Clustering of recreational divers by their health conditions in a database of a citizen science project.

Divers Alert Network Europe has created a database with a large amount of dive-related data that has been collected since 1993 within the scope of the Diving Safety Laboratory citizen science project. The main objectives of this study are the grouping divers by their health information and revealing significant differences in diving parameters using data mining techniques. Due to the methodology of the project, data cleaning was performed before applying clustering methods in order to eliminate potential mistakes resulting from inaccuracies and missing information. Despite the fact that 63% of the data were lost during the cleaning phase, the remaining 1,169 "clean" diver data enabled meaningful clustering using the "two-step" method. Experienced male divers without any health problems are in Cluster 1. Male and female divers with health problems and high rates of cigarette smoking are in Cluster 2; healthy, overweight divers are in Cluster 3. There are significant differences in terms of dive parameters including pre- and post-dive conditions with respect to each group, such as: exercise level, alcohol consumption, thermal comfort, equipment malfunctions, and maximum depth. The study proves the usefulness of citizen science projects, while data collection methodologies can be improved to decrease potential mistakes resulting from inconsistencies, inaccuracies and missing information. It is hypothesized that if naturally occurring clusters of divers were identified it might be possible to identify risk factors arising from different clusters while merging the database with other dive accident databases in the future.

Design and Validation of a Breathing Detection System for Scuba Divers.

Drowning is the major cause of death in self-contained underwater breathing apparatus (SCUBA) diving. This study proposes an embedded system with a live and light-weight algorithm which detects the breathing of divers through the analysis of the intermediate pressure (IP) signal of the SCUBA regulator. A system composed mainly of two pressure sensors and a low-power microcontroller was designed and programmed to record the pressure sensors signals and provide alarms in absence of breathing. An algorithm was developed to analyze the signals and identify inhalation events of the diver. A waterproof case was built to accommodate the system and was tested up to a depth of 25 m in a pressure chamber. To validate the system in the real environment, a series of dives with two different types of workload requiring different ranges of breathing frequencies were planned. Eight professional SCUBA divers volunteered to dive with the system to collect their IP data in order to participate to validation trials. The subjects underwent two dives, each of 52 min on average and a maximum depth of 7 m. The algorithm was optimized for the collected dataset and proved a sensitivity of inhalation detection of 97.5% and a total number of 275 false positives (FP) over a total recording time of 13.9 h. The detection algorithm presents a maximum delay of 5.2 s and requires only 800 bytes of random-access memory (RAM). The results were compared against the analysis of video records of the dives by two blinded observers and proved a sensitivity of 97.6% on the data set. The design includes a buzzer to provide audible alarms to accompanying dive buddies which will be triggered in case of degraded health conditions such as near drowning (absence of breathing), hyperventilation (breathing frequency too high) and skip-breathing (breathing frequency too low) measured by the improper breathing frequency. The system also measures the IP at rest before the dive and indicates with flashing light-emitting diodes and audible alarm the regulator malfunctions due to high or low IP that may cause fatal accidents during the dive by preventing natural breathing. It is also planned to relay the alarm signal to underwater and surface rescue authorities by means of acoustic communication.

Commercial diver selection using multiple-criteria decision-making methods.

INTRODUCTION: Personnel selection for different commercial diving jobs is time-consuming and subjective, This paper proposes a combination of two multiple-criteria decision-making (MCDM) methods to provide an objective tool for evaluation according to two main selection criteria: work experience and physical fitness. METHOD: Subcriteria were computed using the analytic hierarchy process (AHP). By consulting two field professionals, subcriteria for work experience were determined as: working hours on the project type, hand tools, hydraulic tools, pneumatic tools, LP air jet and water lift/dredge, wet bell diving and paramedic training level. Determined by three medical experts, the subcriteria for physical fitness were: age, VO2Max, critical flicker fusion frequency (CFFF), psychomotor performance, and visual and hearing acuities. The pair-wise comparison matrices used to calculate subcriteria weights are filled by the same experts. Eight divers were included in the analysis. The AHP yielded scores of work experience for seven different project types and a physical fitness score for each diver. These scores were used in data envelopment analysis (DEA), to obtain an aggregate ranking of the divers. RESULT: The methodology was able to differentiate between qualified and unqualified divers. Divers were scored between 0 and 1 for each project type. The overall ranking of divers according to the average of the seven project types' scores was: 1. Diver 7 (1.0000); 2. Diver 5 (0.9486); 3, Diver 8 (0.9453); 4. Diver 2 (0.9421); 5. Diver 3 (0.8441); 6. Diver 4 (0.7804); 7. Diver 6 (0.6554); 8. Diver 1 (0.3931). DISCUSSION: The proposed methodology allows decision-makers to perform evaluations objectively and systematically, reducing personal conflicts and confusions resulting from subjective immethodical judgments. This methodology is to be applied in real projects to validate the selection criteria and confirm the results.

