Search Results

Estimate bone mineral content (BMC in grams) and bone mineral density (BMD in grams/cm²) in the distal section of the forearm.

The DTX-200 candidate device is a dual energy system, where the measured object, in this case the forearm, is submerged into a soft tissue equivalent water bath. The X-Ray generator is driven at 55 Kv, with a current of 0.3 mAmps. The detector uses a scintillating crystal and a solid state dual energy sandwich detector. A highly stable X-Ray output, together with a source collimation of 1 mm diameter, and excellent pixel resolution, yields images of very high quality. The typical time to estimate bone mineral content and bone mineral density is approximately 3.0 to 4.5 minutes. The effective patient dose is estimated to be 0.1 micro Sievert per scan. Both the DTX-200 candidate and the DTX-200 predicate bone densitometer devices consist of a computer, keyboard, monitor, printer, and scanner system using an X-ray transmission source. The DTX-200 candidate device and the DTX-200 predicate device are identical and use dual X-ray photon absorptiometry (DXA) to estimate bone mineral content (BMC) and bone mineral density (BMD). Both the candidate and predicate DTX-200 devices are identical and use water as soft tissue equivalent material. Both the DTX-200 candidate device and the DTX-200 predicate device use a line-by-line calibration system, ensuring good precision.

The provided text describes the 510(k) summary for the DTX-200 Bone Densitometer. However, it does not contain specific acceptance criteria or details of a study designed to prove the device meets such criteria.

The document primarily focuses on establishing substantial equivalence to a predicate device (also a DTX-200 Bone Densitometer) by comparing technological characteristics and intended use. The "clinical tests" described are not designed to test the device's accuracy or precision against specific acceptance criteria, but rather to establish a reference database for a normal American female caucasian population.

Therefore, I cannot fulfill your request for a table of acceptance criteria and reported device performance, or details about the study proving it meets those criteria, as this information is not present in the provided text.

Here is what can be extracted or inferred from the provided text regarding the closest relevant information, though it does not directly address acceptance criteria for performance:

1. Table of Acceptance Criteria and Reported Device Performance: This information is not explicitly stated in the document. The document states that "Accuracy and precision error of the DTX-200 candidate device is comparable to that of the DTX-200 predicate device," but does not provide specific numerical acceptance criteria or reported values for either device.

2. Sample size used for the test set and the data provenance:

   • Sample Size: "at least 50 persons in ten year peer age groups" for each clinical study, to establish a reference data base. The studies covered ages 20 to 80, implying 6 age groups (20-29, 30-39, ..., 70-79). So, a minimum of 6 * 50 = 300 women per study, and a total of at least 600 women across both studies.
   • Data Provenance:
     • Country of Origin: USA (Helen Hayes Hospital, West Haverstraw, NY; United States Department of Agriculture Human Nutrition Research Center on Aging at Tufts University, Boston, MA).
     • Retrospective or Prospective: Prospective, as the studies involved "Determination of Forearm Bone Density in a Normal US Population" and "Mineral Density in a Normal American Population" conducted over specific timeframes (Feb-Sep 1996 and Mar-Oct 1996).

3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts: Not applicable. The "clinical tests" were to establish a reference database of normal bone density values, not to establish a "ground truth" for diagnostic accuracy or performance against a standard. The measurements were taken directly by the device itself to form this database.

4. Adjudication method (e.g. 2+1, 3+1, none) for the test set: Not applicable, as there was no expert adjudication of device outputs or diagnoses. The device directly measured BMC and BMD.

5. If a multi reader multi case (MRMC) comparative effectiveness study was done, If so, what was the effect size of how much human readers improve with AI vs without AI assistance: Not applicable. This device is a bone densitometer, not an AI-assisted diagnostic tool that involves human readers interpreting images.

6. If a standalone (i.e. algorithm only without human-in-the loop performance) was done: The device's performance, in terms of measuring BMC and BMD, is inherently standalone. The clinical studies collected these measurements directly from the device. However, specific standalone performance metrics (e.g., accuracy, precision values) are not provided, only a statement of comparability to the predicate device.

7. The type of ground truth used (expert consensus, pathology, outcomes data, etc): Not applicable in the traditional sense of a diagnostic device. The "ground truth" here is the measurement of BMC and BMD taken by the device from a "normal American female caucasian" population to establish a reference database. There wasn't an external "gold standard" used to validate individual measurements against, but rather the statistical representativeness of the collected data for the target population.

8. The sample size for the training set: Not applicable. The "clinical tests" described were for establishing a reference database for a normal population, which serves as a statistical comparison point for future patient measurements, not for "training" an algorithm in the sense of machine learning. The device itself is a measurement instrument, not a learning algorithm that requires a training set.

9. How the ground truth for the training set was established: Not applicable, as there was no training set in the context of machine learning.

Ask a specific question about this device

To estimate bone mineral content (BMC, grams) and bone mineral density (BMD, grams/cm').

