Automated classification of cancer morphology from Italian pathology reports using Natural Language Processing techniques: A rule-based approach.

Pathology reports represent a primary source of information for cancer registries. Hospitals routinely process high volumes of free-text reports, a valuable source of information regarding cancer diagnosis for improving clinical care and supporting research. Information extraction and coding of textual unstructured data is typically a manual, labour-intensive process. There is a need to develop automated approaches to extract meaningful information from such texts in a reliable and accurate way. In this scenario, Natural Language Processing (NLP) algorithms offer a unique opportunity to automatically encode the unstructured reports into structured data, thus representing a potential powerful alternative to expensive manual processing. However, notwithstanding the increasing interest in this area, there is still limited availability of NLP approaches for pathology reports in languages other than English, including Italian, to date. The aim of our work was to develop an automated algorithm based on NLP techniques, able to identify and classify the morphological content of pathology reports in the Italian language with micro-averaged performance scores higher than 95%. Specifically, a novel, domain-specific classifier that uses linguistic rules was developed and tested on 27,239 pathology reports from a single Italian oncological centre, following the International Classification of Diseases for Oncology morphology classification standard (ICD-O-M). The proposed classification algorithm achieved successful results with a micro-F1 score of 98.14% on 9594 pathology reports in the test dataset. This algorithm relies on rules defined on data from a single hospital that is specifically dedicated to cancer, but it is based on general processing steps which can be applied to different datasets. Further research will be important to demonstrate the generalizability of the proposed approach on a larger corpus from different hospitals.

Apps for Hearing Science and Care.

PURPOSE: Our research aims at the identification and assessment of applications (referred to as apps) in the hearing health care domain. This research forum article presents an overview of the current availability, affordability, and variety of hearing-related apps. METHOD: The available apps were reviewed by searching on the leading platforms (iOS, Android, Windows Phone stores) using the keywords hearing, audiology, audio, auditory, speech, language, tinnitus, hearing loss, hearing aid, hearing sys tem, cochlear implant, implantable device, auditory training, hearing rehabilitation, and assistive technology/tool/device. O n the bas is of the offered services, apps were classified into 4 application domains: (a) screening and assessment, (b) intervention and rehabilitation, (c) education and information, and (d) assistive tools. CONCLUSIONS: A large variety of apps are available in the hearing health care domain. These cover a wide range of services for people with hearing or communication problems as well as for hearing professionals, families, or informal caregivers. This evolution can potentially bring along considerable advantages and improved outcomes in the field of hearing health care. Nevertheless, potential risks and threats (e.g., safety, quality, effectiveness, privacy, and regulation) should not be overlooked. Significant research­particularly in terms of assessment and guidance­is still needed for the informed, aware, and safe adoption of hearing-related apps by patients and professionals.

Development of a test of suprathreshold acuity in noise in Brazilian Portuguese: a new method for hearing screening and surveillance.

This paper describes the development of a speech-in-noise test for hearing screening and surveillance in Brazilian Portuguese based on the evaluation of suprathreshold acuity performances. The SUN test (Speech Understanding in Noise) consists of a list of intervocalic consonants in noise presented in a multiple-choice paradigm by means of a touch screen. The test provides one out of three possible results: "a hearing check is recommended" (red light), "a hearing check would be advisable" (yellow light), and "no hearing difficulties" (green light) (Paglialonga et al., Comput. Biol. Med. 2014). This novel test was developed in a population of 30 normal hearing young adults and 101 adults with varying degrees of hearing impairment and handicap, including normal hearing. The test had 84% sensitivity and 76% specificity compared to conventional pure-tone screening and 83% sensitivity and 86% specificity to detect disabling hearing impairment. The test outcomes were in line with the degree of self-perceived hearing handicap. The results found here paralleled those reported in the literature for the SUN test and for conventional speech-in-noise measures. This study showed that the proposed test might be a viable method to identify individuals with hearing problems to be referred to further audiological assessment and intervention.

A bispectral approach to analyze nonlinear cochlear active mechanisms in transient evoked otoacoustic emissions.

