not evaluated CCP documented to have high neutralizing antibody titer by a highly accurate assay. To evaluate the correlation of the administration of CCP with titer determined by a live viral neutralization assay with 7‐ and 28‐day death rates during hospitalization, a total of 23 118 patients receiving a single unit of CCP were stratified into two groups: those receiving high titer CCP (>250 50% inhibitory dilution, ID50; n = 13 636) or low titer CCP (≤250 ID50; n = 9482). Multivariable Cox regression was performed to assess risk factors. Non‐intubated patients who were transfused with high titer CCP showed 1.1% and 1.7% absolute reductions in overall 7‐ and 28‐day death rates, respectively, compared to those non‐intubated patients receiving low titer CCP. No benefit of CCP was observed in intubated patients. The relative benefit of high titer CCP was confirmed in multivariable Cox regression. Administration of CCP with high titer antibody content determined by live viral neutralization assay to non‐intubated patients is associated with modest clinical efficacy. Although shown to be only of modest clinical benefit, CCP may play a role in the future should viral variants develop that are not neutralized by other available therapeutics.

Analyzing real world data of blood transfusion adverse events: Opportunities and challenges

BACKGROUND

Blood transfusions are a vital component of modern healthcare, yet adverse reactions to blood product transfusions can cause morbidity, and rarely result in mortality. Therefore, accurate reporting of transfusion related adverse events (TRAEs) is paramount to improved transfusion practice. This study aims to investigate real-world data (RWD) on TRAEs by evaluating differences between ICD 9/10-based electronic health records (EHR) and blood bank-specific reporting.

STUDY DESIGN AND METHODS

TRAE data were retrospectively collected from a blood bank-specific database between Jan 2015 and June 2019 as the reference data source and compared it to ICD 9/10 diagnostic codes corresponding to various TRAEs. Seven reactions that have corresponding ICD 9/10 diagnostic codes were evaluated: Transfusion related circulatory overload (TACO), transfusion related acute lung injury (TRALI), febrile non-hemolytic reaction (FNHTR), transfusion-related anaphylactic reaction (TRA), acute hemolytic transfusion reaction (AHTR), delayed hemolytic transfusion reaction (DHTR), and delayed serologic reaction (DSTR). These accounted for 33% of the TRAEs at an academic institution during the study period.

RESULTS

Among 18637 adult blood transfusion recipients, there were 229 unique patients with 263 TRAE related ICD codes in the EHR, while there were 191 unique patients with 287 TRAEs identified in the blood bank database. None of the categories of reaction we investigated had perfect alignment between ICD 9/10 codes and blood bank specific diagnoses.

DISCUSSION

Multiple systemic challenges were identified that hinder effective reporting of TRAEs. Identifying factors causing inconsistent reporting between blood banks and EHRs is paramount to developing effective workability between these electronic systems, as well as across clinical and laboratory teams.

The Food and Drug Administration Biologics Effectiveness and Safety Initiative Facilitates Detection of Vaccine Administrations From Unstructured Data in Medical Records Through Natural Language Processing

Introduction: The Food and Drug Administration Center for Biologics Evaluation and Research conducts post-market surveillance of biologic products to ensure their safety and effectiveness. Studies have found that common vaccine exposures may be missing from structured data elements of electronic health records (EHRs), instead being captured in clinical notes. This impacts monitoring of adverse events following immunizations (AEFIs). For example, COVID-19 vaccines have been regularly administered outside of traditional medical settings. We developed a natural language processing (NLP) algorithm to mine unstructured clinical notes for vaccinations not captured in structured EHR data.

Methods: A random sample of 1,000 influenza vaccine administrations, representing 995 unique patients, was extracted from a large U.S. EHR database. NLP techniques were used to detect administrations from the clinical notes in the training dataset [80% (N = 797) of patients]. The algorithm was applied to the validation dataset [20% (N = 198) of patients] to assess performance. Full medical charts for 28 randomly selected administration events in the validation dataset were reviewed by clinicians. The NLP algorithm was then applied across the entire dataset (N = 995) to quantify the number of additional events identified.

Results: A total of 3,199 administrations were identified in the structured data and clinical notes combined. Of these, 2,740 (85.7%) were identified in the structured data, while the NLP algorithm identified 1,183 (37.0%) administrations in clinical notes; 459 were not also captured in the structured data. This represents a 16.8% increase in the identification of vaccine administrations compared to using structured data alone. The validation of 28 vaccine administrations confirmed 27 (96.4%) as “definite” vaccine administrations; 18 (64.3%) had evidence of a vaccination event in the structured data, while 10 (35.7%) were found solely in the unstructured notes.

Discussion: We demonstrated the utility of an NLP algorithm to identify vaccine administrations not captured in structured EHR data. NLP techniques have the potential to improve detection of vaccine administrations not otherwise reported without increasing the analysis burden on physicians or practitioners. Future applications could include refining estimates of vaccine coverage and detecting other exposures, population characteristics, and outcomes not reliably captured in structured EHR data.