Decompression illness medically reported by hyperbaric treatment facilities: cluster analysis of 1929 cases.

INTRODUCTION: The term decompression illness (DCI) describes maladies resulting from inadequate decompression, but there is little consensus concerning clinically useful DCI subclasses. Our aim was to explore an objective DCI classification using multivariate statistics to assess naturally associated clusters of DCI manifestations. We also evaluated their mapping onto other DCI classifications and investigated the association with therapeutic outcome. METHODS: We defined the optimal number of clusters using "two-step" cluster analysis and Bayesian information criterion with confirmation by hierarchical clustering with squared Euclidian distances and Ward's method. The data were 1929 DCI cases reported by hyperbaric chambers to the Divers Alert Network (DAN America) from 1999-2003. RESULTS: Four robust and highly significant clusters of DCI manifestations were demonstrated containing 300, 741, 333, and 555 patients. Each cluster had characteristic manifestations. Cluster 1 was effectively pain only. For Cluster 2, characteristic manifestations included numbness, paresthesia, and decreased skin sensitivity; for Cluster 3, malaise, paralysis, muscular weakness, and bladder-bowel dysfunction; and for Cluster 4, hearing loss, localized skin swelling, tinnitus, skin rash and mottling, confusion, dyspnea/chokes, muscular problems, vision problems, altered consciousness, headache, vertigo, nausea, fatigue, dizziness, and abnormal sensations. DISCUSSION: Internal reliability was confirmed by arbitrarily dividing the dataset into two parts and repeating the analysis. The clusters mapped poorly onto traditional DCI categories (AGE, Type I DCS, Type II DCS), but more specifically onto the Perceived Severity Index (PSI). All three classification methods (DCI, Cluster, PSI) predicted complete relief of manifestations equally well. We conclude that cluster analysis is an objective method for classifying DCI manifestations independent of clinical judgment.

Safety Priorities and Underestimations in Recreational Scuba Diving Operations: A European Study Supporting the Implementation of New Risk Management Programmes.

Introduction: Scuba diving is an important marine tourism sector, but requires proper safety standards to reduce the risks and increase accessibility to its market. To achieve safety goals, safety awareness and positive safety attitudes in recreational scuba diving operations are essential. However, there is no published research exclusively focusing on scuba divers' and dive centres' perceptions toward safety. This study assessed safety perceptions in recreational scuba diving operations, with the aim to inform and enhance safety and risk management programmes within the scuba diving tourism industry. Materials and Methods: Two structured questionnaire surveys were prepared by the organisation Divers Alert Network and administered online to scuba diving operators in Italy and scuba divers in Europe, using a mixture of convenience and snowball sampling. Questions in the survey included experience and safety offered at the dive centre; the buddy system; equipment and accessories for safe diving activities; safety issues in the certification of new scuba divers; incidents/accidents; and attitudes toward safety. Results: 91 scuba diving centres and 3,766 scuba divers participated in the study. Scuba divers gave importance to safety and the responsiveness of service providers, here represented by the dive centres. However, they underestimated the importance of a personal emergency action/assistance plan and, partly, of the buddy system alongside other safety procedures. Scuba divers agreed that some risks, such as those associated with running out of gas, deserve attention. Dive centres gave importance to aspects such as training and emergency action/assistance plans. However, they were limitedly involved in safety campaigning. Dive centres' perceptions of safety in part aligned with those of scuba divers, with some exceptions. Conclusion: Greater responsibility is required in raising awareness and educating scuba divers, through participation in prevention campaigns and training. The study supports the introduction of programmes aiming to create a culture of safety among dive centres and scuba divers. Two examples, which are described in this paper, include the Hazard Identification and Risk Assessment protocol for dive centres and scuba divers, and the Diving Safety Officer programme to create awareness, improve risk management, and mitigate health and safety risks.