A new approach to study nonlinearity in cochlear active mechanisms, as evaluated in transient evoked otoacoustic emissions (TEOAEs), is presented. TEOAEs are signals generated in the cochlea by a mix of linear and nonlinear mechanisms. This new approach was designed to complement the traditional TEOAE analysis performed by currently available systems used in objective hearing screening and assessment. Nonlinearity of TEOAEs was studied by means of the bispectrum, which is able to find out quadratic frequency couplings (QFCs) that occur when a frequency is not only generated by an independent cochlear source, but it is the result of the interaction among a number of cochlear sources. To fit with the technical constraints of currently available TEOAE systems, the bispectrum was estimated by the third-order scaled polyperiodogram. The proposed method was characterized with synthesized TEOAEs as a function of the main TEOAE parameters and then used to analyze TEOAEs recorded in normal hearing adults and full-term neonates. Results revealed the presence of QFCs in both adult and neonatal TEOAEs, with peculiar patterns and significantly different frequency content in the two groups: adults had QFCs mainly around 2 kHz and neonates had QFCs mainly in the range 3.5-4 kHz.

Introduction to the AJA research forum on hearing screening in adults and older adults.

PURPOSE: To illustrate the overall project that led to the development of a series of research forums highlighting several key contributions to AHS 2012, the 2nd International Conference on Adult Hearing Screening, in Cernobbio (Lake Como), Italy, and, in particular, to provide an overview of the first research forum, "Hearing Screening in Adults and Older Adults," which contains a set of brief papers that tackle prominent issues related to adult hearing screening: guiding principles for adult screening, development of methods and technologies, program implementation and evaluation, possible future scenarios, and health policy issues.

Time-frequency analysis of transient-evoked otoacoustic emissions in children exposed to carboplatin chemotherapy.

The aims of this study were to characterize and quantify time-frequency changes in transient-evoked otoacoustic emissions (TEOAEs) recorded in children diagnosed with retinoblastoma who were receiving carboplatin chemotherapy. A signal processing technique, the wavelet transform (WT), was used to analyze TEOAE waveforms in narrow-band frequency components. Ten children (aged 3-72 months) diagnosed with unilateral or bilateral retinoblastoma were enrolled in the study. TEOAEs were acquired from the children with linear sequences of 70 dB peak equivalent SPL clicks. After WT analysis, TEOAE energy, latency and normalized energy in the narrow-band frequency components were compared before and during carboplatin chemotherapy treatment (average dose 1693 mg/m2). On a group basis, no significant differences (p>0.05) in the TEOAE energy, latency or normalized energy before and after carboplatin treatment were observed. There were decreases in normalized energy on an individual basis in 10 out of 18 ears in the sample. Exposure to carboplatin chemotherapy did not cause significant changes in TEOAE energy, latency and normalized energy during treatment. However, long-term monitoring of hearing with measurements of TEOAEs is warranted, given the risks of delayed hearing loss in some children receiving carboplatin chemotherapy.

Computational exposure assessment of electromagnetic fields generated by an RFID system for mother--newborn identity reconfirmation.

Radio frequency identification (RFID) is an innovative technology currently applied in a large number of industrial and consumer applications. The spread of RFID technology does not correspond to a parallel increase in studies on its possible impact on health in terms of electromagnetic field (EMF) exposure. The aim of this paper is to estimate, by computational techniques, the EMF generated by passive RFID systems for mother-newborn identity reconfirmation. The computation was performed on realistic models of newborn and mother for three different reader positions. The compliance with EMF exposure guidelines was investigated as a function of the change in reader-tag specifications (magnetic field threshold and maximum distance of the reader to awake the tag) and time of use of the reader close to the body. The results show that attention should be paid to the identification of the optimal reader-tag technical specifications to be used in this type of application. That should be done by an accurate exposure assessment investigation, in particular for newborn exposure. The need to reduce the exposure time as much as possible indicates the importance of specific training on the practical applications of the RFID (DATALOGIC J-series, Bologna, Italy) device.