Development and Validation of a Treatment Benefit Index to Identify Hospitalized Patients With COVID-19 Who May Benefit From Convalescent Plasma

Importance

Identifying which patients with COVID-19 are likely to benefit from COVID-19 convalescent plasma (CCP) treatment may have a large public health impact.

Objective

To develop an index for predicting the expected relative treatment benefit from CCP compared with treatment without CCP for patients hospitalized for COVID-19 using patients' baseline characteristics.

Design, Setting, and Participants

This prognostic study used data from the COMPILE study, ie, a meta-analysis of pooled individual patient data from 8 randomized clinical trials (RCTs) evaluating CCP vs control in adults hospitalized for COVID-19 who were not receiving mechanical ventilation at randomization. A combination of baseline characteristics, termed the treatment benefit index (TBI), was developed based on 2287 patients in COMPILE using a proportional odds model, with baseline characteristics selected via cross-validation. The TBI was externally validated on 4 external data sets: the Expanded Access Program (1896 participants), a study conducted under Emergency Use Authorization (210 participants), and 2 RCTs (with 80 and 309 participants).

Exposure

Receipt of CCP.

Main Outcomes and Measures

World Health Organization (WHO) 11-point ordinal COVID-19 clinical status scale and 2 derivatives of it (ie, WHO score of 7-10, indicating mechanical ventilation to death, and WHO score of 10, indicating death) at day 14 and day 28 after randomization. Day 14 WHO 11-point ordinal scale was used as the primary outcome to develop the TBI.

Results

A total of 2287 patients were included in the derivation cohort, with a mean (SD) age of 60.3 (15.2) years and 815 (35.6%) women. The TBI provided a continuous gradation of benefit, and, for clinical utility, it was operationalized into groups of expected large clinical benefit (B1; 629 participants in the derivation cohort [27.5%]), moderate benefit (B2; 953 [41.7%]), and potential harm or no benefit (B3; 705 [30.8%]). Patients with preexisting conditions (diabetes, cardiovascular and pulmonary diseases), with blood type A or AB, and at an early COVID-19 stage (low baseline WHO scores) were expected to benefit most, while those without preexisting conditions and at more advanced stages of COVID-19 could potentially be harmed. In the derivation cohort, odds ratios for worse outcome, where smaller odds ratios indicate larger benefit from CCP, were 0.69 (95% credible interval [CrI], 0.48-1.06) for B1, 0.82 (95% CrI, 0.61-1.11) for B2, and 1.58 (95% CrI, 1.14-2.17) for B3. Testing on 4 external datasets supported the validation of the derived TBIs.

Conclusions and Relevance

The findings of this study suggest that the CCP TBI is a simple tool that can quantify the relative benefit from CCP treatment for an individual patient hospitalized with COVID-19 that can be used to guide treatment recommendations. The TBI precision medicine approach could be especially helpful in a pandemic.

Opportunities and challenges for applying model-informed drug development approaches to gene therapies

As part of the US Food and Drug Administration (FDA)'s Prescription Drug User Fee Act (PDUFA) VI commitments, the Center for Biologics Evaluation and Research (CBER) and Center for Drug Evaluation and Research (CDER) are conducting a model-informed drug development (MIDD) pilot program. Sponsor(s) who apply and are selected will be granted meetings that aim to facilitate the application of MIDD approaches throughout the product development lifecycle and the regulatory process. Due to their complex mechanisms of action and limited clinical experience, cell and gene therapies have the potential to benefit from the application of MIDD methods, which may facilitate their safety and efficacy evaluations. Leveraging data that are generated from all stages of drug development into appropriate modeling and simulation techniques that inform decisions remains challenging. Additional discussions regarding the application of quantitative modeling approaches to drug development decisions, such as through the MIDD pilot program, may be crucial for both the sponsor(s) and regulatory review teams. Here, we share some perspectives on the opportunities and challenges for utilizing MIDD approaches for product review, which we hope will encourage investigators to publish their experiences and application of MIDD in gene therapy product development.

COVID-19 reopening strategies at the county level in the face of uncertainty: Multiple Models for Outbreak Decision Support

Policymakers make decisions about COVID-19 management in the face of considerable uncertainty. We convened multiple modeling teams to evaluate reopening strategies for a mid-sized county in the United States, in a novel process designed to fully express scientific uncertainty while reducing linguistic uncertainty and cognitive biases. For the scenarios considered, the consensus from 17 distinct models was that a second outbreak will occur within 6 months of reopening, unless schools and non-essential workplaces remain closed. Up to half the population could be infected with full workplace reopening; non-essential business closures reduced median cumulative infections by 82%. Intermediate reopening interventions identified no win-win situations; there was a trade-off between public health outcomes and duration of workplace closures. Aggregate results captured twice the uncertainty of individual models, providing a more complete expression of risk for decision-making purposes.

