Abstract: A laser beam treatment system that delivers laser beam pulses to a dental treatment area according to a particular pattern is described. In various instances, the spacing of the pattern (e.g., locations at which pulses are delivered and the distances therebetween) and/or the timing of the pattern (e.g., amount of time between the delivery of pulses to a first location and a later location that abuts the first location) can have a demonstrable effect on ablation performance. The effects can include, for example: improved ablation efficiency, improved surface smoothness, improved material removal rate, and/or the absence of melt, carbonization or other negative surface features.

Abstract: A dental laser system for treatment of hard and/or soft tissue includes a main chamber housing optical and primary fluid supply subsystems, for directing a laser beam and fluid to a treatment area. A hand piece affixable to the main chamber, includes mating optical and secondary fluid supply subsystems. The hand piece can be rotatable or re-orientable about an optical axis within the hand piece. A lock can maintain a selectable angular orientation of the hand piece relative to the main chamber. A coupling can maintain a fluidic communication between the primary and secondary fluid supply subsystems even when the hand piece is rotated or re-oriented. A sensor and controller can sense a selected angular orientation of the hand piece and adjust the main optical subsystem according to the sensed angular orientation, to align the two optical subsystems. The laser may be controlled using a variable speed foot pedal.

Abstract: Data characterizing a plurality of sensor generated events is received. Thereafter, analysis of the plurality of events is initiated using a decision tree with splits performed on decision keys. A first portion of the decision keys comprising analyst-selected splits can be derived from user-generated domain knowledge regarding a first plurality of historical events. A second portion of the decision keys comprising software-driven splits can be derived from a predictive model trained using a second plurality of historical events. Later, a disposition is determined for each event based on a traversal of at least one of the decision keys in the decision tree and such disposition is later initiated. Related apparatus, systems, techniques and articles are also described.