The DTX-200 candidate device is a dual energy system, where the measured object, in this case the forearm, by the software, i s divided into two compartments, bone and soft-tissue. Having two energies, and two compartments (unknowns) it is possible to establish and solve two formulae with two unknowns. The X-Ray generator is driven at 55 kV , with a current of 300 yAmps. The beam is filtered with Tin (Sn), using the K-Edge of this material to enhance the separation of the low and the high energy. The average energy peaks are approximately 29 keV, and 46 keV respectively. A highly stable X-Ray output, together with a source collimation of 1 mm and a pixel resolution of 0.4mm X 0.4mm, yields images of very high quality. The detector is a sandwich construction, using solid state photodiodes consisting of two diodes with scintillation material. The two energies are separated by the sandwich construction. The X-ray beam meets the first scintillator, where predominantly the low energy is detected, and then it meets the second scintillator, where the rest of the energy is detected. The typical time to estimate bone mineral content and bone mineral density is approximately 4 minutes. The effective patient dose is estimated to be 0.1 micro Sievert per scan.

Here's a breakdown of the acceptance criteria and the studies performed for the DTX-200 Bone Densitometer, based on the provided 510(k) summary:

1. Table of Acceptance Criteria and Reported Device Performance

The provided text focuses on demonstrating substantial equivalence to predicate devices rather than explicit, numerical acceptance criteria for a novel device. The primary performance metrics evaluated are functional correlation and precision.

• Linear regression analysis was used to determine the degree of correlation between DTX-200 and DTX-100 for BMC and BMD measurements at the 8mm distal site and ultra distal site in the non-dominant forearm.
• Conclusion: "The clinical study on eighty one (81) patients showed the DTX-200 candidate device and the DTX-100 predicate device are substantially equivalent in their ability estimate bone mineral content (BMC) and bone mineral density (BMD)." |
  | Precision: The DTX-200 candidate device should be able to estimate bone mass with precision errors that allow for the detection of clinically meaningful differences between repeated bone scans in the same individual. | Precision Study:
• Precision estimates were calculated as the coefficient of variation (CV) at a 95% confidence interval using log-transformed data for BMC and BMD measurements.
• Conclusion: "The results of the clinical study on fifteen (15) individuals shows that the DTX-200 candidate device estimates bone mass with precision errors in an order that makes it possible to detect clinically meaningful differences between repeated bone scans in the same individual." |
  | Comparability to Predicate Devices (General): Design, material, chemical composition, energy source, and other technological characteristics (e.g., precision, accuracy error) should be comparable to predicate devices. | Technological Characteristics Section:
• States that these characteristics "are considered to be the same as the technological characteristics of the predicate devices."
• Precision: "The precision of the devices [DTX-200, DTX-100, QDR-1000/W] is comparable."
• Accuracy and precision error: "Accuracy and precision error of the DTX-200 candidate device is comparable to that of the DTX-100 predicate device and the QDR-1000/W predicate device." |

2. Sample Size Used for the Test Set and the Data Provenance

• Functional Correlation Study:

  • Sample Size: 81 individuals
  • Data Provenance: Not explicitly stated whether retrospective or prospective, nor the country of origin. However, the study was sponsored by the device manufacturer (Osteometer Meditech A/S, Denmark), suggesting it was likely conducted in or around their location.

• Precision Study:

  • Sample Size: 15 individuals
  • Data Provenance: Not explicitly stated whether retrospective or prospective, nor the country of origin. Similar to the correlation study, sponsored by the manufacturer.

3. Number of Experts Used to Establish the Ground Truth for the Test Set and the Qualifications of Those Experts

The studies described in the 510(k) summary do not involve "experts" establishing a ground truth in the traditional sense of diagnostic interpretation. Instead, the ground truth is established by the measurements from the predicate device (DTX-100) for the functional correlation study, and the repeated measurements by the DTX-200 itself for the precision study. Therefore, no information on the number or qualifications of experts is provided for determining ground truth in these specific studies.

4. Adjudication Method for the Test Set

Not applicable. The studies are based on quantitative measurements from devices, not human interpretation requiring adjudication.

5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study Was Done, If So, What Was the Effect Size of How Much Human Readers Improve with AI vs Without AI Assistance

No, a Multi-Reader Multi-Case (MRMC) comparative effectiveness study was not done. The DTX-200 is a bone densitometer (device-only measurement), not an AI-assisted diagnostic tool that would involve human readers.

6. If a Standalone (i.e., algorithm only without human-in-the-loop performance) Was Done

Yes, the studies presented are effectively standalone evaluations of the device's performance. The DTX-200 bone densitometer operates as an algorithm-only device (though it lacks AI in the modern sense) without human intervention in the measurement process itself, beyond operating the machine. The studies evaluate the device's measurements directly.

7. The Type of Ground Truth Used

• Functional Correlation Study: The "ground truth" for the DTX-200's performance was the measurements obtained from the predicate device, the DTX-100 bone densitometer. The study aimed to show strong correlation with an already accepted device.
• Precision Study: The "ground truth" for evaluating precision was the mean of the multiple repeated measurements from the DTX-200 itself for each individual. The goal was to quantify the variability of the device's own measurements.
• For the referenced published literature (2A-2E), the ground truth varies depending on the study (e.g., in vivo bone mineral measurements, in vitro phantom measurements, cadaver studies, comparative measurements between different densitometry methods).

8. The Sample Size for the Training Set

The provided 510(k) summary describes performance evaluation studies (test sets) but does not mention any "training set." This is consistent with devices from this era, where machine learning/AI models requiring training data were not typically employed in this manner for medical device clearance. The DTX-200 uses established physics-based principles (DXA) rather than a data-driven model that would necessitate a training set.

9. How the Ground Truth for the Training Set Was Established

Not applicable, as there is no mention of a training set for the DTX-200.

Ask a specific question about this device