Comparing clotting factors attributes across different methods of preference elicitation in haemophilia patients

INTRODUCTION

Emerging, systematic approaches for capturing patient input, such as preference elicitation, can provide valuable information for the benefit-risk assessment of medical products for treating bleeding disorders, such as haemophilia.

AIM

This study aims to identify existing and develop new methods to capture, rank and summarize preference scores for clotting factor therapies.

METHODS

Haemophilia patient preference data were compiled from studies identified through literature review and publicly available US FDA patient-focused drug development meeting documents. Text mining was performed to identify major themes across studies. A standardized preference score was estimated and aggregated.

RESULTS

Ten preference studies that employed qualitative (n = 3), and quantitative methods (n = 7) met the inclusion criteria. Text mining of qualitative and quantitative studies revealed similar themes as the standardized preference attribute importance. We found that seven quantitative studies employed discrete choice experiments (DCE)/conjoint analysis (CA) and examined a range of 5-12 attributes. For DCE/CA studies published prior to 2014 (n = 4), safety attributes (inhibitor and viral safety) were among the most important attributes, accounting for ~46% of the total utility measured. DCE/CA studies published after 2014 (n = 3) focused on frequency of infusion and reduction of bleeding risk, accounting for ~67% of the total utility. Interestingly, two studies that used different preference elicitation approaches (DCE and a monadic conjoint approach) both ranked infusion frequency as the most important attribute.

CONCLUSIONS

Although there are few published patient preference studies for haemophilia, the results of this study can be viewed in the larger context of enhancing scientific methods of incorporating patient input in medical product development.

Search for solar axions by the CERN axion solar telescope with 3He buffer gas: closing the hot dark matter gap

The CERN Axion Solar Telescope has finished its search for solar axions with (3)He buffer gas, covering the search range 0.64 eV ≲ ma ≲ 1.17 eV. This closes the gap to the cosmological hot dark matter limit and actually overlaps with it. From the absence of excess x rays when the magnet was pointing to the Sun we set a typical upper limit on the axion-photon coupling of gaγ ≲ 3.3 × 10(-10)  GeV(-1) at 95% C.L., with the exact value depending on the pressure setting. Future direct solar axion searches will focus on increasing the sensitivity to smaller values of gaγ, for example by the currently discussed next generation helioscope International AXion Observatory.

Search for sub-eV mass solar axions by the CERN Axion Solar Telescope with 3He buffer gas

The CERN Axion Solar Telescope (CAST) has extended its search for solar axions by using (3)He as a buffer gas. At T=1.8 K this allows for larger pressure settings and hence sensitivity to higher axion masses than our previous measurements with (4)He. With about 1 h of data taking at each of 252 different pressure settings we have scanned the axion mass range 0.39 eV≲m(a)≲0.64 eV. From the absence of excess x rays when the magnet was pointing to the Sun we set a typical upper limit on the axion-photon coupling of g(aγ)≲2.3×10(-10) GeV(-1) at 95% C.L., the exact value depending on the pressure setting. Kim-Shifman-Vainshtein-Zakharov axions are excluded at the upper end of our mass range, the first time ever for any solar axion search. In the future we will extend our search to m(a)≲1.15 eV, comfortably overlapping with cosmological hot dark matter bounds.

First results from the CERN axion solar telescope

Hypothetical axionlike particles with a two-photon interaction would be produced in the sun by the Primakoff process. In a laboratory magnetic field ("axion helioscope"), they would be transformed into x-rays with energies of a few keV. Using a decommissioned Large Hadron Collider test magnet, the CERN Axion Solar Telescope ran for about 6 months during 2003. The first results from the analysis of these data are presented here. No signal above background was observed, implying an upper limit to the axion-photon coupling g(agamma)<1.16x10(-10) GeV-1 at 95% C.L. for m(a) less, similar 0.02 eV. This limit, assumption-free, is comparable to the limit from stellar energy-loss arguments and considerably more restrictive than any previous experiment over a broad range of axion masses.

Effect of stimulation parameters on electrically evoked auditory brainstem responses

It is evident that the conventional technique for cochlear implant adjustment is not suitable for children in their first years of life. In order to find a solution to this problem, the possibility of electrically evoked auditory brainstem response (EABR) recording was investigated. EABRs were recorded in 9 patients with the Nucleus multichannel cochlear implant. The main problems that have to be solved during EABR recording in cochlear implantees are: i) EABR distortion due to the stimulus artefact: and ii) difference in the stimulus presentation rate during EABR registration (low pulse rate) and conventional psychophysical threshold estimation (high pulse rate) in cochlear implant patients. The influence of stimulus artefact on the recording results was minimized by setting the implant to the widest amplifier frequency band and by zeroing the initial segment containing the stimulus artefact with subsequent zero-phase digital filtering. The dependence of the EABR amplitude and latency on the stimulus intensity, width, electrode location and interstimulus interval was investigated. It was concluded that despite the difference revealed between absolute values of EABR thresholds and psychophysical threshold levels, it is possible to calculate implant adjustment parameters based on the EABR data with the proper correction applied.